<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" media="screen" href="/~d/styles/rss2full.xsl"?><?xml-stylesheet type="text/css" media="screen" href="http://feeds.feedburner.com/~d/styles/itemcontent.css"?><rss xmlns:sas="http://www.sas.com" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:feedburner="http://rssnamespace.org/feedburner/ext/1.0" version="2.0">
<channel>
	<title>SAS Blogs » RSS</title>
	<link>http://blogs.sas.com/content/network-rss?feed=networkrss</link>
	
	<description>Connecting you to people, products &amp; ideas from SAS</description>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<atom10:link xmlns:atom10="http://www.w3.org/2005/Atom" rel="self" type="application/rss+xml" href="http://feeds.feedburner.com/sasblogs" /><feedburner:info uri="sasblogs" /><atom10:link xmlns:atom10="http://www.w3.org/2005/Atom" rel="hub" href="http://pubsubhubbub.appspot.com/" /><feedburner:emailServiceId>sasblogs</feedburner:emailServiceId><feedburner:feedburnerHostname>http://feedburner.google.com</feedburner:feedburnerHostname><item>
		<title><![CDATA[BarLine Graphs]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/qfNg6hhZQcQ/</link>
                <dc:creator>Sanjay Matange</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/graphicallyspeaking/wp-content/blogs.dir/28/files/userphoto/250.thumbnail.jpg" alt="Sanjay Matange" width="56" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>Graphically Speaking</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/graphicallyspeaking/?p=3949</guid>
		<pubDate>Tue, 18 Jun 13 11:07:38 +0000</pubDate>
        <description><![CDATA[A Bar Line graph is commonly used in many domains.  The SGPLOT procedure makes it easy to create bar line graphs where the user can customize it in many different ways.  This post is prompted by a recent question on the communities page on creating such a graph, with one bar and multiple line plots.

Bar Line with Multi Column Data:

This graph is easily done using the SGPLOT procedure when the data set has the response columns by category, one for the bar and one for each line as shown below:



Here is a basic bar line graph with  the Sum represented as the bar on the left Y axis, and all the percent values on the right Y2 axis.



SGPLOT code:
proc sgplot data=testcols;
  title 'Sum and Percent by Week and Operation';
  vbar week / response=sum fillattrs=graphdatadefault nostatlabel;
  vline week /  response=A lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=B lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=C lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=D lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=E lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=F lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  xaxis display=(nolabel);
  yaxis offsetmin=0  display=(nolabel) ;
  y2axis offsetmin=0 display=(nolabel);
  run;
Note the following:

	We have used a VBAR statement to display sum x week.
	We have used multiple VLINE statements to display each % by week.
	We have set offsetmin=0 for both Y and Y2 axis.  This ensures the bars start from the x axis.
	NOSTATLABEL prevents the addition of the statistics to the labels and legends.
	The Y and Y2 axis ticks are not aligned, so it is hard to draw grid lines.

To add Y axis grid lines, it is important to align the tick values on both axes.  These can be aligned by setting the tick values on each axis by setting the VALUES option.  Here is the resulting graph:



Here we have used the VALUES option on both Y and Y2 axis to get equal number of ticks on each axis.  Now we can enable GRID on the Y axis.  The bar is made a bit transparent so the grid lines show through.

Bar Line with Grouped Data:

If the data is in grouped format, we can create a similar graph except that it is necessary that both the VBAR and VLINE statements have the same combination of CATEGORY and GROUP variables.  Since VLINE are grouped by operation, we also have to use the same group variable for VBAR.  To ensure we only get one bar, provide only one non-missing value per category.  Here is the data for the grouped case:

Only 3 values of operation are shown to save space.  Note that only the first operation has a non-missing value for sum, and all others have missing value.

Here is the graph and the SGPLOT code.  Note, in this graph, we have used a data skin, and curve labels.  Curve labels often improve the readability of the graph, and no legend is required.



SGPLOT code:
proc sgplot data=test noautolegend;
  title 'Sum and Percent by Week and Operation';
  vbar week / group=operation response=sum_week fillattrs=graphdatadefault
       nostatlabel transparency=0.2 dataskin=gloss;
  vline week / group=operation response=percent y2axis
        lineattrs=(thickness=5 pattern=solid) nostatlabel curvelabel;
  xaxis display=(nolabel);
  yaxis offsetmin=0 offsetmax=0.1 values=(0 to 8000 by 2000)
        display=(nolabel) grid;
  y2axis  offsetmin=0 offsetmax=0.1 values=(0 to 0.4 by 0.1)
        display=(nolabel);
  run;
Full SAS 9.3 SGPLOT code: BarLine]]></description>
        <content:encoded><![CDATA[A Bar Line graph is commonly used in many domains.  The SGPLOT procedure makes it easy to create bar line graphs where the user can customize it in many different ways.  This post is prompted by a recent question on the communities page on creating such a graph, with one bar and multiple line plots.

<strong>Bar Line with Multi Column Data:</strong>

This graph is easily done using the SGPLOT procedure when the data set has the response columns by category, one for the bar and one for each line as shown below:

<a href="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/DataCols.png"><img class="aligncenter size-full wp-image-3950" src="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/DataCols.png" alt="" width="425" height="115" /></a>

Here is a basic bar line graph with  the Sum represented as the bar on the left Y axis, and all the percent values on the right Y2 axis.

<a href="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/BarLineCols12.png"><img class="aligncenter size-full wp-image-3954" src="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/BarLineCols12.png" alt="" width="500" height="300" /></a>

<strong>SGPLOT code:</strong>
<pre lang="sas">proc sgplot data=testcols;
  title 'Sum and Percent by Week and Operation';
  vbar week / response=sum fillattrs=graphdatadefault nostatlabel;
  vline week /  response=A lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=B lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=C lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=D lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=E lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  vline week /  response=F lineattrs=(thickness=5 pattern=solid) nostatlabel y2axis;
  xaxis display=(nolabel);
  yaxis offsetmin=0  display=(nolabel) ;
  y2axis offsetmin=0 display=(nolabel);
  run;</pre>
Note the following:
<ul>
	<li>We have used a VBAR statement to display sum x week.</li>
	<li>We have used multiple VLINE statements to display each % by week.</li>
	<li>We have set offsetmin=0 for both Y and Y2 axis.  This ensures the bars start from the x axis.</li>
	<li>NOSTATLABEL prevents the addition of the statistics to the labels and legends.</li>
	<li>The Y and Y2 axis ticks are not aligned, so it is hard to draw grid lines.</li>
</ul>
To add Y axis grid lines, it is important to align the tick values on both axes.  These can be aligned by setting the tick values on each axis by setting the VALUES option.  Here is the resulting graph:

<a href="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/BarLineCols2.png"><img class="aligncenter size-full wp-image-3953" src="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/BarLineCols2.png" alt="" width="500" height="300" /></a>

Here we have used the VALUES option on both Y and Y2 axis to get equal number of ticks on each axis.  Now we can enable GRID on the Y axis.  The bar is made a bit transparent so the grid lines show through.

<strong>Bar Line with Grouped Data:</strong>

If the data is in grouped format, we can create a similar graph except that <strong>it is necessary that both the VBAR and VLINE statements have the same combination of CATEGORY and GROUP variables.</strong>  Since VLINE are grouped by operation, we also have to use the same group variable for VBAR.  To ensure we only get one bar, provide only one non-missing value per category.  Here is the data for the grouped case:

<a href="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/Data1.png"><img class="aligncenter size-full wp-image-3956" src="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/Data1.png" alt="" width="263" height="197" /></a>Only 3 values of operation are shown to save space.  Note that only the first operation has a non-missing value for sum, and all others have missing value.

Here is the graph and the SGPLOT code.  Note, in this graph, we have used a data skin, and curve labels.  Curve labels often improve the readability of the graph, and no legend is required.

<a href="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/BarLineGrp.png"><img class="aligncenter size-full wp-image-3957" src="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/BarLineGrp.png" alt="" width="500" height="300" /></a>

<strong>SGPLOT code:</strong>
<pre lang="sas">proc sgplot data=test noautolegend;
  title 'Sum and Percent by Week and Operation';
  vbar week / group=operation response=sum_week fillattrs=graphdatadefault
       nostatlabel transparency=0.2 dataskin=gloss;
  vline week / group=operation response=percent y2axis
        lineattrs=(thickness=5 pattern=solid) nostatlabel curvelabel;
  xaxis display=(nolabel);
  yaxis offsetmin=0 offsetmax=0.1 values=(0 to 8000 by 2000)
        display=(nolabel) grid;
  y2axis  offsetmin=0 offsetmax=0.1 values=(0 to 0.4 by 0.1)
        display=(nolabel);
  run;</pre>
<strong>Full SAS 9.3 SGPLOT code: <a href="http://blogs.sas.com/content/graphicallyspeaking/files/2013/06/BarLine.txt">BarLine</a></strong><div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=qfNg6hhZQcQ:DQuIBlmhVc0:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=qfNg6hhZQcQ:DQuIBlmhVc0:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=qfNg6hhZQcQ:DQuIBlmhVc0:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=qfNg6hhZQcQ:DQuIBlmhVc0:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=qfNg6hhZQcQ:DQuIBlmhVc0:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=qfNg6hhZQcQ:DQuIBlmhVc0:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=qfNg6hhZQcQ:DQuIBlmhVc0:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=qfNg6hhZQcQ:DQuIBlmhVc0:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/qfNg6hhZQcQ" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/graphicallyspeaking/2013/06/18/grouped-barline-graph/</feedburner:origLink></item>
	<item>
		<title><![CDATA[Antworten dort finden, wo auch die Fragen gestellt werden]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/pDhfgI6ZKmQ/</link>
                <dc:creator>Thomas Keil</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/sasdach/wp-content/blogs.dir/34/files/userphoto/514.thumbnail.jpg" alt="Thomas Keil" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>Mehr Wissen</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/sasdach/?p=1506</guid>
		<pubDate>Mon, 17 Jun 13 18:12:03 +0000</pubDate>
        <description><![CDATA[Aus ihren Daten wirklich Nutzen zu ziehen, können viele Unternehmen. Das Finden von Mustern mit Data Mining gibt es seit Jahrzehnten, eine ähnliche Historie weisen Forecasting oder Predictive Analytics auf. Je nach Datenart und Anforderung gibt es hier schon sehr lange valide, reliable und vor allem alltags- sowie business-relevante Methoden – denken wir nur an so alltägliche Bereiche wie Wettervorhersagen und Stauprognosen.

Wenn ich aber sage „Unternehmen“ können dies, muss man ehrlicherweise hinzufügen, dass damit in der Realität vereinzelte Experten in spezialisierten Abteilungen gemeint sind, die zum allergrößten Teil eine mathematische oder sogar statistische Ausbildung, meist ein Studium, mitbringen. Das liegt in der Natur der Sache: Sobald man sich über Intuition und gefühlte Realität („Bei Ferienbeginn staut es sich am Brenner“ oder „im Sommer wird mehr Eis verkauft“) hinaus begibt, geht es eben um die Entwicklung von Vorhersagemodellen mit mathematischen Algorithmen. In der wissenschaftlichen Diskussion ist das disziplinübergreifend akzeptiert: Ohne mathematische Kenntnisse sind alle empirischen Wissenschaften von Maschinenbau bis zu den Sozialwissenschaften nicht denkbar. Nicht umsonst gehört ein Statistik-Grundkurs mittlerweile in die Lehrpläne vieler Studiengänge. Aber auch in den Unternehmen setzt sich diese Erkenntnis immer mehr durch.

Mathematik - die Grundlage für wirtschaftlichen Erfolg?

Eine stetig fortschreitende Rationalisierung des Wirtschaftslebens hat dafür gesorgt, dass jegliche Entscheidungen in ihren Auswirkungen nicht nur auf Fakten basieren sollten, sondern dies eben auch können. Anders gesagt: die Voraussetzungen für eine Mathematisierung der Unternehmensführung sind durch die massenhafte Verbreitung entsprechender Technologien geschaffen. Die Überlegung ist einfach: Nur was gemessen werden kann, kann auch gemanagt werden (Peter Drucker). Und je mehr ich messen kann, desto mehr kann ich managen und damit womöglich einen Wettbewerbsvorsprung erarbeiten.

Das führt ganz zwangsläufig dazu, dass immer mehr Messdaten erhoben werden: Wie viele Produkte habe ich in welchem Verkaufskanal zu welchem Preis verkauft? Welche Produkte bietet mein Wettbewerber an? Welche Kunden sind für mich profitabel? Diese Fragen sind heute beantwortbar – und liefern die Grundlage für die oben genannten „Unternehmen“, die heute Vorhersagen, Data-Mining und Predictive Analytics einsetzen.

Damit hat sich aber eine Lücke aufgetan: Die Fragen bezüglich den Messpunkten und den möglichen Ableitungen für die Zukunft nähren sich aus den Herausforderungen des jeweiligen Unternehmens und des jeweiligen Geschäftsmodells. Dazu ist tiefes Fachwissen erforderlich, ob es um Bereiche wie Produktionsoptimierung, Vertrieb- und Marketing oder logistische Fragestellungen geht. Die gut ausgebildeten Mitarbeiter in diesen Fachbereichen bringen aber nur ein Grundgerüst an mathematischen Kenntnissen mit, keineswegs die „High-End“-Anforderungen, die an die Entwicklung von Vorhersagemodellen, neuronalen Netzen und anderen, mittlerweile gängigen Verfahren gestellt werden.

Und wenn die Frage zur Antwort kommt - anstatt immer den Berg zum Propheten zu schicken?

Wie wäre es nun aber, wenn die Antworten dort gefunden werden könnten, wo auch die Fragen gestellt werden? Und damit die Entwicklung neuer Fragen gefördert und ermöglicht wird? Das zu ermöglichen ist die alles entscheidende Triebfeder in der aktuellen Big-Data-Diskussion. Wie schaffen es Unternehmen, die Nutzung von fortgeschrittenen mathematischen Verfahren zu verbreitern und damit neue Effizienzen in ihren Kernprozessen zu heben. Die Mathematik ist nicht einfacher zu machen, als sie ist. Die Daten sind so, wie sie sind. Und auch die Menschen sind so, wie sie sind. Zu glauben, man könne jetzt einfach überall „Data Scientists“ einstellen, ist naiv – diese Leute gibt es nicht in ausreichender Zahl.

Der Weg muss ganz klar dahin gehen, die Nutzung von Analytics so einfach wie die Bedienung von Outlook und Powerpoint zu machen. Diesen Weg geht nicht ganz überraschend einer der Pioniere der Statistik unter zu Hilfenahme neuester Technologien – mit SAS Visual Analytics. Die Visualisierungen machen Bedienung, Exploration und Verständnis der Ergebnisse um ein Vielfaches leichter – und damit Analytics erstmals wirklich greifbar für den Fachbereich. Der ausgebildete Statistiker wird dort vieles vermissen und trotzdem die Qualität der Ergebnisse mit seinen eigenen vergleichen können. Aber für viele Mitarbeiter in vielen Unternehmen ist das eine ganz große Chance, faktenbasierte Entscheidungen auf eine neue Qualitätsebene zu heben. Ich würde sagen „Self-Service-Business Analytics“ (nicht nur Self-Service-BI) ist der Schlüssel, für den Nutzen von Daten, meinetwegen auch von Big Data.

Wie Unternehmen visuelle Analysen nutzen und welche Erfahrungen bereits heute mit Self-Service-Ansätzen gemacht wurden, erfahren Sie auch auf dem SAS Forum 2013 am 11. und 12. September 2013 in Mannheim.]]></description>
        <content:encoded><![CDATA[Aus ihren Daten wirklich Nutzen zu ziehen, können viele Unternehmen. Das Finden von Mustern mit <a href="http://de.wikipedia.org/wiki/Data-Mining" target="_blank">Data Mining</a> gibt es seit Jahrzehnten, eine ähnliche Historie weisen Forecasting oder Predictive Analytics auf. Je nach Datenart und Anforderung gibt es hier schon sehr lange valide, reliable und vor allem alltags- sowie business-relevante Methoden – denken wir nur an so alltägliche Bereiche wie Wettervorhersagen und Stauprognosen.

Wenn ich aber sage „Unternehmen“ können dies, muss man ehrlicherweise hinzufügen, dass damit in der Realität vereinzelte Experten in spezialisierten Abteilungen gemeint sind, die zum allergrößten Teil eine mathematische oder sogar statistische Ausbildung, meist ein Studium, mitbringen. Das liegt in der Natur der Sache: Sobald man sich über Intuition und gefühlte Realität („Bei Ferienbeginn staut es sich am Brenner“ oder „im Sommer wird mehr Eis verkauft“) hinaus begibt, geht es eben um die Entwicklung von Vorhersagemodellen mit mathematischen Algorithmen. In der wissenschaftlichen Diskussion ist das disziplinübergreifend akzeptiert: Ohne mathematische Kenntnisse sind alle <a href="http://www.scilogs.de/wblogs/blog/sprachlog/allgemein/2010-05-04/keine-wissenschaft-ohne-mathematik" target="_blank">empirischen Wissenschaften von Maschinenbau bis zu den Sozialwissenschaften</a> nicht denkbar. Nicht umsonst gehört ein Statistik-Grundkurs mittlerweile in die Lehrpläne vieler Studiengänge. Aber auch in den Unternehmen setzt sich diese Erkenntnis immer mehr durch.

<strong>Mathematik - die Grundlage für wirtschaftlichen Erfolg?</strong>

Eine stetig fortschreitende Rationalisierung des Wirtschaftslebens hat dafür gesorgt, dass jegliche Entscheidungen in ihren Auswirkungen nicht nur auf Fakten basieren sollten, sondern dies eben auch können. Anders gesagt: die Voraussetzungen für eine Mathematisierung der Unternehmensführung sind durch die massenhafte Verbreitung entsprechender Technologien geschaffen. Die Überlegung ist einfach: Nur was gemessen werden kann, kann auch gemanagt werden (Peter Drucker). Und je mehr ich messen kann, desto mehr kann ich managen und damit womöglich einen Wettbewerbsvorsprung erarbeiten.

Das führt ganz zwangsläufig dazu, dass immer mehr Messdaten erhoben werden: Wie viele Produkte habe ich in welchem Verkaufskanal zu welchem Preis verkauft? Welche Produkte bietet mein Wettbewerber an? Welche Kunden sind für mich profitabel? Diese Fragen sind heute beantwortbar – und liefern die Grundlage für die oben genannten „Unternehmen“, die heute Vorhersagen, Data-Mining und Predictive Analytics einsetzen.

Damit hat sich aber eine Lücke aufgetan: Die Fragen bezüglich den Messpunkten und den möglichen Ableitungen für die Zukunft nähren sich aus den Herausforderungen des jeweiligen Unternehmens und des jeweiligen Geschäftsmodells. Dazu ist tiefes Fachwissen erforderlich, ob es um Bereiche wie Produktionsoptimierung, Vertrieb- und Marketing oder logistische Fragestellungen geht. Die gut ausgebildeten Mitarbeiter in diesen Fachbereichen bringen aber nur ein Grundgerüst an mathematischen Kenntnissen mit, keineswegs die „High-End“-Anforderungen, die an die Entwicklung von Vorhersagemodellen, neuronalen Netzen und anderen, mittlerweile gängigen Verfahren gestellt werden.

<strong>Und wenn die Frage zur Antwort kommt - anstatt immer den Berg zum Propheten zu schicken?</strong>

Wie wäre es nun aber, wenn die Antworten dort gefunden werden könnten, wo auch die Fragen gestellt werden? Und damit die Entwicklung neuer Fragen gefördert und ermöglicht wird? Das zu ermöglichen ist die alles entscheidende Triebfeder in der aktuellen Big-Data-Diskussion. Wie schaffen es Unternehmen, die Nutzung von fortgeschrittenen mathematischen Verfahren zu verbreitern und damit neue Effizienzen in ihren Kernprozessen zu heben. Die Mathematik ist nicht einfacher zu machen, als sie ist. Die Daten sind so, wie sie sind. Und auch die Menschen sind so, wie sie sind. Zu glauben, man könne jetzt einfach überall „Data Scientists“ einstellen, ist naiv – diese <a href="http://www.cio.com/article/733898/The_Rise_of_the_Data_Visualization_Expert">Leute</a> gibt es nicht in ausreichender Zahl.

Der Weg muss ganz klar dahin gehen, die Nutzung von Analytics so einfach wie die Bedienung von Outlook und Powerpoint zu machen. Diesen Weg geht nicht ganz überraschend einer der Pioniere der Statistik unter zu Hilfenahme neuester Technologien – mit SAS Visual Analytics. Die Visualisierungen machen Bedienung, Exploration und Verständnis der Ergebnisse um ein Vielfaches leichter – und damit Analytics erstmals wirklich greifbar für den Fachbereich. Der ausgebildete Statistiker wird dort vieles vermissen und trotzdem die Qualität der Ergebnisse mit seinen eigenen vergleichen können. Aber für viele Mitarbeiter in vielen Unternehmen ist das eine ganz große Chance, faktenbasierte Entscheidungen auf eine neue Qualitätsebene zu heben. Ich würde sagen „Self-Service-Business Analytics“ (nicht nur Self-Service-BI) ist der Schlüssel, für den Nutzen von Daten, meinetwegen auch von Big Data.

Wie Unternehmen visuelle Analysen nutzen und welche Erfahrungen bereits heute mit Self-Service-Ansätzen gemacht wurden, erfahren Sie auch auf dem <a title="SAS Forum 2013" href="http://www.sasforum.de" target="_blank">SAS Forum 2013</a> am 11. und 12. September 2013 in Mannheim.<div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=pDhfgI6ZKmQ:tQvHjVk8qVY:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=pDhfgI6ZKmQ:tQvHjVk8qVY:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=pDhfgI6ZKmQ:tQvHjVk8qVY:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=pDhfgI6ZKmQ:tQvHjVk8qVY:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=pDhfgI6ZKmQ:tQvHjVk8qVY:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=pDhfgI6ZKmQ:tQvHjVk8qVY:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=pDhfgI6ZKmQ:tQvHjVk8qVY:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=pDhfgI6ZKmQ:tQvHjVk8qVY:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/pDhfgI6ZKmQ" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/sasdach/2013/06/17/antworten-dort-finden-wo-auch-die-fragen-gestellt-werden/</feedburner:origLink></item>
	<item>
		<title><![CDATA[My, how quality has changed!]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/5jb42SSwwOA/</link>
                <dc:creator>Bernard McKeown</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/jmp/wp-content/blogs.dir/3/files/userphoto/195.thumbnail.jpg" alt="Bernard McKeown" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>JMP Blog</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/jmp/?p=9154</guid>
		<pubDate>Mon, 17 Jun 13 11:30:23 +0000</pubDate>
        <description><![CDATA[Since I took my degree in engineering in the late 1980s, things have changed dramatically in the world of quality. The Six Sigma strategy was developed in 1986, with Total Quality Management (TQM) in its infancy by the turn of the decade. In the intervening years, engineers have been deluged by a flood of data collected from increasingly complex and sensitive equipment while being continually challenged by growing customer expectations. It’s become increasingly important for engineers to have the right software to calibrate equipment and collect and analyse data in a fast, efficient and coherent way. And it’s for these reasons that JMP, with its easy-to-use, point-and-click environment, is increasingly the software of choice to analyse quality data.

We are holding a seminar on 3 July in Marlow in the UK that showcases how JMP can be used to analyse data in a variety of manufacturing situations to:

	Troubleshoot quality problems
	Improve manufacturing yield
	Improve the capability of your measurement system
	Control complex manufacturing processes

If these are concerns to you, then why not register and join us for the day?

We will be following this seminar up with one on a related topic: design of experiments. Two global thought leaders, Bradley Jones and Peter Goos, will be leading the event, which will take place on 19 Sept.]]></description>
        <content:encoded><![CDATA[Since I took my degree in engineering in the late 1980s, things have changed dramatically in the world of quality. The Six Sigma strategy was developed in 1986, with Total Quality Management (TQM) in its infancy by the turn of the decade. In the intervening years, engineers have been deluged by a flood of data collected from increasingly complex and sensitive equipment while being continually challenged by growing customer expectations. It’s become increasingly important for engineers to have the right software to calibrate equipment and collect and analyse data in a fast, efficient and coherent way. And it’s for these reasons that <a href="http://jmp.com/software">JMP</a>, with its easy-to-use, point-and-click environment, is increasingly the software of choice to analyse quality data.

We are holding a seminar on <strong>3 July in Marlow in the UK</strong> that showcases how JMP can be used to analyse data in a variety of manufacturing situations to:
<ul>
	<li>Troubleshoot quality problems</li>
	<li>Improve manufacturing yield</li>
	<li>Improve the capability of your measurement system</li>
	<li>Control complex manufacturing processes</li>
</ul>
If these are concerns to you, then why not <a href="http://www.jmp.com/uk/about/events/explorers/seminar_detail.shtml?reglink=70130000001qbQ3">register</a> and join us for the day?

We will be following this seminar up with one on a related topic: design of experiments. Two global thought leaders, <a href="http://blogs.sas.com/content/jmp/author/bradleyjones/">Bradley Jones</a> and Peter Goos, will be leading the event, which will take place on 19 Sept.<div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=5jb42SSwwOA:ls8Ogzn9FLM:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=5jb42SSwwOA:ls8Ogzn9FLM:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=5jb42SSwwOA:ls8Ogzn9FLM:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=5jb42SSwwOA:ls8Ogzn9FLM:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=5jb42SSwwOA:ls8Ogzn9FLM:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=5jb42SSwwOA:ls8Ogzn9FLM:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=5jb42SSwwOA:ls8Ogzn9FLM:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=5jb42SSwwOA:ls8Ogzn9FLM:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/5jb42SSwwOA" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/jmp/2013/06/17/my-how-quality-has-changed/</feedburner:origLink></item>
	<item>
		<title><![CDATA[The book writing business: Publishing across the world with Evan Stubbs]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/ct4M15U7RPs/</link>
                <dc:creator>Shelley Sessoms</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/publishing/wp-content/blogs.dir/18/files/userphoto/155.thumbnail.jpg" alt="Shelley Sessoms" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>The SAS Bookshelf</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/publishing/?p=5649</guid>
		<pubDate>Mon, 17 Jun 13 11:18:10 +0000</pubDate>
        <description><![CDATA[Writing, editing, galley proofs, indexing, cover design…it all takes time. The logistics of getting a book published can be tough when you’re sitting across the room from each other. What happens when you’re across the world from each other? That’s the topic of this month’s blog post.

Technology makes the world a much smaller place. Between email, instant messaging, fax machines, social media, and the like, work never stops. I wondered how all of this technology helps our international authors. So I asked Evan Stubbs, author of 2 current books, and one in the works, “How was it working on three books with SAS Press, when you are based in Australia and the publishing division is in Cary, NC?”

Evan replied, “It's not as hard as you'd think; so much of my communication is digital anyway that writing and editing simply becomes another workflow in the overall machine. I think it's always been possible to publish or do research from anywhere; the biggest shift has been around the immediacy of response. Where we'd once communicate by fax or mail, whether someone's next to you or on the other side of the planet is largely irrelevant; the communication channels are now exactly the same.

Having said that, time zones always present a challenge. When one takes into account the breadth of people I went to for feedback, working across so many time zones was a little daunting at first. The reality is that that's just the way it is now, though: given how mobile people have become, you work out how best to accommodate everyone's very busy schedules. Having effective writing tools made a big difference.

Being pretty mobile myself, I needed to be able to edit the same content across multiple devices including my personal PC, my iPad, and my laptop regardless of where I am. Everyone has reviewing preferences so making sure content's as portable as possible made it easier to get feedback. Some people swear by their Kindles, other people only speak Word. Still others like a PDF. For me, a key part of collaborating and coordinating internationally was making my content as device agnostic and portable as I could. The less time I spend playing with technology and trying to "make things work", the more time I have to write.

Social media's a blessing and curse. On one hand, it's a rich source of immediate feedback and inspiration. On the other, it'll drive you to distraction if you can't divorce yourself from it periodically. With constant connectivity, the temptation's always there to stay permanently plugged in. For me at least, a big part was also about learning how to balance the opportunities against the challenges.”

Visit Evan Stubbs' author page to read more about him and his work.]]></description>
        <content:encoded><![CDATA[Writing, editing, galley proofs, indexing, cover design…it all takes time. The logistics of getting a book published can be tough when you’re sitting across the room from each other. What happens when you’re across the world from each other? That’s the topic of this month’s blog post.

Technology makes the world a much smaller place. Between email, instant messaging, fax machines, social media, and the like, work never stops. I wondered how all of this technology helps our international authors. So I asked <strong><a href="http://support.sas.com/publishing/authors/stubbs.html">Evan Stubbs</a></strong>, author of 2 current books, and one in the works, “How was it working on three books with SAS Press, when you are based in Australia and the publishing division is in Cary, NC?”<a href="http://blogs.sas.com/content/publishing/files/2013/06/Stubbs_cover1.gif"><img class="alignright size-full wp-image-5659" src="http://blogs.sas.com/content/publishing/files/2013/06/Stubbs_cover1.gif" alt="Delivering Business Analytics" width="108" height="162" /></a>

Evan replied, “It's not as hard as you'd think; so much of my communication is digital anyway that writing and editing simply becomes another workflow in the overall machine. I think it's always been possible to publish or do research from anywhere; the biggest shift has been around the immediacy of response. Where we'd once communicate by fax or mail, whether someone's next to you or on the other side of the planet is largely irrelevant; the communication channels are now exactly the same.

Having said that, time zones always present a challenge. When one takes into account the breadth of people I went to for feedback, working across so many time zones was a little daunting at first. The reality is that that's just the way it is now, though: given how mobile people have become, you work out how best to accommodate everyone's very busy schedules. Having effective writing tools made a big difference.

Being pretty mobile myself, I needed to be able to edit the same content across multiple devices including my personal PC, my iPad, and my laptop regardless of where I am. Everyone has reviewing preferences so making sure content's as portable as possible made it easier to get feedback. Some people swear by their Kindles, other people only speak Word. Still others like a PDF. For me, a key part of collaborating and coordinating internationally was making my content as device agnostic and portable as I could. The less time I spend playing with technology and trying to "make things work", the more time I have to write.<a href="http://blogs.sas.com/content/publishing/files/2013/06/Stubbs_cover2.gif"><img class="alignright size-full wp-image-5660" src="http://blogs.sas.com/content/publishing/files/2013/06/Stubbs_cover2.gif" alt="The Value of Business Analytics" width="108" height="162" /></a>

Social media's a blessing and curse. On one hand, it's a rich source of immediate feedback and inspiration. On the other, it'll drive you to distraction if you can't divorce yourself from it periodically. With constant connectivity, the temptation's always there to stay permanently plugged in. For me at least, a big part was also about learning how to balance the opportunities against the challenges.”

<em>Visit Evan Stubbs' <a href="http://support.sas.com/publishing/authors/stubbs.html">author page</a> to read more about him and his work.</em><div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=ct4M15U7RPs:07wZjcLVpY0:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=ct4M15U7RPs:07wZjcLVpY0:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=ct4M15U7RPs:07wZjcLVpY0:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=ct4M15U7RPs:07wZjcLVpY0:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=ct4M15U7RPs:07wZjcLVpY0:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=ct4M15U7RPs:07wZjcLVpY0:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=ct4M15U7RPs:07wZjcLVpY0:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=ct4M15U7RPs:07wZjcLVpY0:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/ct4M15U7RPs" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/publishing/2013/06/17/the-book-writing-business-publishing-across-the-world-with-evan-stubbs/</feedburner:origLink></item>
	<item>
		<title><![CDATA[ Hospitality analytics in 2013: a review]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/VFFJsbSFNGY/</link>
                <dc:creator>Kelly McGuire</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/hospitality/wp-content/blogs.dir/29/files/userphoto/100.thumbnail.jpg" alt="Kelly McGuire" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>The Analytic Hospitality Executive</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/hospitality/?p=828</guid>
		<pubDate>Mon, 17 Jun 13 10:55:47 +0000</pubDate>
        <description><![CDATA[It’s hard to believe that we are already half way through 2013! As we head into the summer, it’s a good time to look back on the topics we’ve already covered this year (in case you lost track) before we head forward into the second half of 2013.

The first half of 2013 has been all about helping our Analytic Hospitality Executives build a strategic analytic culture within their organizations.  To survive and thrive in today’s fast moving, highly competitive environment, companies must find their competitive edge.   The Analytic Hospitality Executive knows that enterprise use of analytics will help companies find and exploit opportunities to get ahead in today’s fast-paced business environment.

Natalie started out the year discussing how analytics can help hospitality executives achieve the crucial balance between providing an excellent customer experience and meeting revenue &amp; profit responsibilities.  This only works when data and analytics are used to make fast-based decisions across the enterprise, not just department by department.  To help our readers get started, I described how hospitality companies create a strategic analytic culture.

Good analytics start with good data.   Natalie talked about that, and described how information management is the foundation of a strategic analytic culture.  Since big data and big analytics are such a hot topic in today’s business environment, I defined big analytics, and then described how hospitality companies can benefit from big analytics.  Natalie described how hospitality companies should manage for big data.    Natalie also helped us understand how data and analytics can be made more approachable through data visualization.  Alex Dietz joined us to give examples of big data in revenue management, and the opportunities it provides to drive the revenue management analytics of the future.

To give examples of how analytics are applied to solve hospitality business problems Natalie and I discussed four research studies that were presented in February during our SAS/Cornell CHR webcast.  I gave my reactions to Chris Anderson’s study relating social media and lodging performance and talked about Pamela Moulton’s study on PEAD and lodging stock performance.  Natalie addressed the issue of whether enrollment in customer loyalty programs can be measured, based on her conversations with Mike McCall about his latest research, and I described my conversation with SAS’s own Maarten Oosten about his thoughts on pricing as a strategic tool.

In the upcoming months we’ll talk much more about how companies are integrating and operationalizing analytics through discussions of my latest research into revenue management and social media, and a more in-depth look at pricing as a strategic tool.  We’ll describe ways in which departments like revenue management, marketing and operations can share data and analytics for enterprise-wide benefits.  We will have more interviews with Cornell researchers about their work, and as well, continue to provide the perspective of your industry peers.  We will finish the year talking about innovative uses of analytics, covering the latest in digital marketing, as well as some examples of how hospitality industry sub-segments are driving innovation through analytics.

As always, we welcome your comments, suggestions and feedback, so keep it coming!!]]></description>
        <content:encoded><![CDATA[It’s hard to believe that we are already half way through 2013! As we head into the summer, it’s a good time to look back on the topics we’ve already covered this year (in case you lost track) before we head forward into the second half of 2013.

The first half of 2013 has been all about helping our Analytic Hospitality Executives build a strategic analytic culture within their organizations.  To survive and thrive in today’s fast moving, highly competitive environment, companies must find their competitive edge.   The Analytic Hospitality Executive knows that enterprise use of analytics will help companies find and exploit opportunities to get ahead in today’s fast-paced business environment.

Natalie started out the year discussing how analytics can help hospitality executives <a href="http://blogs.sas.com/content/hospitality/2013/01/14/achieving-the-balance-in-hospitality-with-analytics/">achieve the crucial balance</a> between providing an excellent customer experience and meeting revenue &amp; profit responsibilities.  This only works when data and analytics are used to make fast-based decisions across the enterprise, not just department by department.  To help our readers get started, I described how hospitality companies <a href="http://blogs.sas.com/content/hospitality/2013/04/04/creating-a-strategic-analytic-culture-from-the-ground-up-2/">create a strategic analytic culture</a>.

<a href="http://blogs.sas.com/content/hospitality/2013/02/25/game-changing-hospitality-analytics-start-with-good-data/">Good analytics start with good data</a>.   Natalie talked about that, and described how <a href="http://blogs.sas.com/content/hospitality/2013/04/18/hospitality-information-management-the-foundation-of-a-strategic-analytic-culture/">information management is the foundation of a strategic analytic culture</a>.  Since big data and big analytics are such a hot topic in today’s business environment, I <a href="http://blogs.sas.com/content/hospitality/2013/03/07/defining-big-analytics/">defined big analytics</a>, and then described how <a href="http://blogs.sas.com/content/hospitality/2013/03/13/big-analytics-for-hospitality-2/">hospitality companies can benefit from big analytics</a>.  Natalie described how hospitality companies should <a href="http://blogs.sas.com/content/hospitality/2013/03/27/managing-for-big-data-in-hospitality/">manage for big data</a>.    Natalie also helped us understand how data and analytics can be made more approachable through <a href="http://blogs.sas.com/content/hospitality/2013/05/03/making-analytics-more-approachable-with-data-visualization/">data visualization</a>.  Alex Dietz joined us to give examples of <a href="http://blogs.sas.com/content/hospitality/2013/05/17/big-data-revenue-management/">big data in revenue management</a>, and the opportunities it provides to <a href="http://blogs.sas.com/content/hospitality/2013/05/28/big-data-revenue-management-part-2/">drive the revenue management analytics of the future</a>.

To give examples of how analytics are applied to solve hospitality business problems Natalie and I discussed four research studies that were presented in February during our <a href="http://go.sas.com/k46h0r">SAS/Cornell CHR webcast</a>.  I gave my reactions to Chris Anderson’s study relating <a href="http://blogs.sas.com/content/hospitality/2013/01/22/social-media-and-lodging-performance/">social media and lodging performance</a> and talked about Pamela Moulton’s study on <a href="http://blogs.sas.com/content/hospitality/2013/01/29/a-primer-on-pead-an-interview-with-pamela-moulton-on-analysis-of-hospitality-stock-performance/">PEAD and lodging stock performance</a>.  Natalie addressed the issue of whether <a href="http://blogs.sas.com/content/hospitality/2013/02/15/can-the-impact-of-enrollments-in-customer-loyalty-programs-be-measured/">enrollment in customer loyalty programs can be measured</a>, based on her conversations with Mike McCall about his latest research, and I described my conversation with SAS’s own Maarten Oosten about his thoughts on <a href="http://blogs.sas.com/content/hospitality/2013/02/07/pricing-as-a-strategic-tool-a-conversation-with-maarten-oosten/">pricing as a strategic tool</a>.

In the upcoming months we’ll talk much more about how companies are integrating and operationalizing analytics through discussions of my latest research into revenue management and social media, and a more in-depth look at pricing as a strategic tool.  We’ll describe ways in which departments like revenue management, marketing and operations can share data and analytics for enterprise-wide benefits.  We will have more interviews with Cornell researchers about their work, and as well, continue to provide the perspective of your industry peers.  We will finish the year talking about innovative uses of analytics, covering the latest in digital marketing, as well as some examples of how hospitality industry sub-segments are driving innovation through analytics.

As always, we welcome your comments, suggestions and feedback, so keep it coming!!<div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=VFFJsbSFNGY:DLVeeI9_8M8:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=VFFJsbSFNGY:DLVeeI9_8M8:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=VFFJsbSFNGY:DLVeeI9_8M8:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=VFFJsbSFNGY:DLVeeI9_8M8:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=VFFJsbSFNGY:DLVeeI9_8M8:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=VFFJsbSFNGY:DLVeeI9_8M8:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=VFFJsbSFNGY:DLVeeI9_8M8:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=VFFJsbSFNGY:DLVeeI9_8M8:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/VFFJsbSFNGY" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/hospitality/2013/06/17/hospitality-analytics-in-2013-a-review/</feedburner:origLink></item>
	<item>
		<title><![CDATA[Healthy Hydration: Goodbye Boring Water!]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/FeMOWM8Y-F8/</link>
                <dc:creator>Ashley Bailey, MS, RD, LDN</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/efs/wp-content/blogs.dir/30/files/userphoto/458.thumbnail.jpg" alt="Ashley Bailey, MS, RD, LDN" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>SAS Life</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/efs/?p=718</guid>
		<pubDate>Mon, 17 Jun 13 10:54:13 +0000</pubDate>
        <description><![CDATA[
Most of us can probably recite the age-old recommendation to "drink eight 8-ounce cups of water every day" in our sleep. However, how many of us actually do it? We are often quick to replace our water bottles with sugar-sweetened beverages, coffee, or tea while telling ourselves, "it’s mostly water, right?"
Sugar-sweetened beverage consumption has more than doubled over the last 30 years and continues to rise with the average American drinking about 45 gallons a year. With approximately 16 teaspoons (or ¼ cup) of sugar per 20-ounce soda, that’s a lot of added sugars and empty calories!

How Much Water Do We Really Need?

Humans are made up of about 60% water and all of the systems in our bodies depend on water to function properly. Water helps regulate body temperature, cushion joints, and get rid of unwanted toxins and wastes.

According to the Institute of Medicine, men should drink approximately 12.5 cups of water daily and women 9 cups. This general recommendation varies from person to person and is affected by factors such as exercise, climate, and health status.

Tired of Boring Water?

If you’re tired of drinking plain water, here are a few ideas to help put some excitement back into your drinks without having to reach for sugar-sweetened beverages.

	The Aqua Zinger: This 20-ounce bottle puts some "zing" into water by infusing the natural flavors of fruits, vegetables, herbs, and spices. You can enjoy two 20-ounce bottles for each recipe creation, which puts you more than halfway to your daily water goal! Check out the video demonstration below to learn more or visit their website.



 

	Ice, Ice Baby! Another easy way to put a fun twist on plain water is to use fruit-inspired ice cubes. Not only are they gorgeous to look at, they also add a great boost of flavor to water.  Below are two recipe options that will leave you saying goodbye to plain, boring water forever! Click here for a printer-friendly version.

Berrylicious Ice Cubes
Makes 16 Ice Cubes
Ingredients
16 raspberries
32-48 blueberries
Water

Directions

	In an ice cube tray, place 1 raspberry and 2-3 blueberries in each cube.
	Fill with water.
	Place tray in freezer overnight, or until completely frozen.
	Remove ice cubes from tray and add to water.
	For a fun twist, try with sparkling water, club soda, seltzer water, etc.


 
Triple Berry Fruit Cubes
Makes 14 Ice Cubes
Ingredients
20 raspberries
40 blueberries
10 strawberries

Directions

	Wash berries well and pat dry. Remove tops from strawberries.
	Place berries into a food processor or blender and pulse until smooth.
	Pour berry puree into an ice cube tray, filling each cube completely.
	Place tray in freezer overnight, or until completely frozen.
	Remove ice cubes from tray and add to water.
	For a fun twist, try with sparkling water, club soda, seltzer water, etc. For a light cocktail option, add your choice of champagne or white wine.

&nbsp;

Sources:
"The Health Consequences of Drinking Soda and Other Sugar-Sweetenend Beverages," www.publichealthadvocacy.org]]></description>
        <content:encoded><![CDATA[<p style="text-align: center"><img class="aligncenter size-full wp-image-44" src="http://blogs.sas.com/content/efs/files/2012/09/Chews_Strategically_Banner.jpg" alt="" width="802" height="99" /><img class="alignright size-full wp-image-91" src="http://blogs.sas.com/content/efs/files/2013/02/BlogMission1.jpg" alt="" width="210" height="495" /></p>
<p style="text-align: left">Most of us can probably recite the age-old recommendation to "drink eight 8-ounce cups of water every day" in our sleep. However, how many of us actually do it? We are often quick to replace our water bottles with sugar-sweetened beverages, coffee, or tea while telling ourselves, "it’s mostly water, right?"</p>
Sugar-sweetened beverage consumption has more than doubled over the last 30 years and continues to rise with the average American drinking about 45 gallons a year. With approximately <strong>16 teaspoons (or ¼ cup) of sugar</strong> per 20-ounce soda, that’s a lot of added sugars and empty calories!

<strong>How Much Water Do We Really Need?</strong>

Humans are made up of about 60% water and all of the systems in our bodies depend on water to function properly. Water helps regulate body temperature, cushion joints, and get rid of unwanted toxins and wastes.

According to the Institute of Medicine, men should drink approximately <strong>12.5 cups</strong> of water daily and women <strong>9 cups.</strong> This general recommendation varies from person to person and is affected by factors such as exercise, climate, and health status.

<strong>Tired of Boring Water?</strong>

If you’re tired of drinking plain water, here are a few ideas to help put some excitement back into your drinks without having to reach for sugar-sweetened beverages.
<ul>
	<li><strong>The Aqua Zinger</strong>: This 20-ounce bottle puts some "zing" into water by infusing the natural flavors of fruits, vegetables, herbs, and spices. You can enjoy two 20-ounce bottles for each recipe creation, which puts you more than halfway to your daily water goal! Check out the video demonstration below to learn more or visit their <a href="http://zinganything.com/">website</a>.</li>
</ul>

<!-- powered by Iframe plugin ver.2.1 (wordpress.org/extend/plugins/iframe/) -->
<iframe title="YouTube video player" width="560" height="315" src="http://www.youtube.com/embed/_4lWifclOIk?rel=0" scrolling="no" class="iframe-class" frameborder="0"></iframe>

<strong></strong> 
<ul>
	<li><strong>Ice, Ice Baby!</strong> Another easy way to put a fun twist on plain water is to use fruit-inspired ice cubes. Not only are they gorgeous to look at, they also add a great boost of flavor to water.  Below are two recipe options that will leave you saying goodbye to plain, boring water forever! <a href="http://blogs.sas.com/content/efs/files/2013/06/FruitIceCubeRecipes.pdf">Click here</a> for a printer-friendly version.</li>
</ul>
<p style="text-align: center"><strong>Berrylicious Ice Cubes</strong>
Makes 16 Ice Cubes</p>
<strong>Ingredients</strong>
16 raspberries
32-48 blueberries
Water

<strong>Directions</strong>
<ol>
	<li>In an ice cube tray, place 1 raspberry and 2-3 blueberries in each cube.</li>
	<li>Fill with water.</li>
	<li>Place tray in freezer overnight, or until completely frozen.<a href="http://blogs.sas.com/content/efs/files/2013/06/TripleBerryFruitCubesSteps.jpg"><img class="aligncenter size-full wp-image-723" style="margin-top: 10px;margin-bottom: 10px" src="http://blogs.sas.com/content/efs/files/2013/06/TripleBerryFruitCubesSteps.jpg" alt="" width="605" height="405" /></a></li>
	<li>Remove ice cubes from tray and add to water.</li>
	<li>For a fun twist, try with sparkling water, club soda, seltzer water, etc.
<a href="http://blogs.sas.com/content/efs/files/2013/06/TripleBerryFruitCubesFinal.jpg"><img class="aligncenter size-full wp-image-725" style="margin-top: 10px;margin-bottom: 10px" src="http://blogs.sas.com/content/efs/files/2013/06/TripleBerryFruitCubesFinal.jpg" alt="" width="604" height="472" /></a></li>
</ol>
<p style="text-align: center"><strong></strong> </p>
<p style="text-align: center"><strong>Triple Berry Fruit Cubes</strong>
Makes 14 Ice Cubes</p>
<strong>Ingredients</strong>
20 raspberries
40 blueberries
10 strawberries

<strong>Directions</strong>
<ol>
	<li>Wash berries well and pat dry. Remove tops from strawberries.</li>
	<li>Place berries into a food processor or blender and pulse until smooth.</li>
	<li>Pour berry puree into an ice cube tray, filling each cube completely.<a href="http://blogs.sas.com/content/efs/files/2013/06/BerryliciousIceCubeSteps.jpg"><img class="aligncenter size-full wp-image-726" style="margin-top: 10px;margin-bottom: 10px" src="http://blogs.sas.com/content/efs/files/2013/06/BerryliciousIceCubeSteps.jpg" alt="" width="604" height="403" /></a></li>
	<li>Place tray in freezer overnight, or until completely frozen.</li>
	<li>Remove ice cubes from tray and add to water.</li>
	<li>For a fun twist, try with sparkling water, club soda, seltzer water, etc. For a light cocktail option, add your choice of champagne or white wine.<a href="http://blogs.sas.com/content/efs/files/2013/06/BerryliciousIceCubesFinal.jpg"><img class="aligncenter size-full wp-image-727" style="margin-top: 10px;margin-bottom: 10px" src="http://blogs.sas.com/content/efs/files/2013/06/BerryliciousIceCubesFinal.jpg" alt="" width="616" height="432" /></a></li>
</ol>
&nbsp;

<span style="font-size: x-small">Sources:
"The Health Consequences of Drinking Soda and Other Sugar-Sweetenend Beverages," <a href="http://www.publichealthadvocacy.org">www.publichealthadvocacy.org</a></span><div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=FeMOWM8Y-F8:aekR-E0MNG8:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FeMOWM8Y-F8:aekR-E0MNG8:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=FeMOWM8Y-F8:aekR-E0MNG8:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FeMOWM8Y-F8:aekR-E0MNG8:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FeMOWM8Y-F8:aekR-E0MNG8:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=FeMOWM8Y-F8:aekR-E0MNG8:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FeMOWM8Y-F8:aekR-E0MNG8:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=FeMOWM8Y-F8:aekR-E0MNG8:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/FeMOWM8Y-F8" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/efs/2013/06/17/healthy-hydration-goodbye-boring-water/</feedburner:origLink></item>
	<item>
		<title><![CDATA[Had a bad date? Here’s the solution]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/QXeqUGB1cyk/</link>
                <dc:creator>Natalie Meyer</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/sascom/wp-content/blogs.dir/2/files/userphoto/607.thumbnail.jpg" alt="Natalie Meyer" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>SAS Users Groups</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/sgf/?p=6142</guid>
		<pubDate>Mon, 17 Jun 13 10:00:09 +0000</pubDate>
        <description><![CDATA[Everyone may find bad dates in their data set from time to time, but it’s often difficult to tell if they’re mere annoyances or indicative of a larger problem. Luckily, Lucheng Shao has come to the rescue in his SAS Global Forum winning paper, Don’t Let a Bad Date Ruin Your Day: Dealing with Invalid Dates in SAS. His paper explores the ins and outs of bad dates and how offers a practical guide to fixing them.

Think bad dates aren’t a big deal? Think again. Shao likens them to headaches, which could be a symptom of a common cold, or, as he cautions “a complication of brain cancer.” Fortunately, he says that the log file is an excellent indicator of the data’s overall health can be used to prevent this potentially-fatal diagnosis.

Unsure as to whether or not your data is in good health? View Shao’s winning paper for a step-by-step guide on bad dates and give your data a routine checkup.

Image provided by Peter Hellberg//attribution by creative commons ]]></description>
        <content:encoded><![CDATA[<a href="http://blogs.sas.com/content/sgf/files/2013/06/headache1.png"><img class="alignright size-thumbnail wp-image-6146" src="http://blogs.sas.com/content/sgf/files/2013/06/headache1-150x150.png" alt="" width="150" height="150" /></a>Everyone may find bad dates in their data set from time to time, but it’s often difficult to tell if they’re mere annoyances or indicative of a larger problem. Luckily, Lucheng Shao has come to the rescue in his SAS Global Forum winning paper, <a href="http://support.sas.com/resources/papers/proceedings13/122-2013.pdf"><strong>Don’t Let a Bad Date Ruin Your Day: Dealing with Invalid Dates in SAS</strong></a>. His paper explores the ins and outs of bad dates and how offers a practical guide to fixing them.

Think bad dates aren’t a big deal? Think again. Shao likens them to headaches, which could be a symptom of a common cold, or, as he cautions “a complication of brain cancer.” Fortunately, he says that the log file is an excellent indicator of the data’s overall health can be used to prevent this potentially-fatal diagnosis.

Unsure as to whether or not your data is in good health? View Shao’s <a href="http://support.sas.com/resources/papers/proceedings13/122-2013.pdf">winning paper</a> for a step-by-step guide on bad dates and give your data a routine checkup.

<em>Image provided by <a href="http://www.flickr.com/photos/peterhellberg/">Peter Hellberg</a>//</em><a href="http://creativecommons.org/licenses/by/2.0/"><em>attribution by creative commons </em></a><div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=QXeqUGB1cyk:yiIjrHNTryI:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=QXeqUGB1cyk:yiIjrHNTryI:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=QXeqUGB1cyk:yiIjrHNTryI:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=QXeqUGB1cyk:yiIjrHNTryI:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=QXeqUGB1cyk:yiIjrHNTryI:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=QXeqUGB1cyk:yiIjrHNTryI:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=QXeqUGB1cyk:yiIjrHNTryI:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=QXeqUGB1cyk:yiIjrHNTryI:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/QXeqUGB1cyk" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/sgf/2013/06/17/had-a-bad-date-heres-the-solution/</feedburner:origLink></item>
	<item>
		<title><![CDATA[Forecast Value Added: A Reality Check on Forecasting Practices]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/lZVsmzEZvkI/</link>
                <dc:creator>Mike Gilliland</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/forecasting/wp-content/blogs.dir/4/files/userphoto/123.thumbnail.jpg" alt="Mike Gilliland" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>The Business Forecasting Deal</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/forecasting/?p=2229</guid>
		<pubDate>Mon, 17 Jun 13 09:10:39 +0000</pubDate>
        <description><![CDATA[If an organization is spending time and money to have a forecasting process, is it not reasonable to expect the process to make the forecast more accurate and less biased (or at least not make it any worse!)? But how would we ever know what the process is accomplishing?

To find out, register for this quarter's installment of the Foresight-SAS webinar series:

Forecast Value Added Analysis: A Reality Check on Forecasting Practices (Thursday June 20, 11:00am EDT)

This webinar is based on an article appearing in the Spring 2013 issue of Foresight: The International Journal of Applied Forecasting. The editors of Foresight have graciously made the article available for free download: Foresight FVA Article.

Join us Thursday. Meantime, here is a short preview...

---------------------------

In our jobs and in our lives we have to make decisions about the future. These decisions are based on some expectation (or "forecast") of what the future will bring. So if we expect demand for Product X to be 10,000 units per month for the rest of 2013, we'll make decisions about production or procurement of inventory, how we will distribute it, how much we'll sell it for, and many others.

To make the best decisions, it helps to have a good forecast (one that is high in accuracy and low in bias). To achieve good forecasting, organizations are wont to spend time and resources on a forecasting process.

The most basic process involves forecasting software and an analyst to monitor the software and perhaps provide manual overrides to the computer generated forecast. In the more elaborate processes we find in larger enterprises, there may be multiple process steps and participants (from sales, marketing, finance, operations, and the executive suite) to review and provide their own adjustments to the forecast.

While it may sound great in theory, an elaborate forecasting process with many human touch points can be a case of "too many cooks in the kitchen." We may assume that every participant has something worthwhile to add, and that each forecast adjustment gets us closer to perfectly predicting the future. But how would we know?

Traditional forecasting performance metrics like accuracy, error (e.g. MAPE), or bias, can tell us the magnitude of our forecasting imperfection. But they don't tell us how good we should be able to be, or how efficient our process was at getting the accuracy we achieved, or -- most important -- whether our process made the forecast any better at all.

Forecast Value Added (FVA) is the metric adopted by many organization to evaluate the effectiveness of their forecasting process. What is sometimes discovered, after conducting FVA analysis, is that all of our heroic efforts just made the forecast worse. The touch points for human intervention, instead of incorporating knowledge that made the forecast better, simply allowed process participants to add their own biases and personal agendas. But without doing FVA analysis, you'd never know.

&nbsp;]]></description>
        <content:encoded><![CDATA[If an organization is spending time and money to have a forecasting process, is it not reasonable to expect the process to make the forecast more accurate and less biased (or at least not make it any worse!)? But how would we ever know what the process is accomplishing?

<a href="http://blogs.sas.com/content/forecasting/files/2013/06/ForesightSpring2013_Issue29_cover2.jpg"><img class="alignright size-full wp-image-2239" src="http://blogs.sas.com/content/forecasting/files/2013/06/ForesightSpring2013_Issue29_cover2.jpg" alt="" width="140" height="184" /></a>To find out, <a href="http://www.sas.com/apps/sim/redirect.jsp?detail=SIM107917_4748" target="_blank">register</a> for this quarter's installment of the <em>Foresight</em>-SAS webinar series:

<a href="http://www.sas.com/apps/sim/redirect.jsp?detail=SIM107917_4748" target="_blank"><strong>Forecast Value Added Analysis: A Reality Check on Forecasting Practices</strong> </a>(Thursday June 20, 11:00am EDT)

This webinar is based on an article appearing in the Spring 2013 issue of <em><a href="http://forecasters.org/foresight/" target="_blank">Foresight: The International Journal of Applied Forecasting</a></em>. The editors of Foresight have graciously made the article available for free download: <a href="http://forecasters.org/foresight/forms/reality-check/" target="_blank"><em>Foresight</em> FVA Article</a>.

Join us Thursday. Meantime, here is a short preview...

---------------------------

In our jobs and in our lives we have to make decisions about the future. These decisions are based on some expectation (or "forecast") of what the future will bring. So if we expect demand for Product X to be 10,000 units per month for the rest of 2013, we'll make decisions about production or procurement of inventory, how we will distribute it, how much we'll sell it for, and many others.

To make the best decisions, it helps to have a good forecast (one that is high in accuracy and low in bias). To achieve good forecasting, organizations are wont to spend time and resources on a forecasting process.

The most basic process involves forecasting software and an analyst to monitor the software and perhaps provide manual overrides to the computer generated forecast. In the more elaborate processes we find in larger enterprises, there may be multiple process steps and participants (from sales, marketing, finance, operations, and the executive suite) to review and provide their own adjustments to the forecast.

While it may sound great in theory, an elaborate forecasting process with many human touch points can be a case of "too many cooks in the kitchen." We may assume that every participant has something worthwhile to add, and that each forecast adjustment gets us closer to perfectly predicting the future. But how would we know?

Traditional forecasting performance metrics like accuracy, error (e.g. MAPE), or bias, can tell us the magnitude of our forecasting imperfection. But they don't tell us how good we should be able to be, or how efficient our process was at getting the accuracy we achieved, or -- most important -- whether our process made the forecast any better at all.

Forecast Value Added (FVA) is the metric adopted by many organization to evaluate the effectiveness of their forecasting process. What is sometimes discovered, after conducting FVA analysis, is that all of our heroic efforts just made the forecast worse. The touch points for human intervention, instead of incorporating knowledge that made the forecast better, simply allowed process participants to add their own biases and personal agendas. But without doing FVA analysis, you'd never know.

&nbsp;<div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=lZVsmzEZvkI:wD8E_26sX6k:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=lZVsmzEZvkI:wD8E_26sX6k:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=lZVsmzEZvkI:wD8E_26sX6k:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=lZVsmzEZvkI:wD8E_26sX6k:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=lZVsmzEZvkI:wD8E_26sX6k:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=lZVsmzEZvkI:wD8E_26sX6k:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=lZVsmzEZvkI:wD8E_26sX6k:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=lZVsmzEZvkI:wD8E_26sX6k:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/lZVsmzEZvkI" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/forecasting/2013/06/17/forecast-value-added-a-reality-check-on-forecasting-practices/</feedburner:origLink></item>
	<item>
		<title><![CDATA[Repetition factors versus frequency variables]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/wdOiVWedqXE/</link>
                <dc:creator>Rick Wicklin</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/iml/wp-content/blogs.dir/22/files/userphoto/136.thumbnail.jpg" alt="Rick Wicklin" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>The DO Loop</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/iml/?p=8483</guid>
		<pubDate>Mon, 17 Jun 13 06:25:23 +0000</pubDate>
        <description><![CDATA[
A regular reader noticed my post on initializing vectors by using repetition factors and asked whether that technique would be useful to expand data that are given in value-frequency pairs.  The short answer is "no."  Repetition factors are useful for defining (static) matrix literals. However, if you want to expand data dynamically, I recommend that you use the REPEAT function or the technique in the article on expanding data by using frequencies.


For example, the following SAS/IML statement defines a vector for which the value 2.2 is repeated two times and the value 3.3 is repeated three times. The resulting vector has five elements:


proc iml;
x = {[2] 2.2  [3] 3.3};


This vector is constructed as a matrix literal. If instead you have the values and frequencies in separate vectors, then use the ExpandFreq module in my previous post: 


values = {2.2 3.3};
freq   = {2   3};
load module=(ExpandFreq); /* define or load ExpandFreg module here */
y = ExpandFreq(values, freq);




This is probably a good time to remind everyone about the SAS/IML Support Community. You can post your SAS/IML questions there 24 hours a day. That is always better than sending me direct email. There are lots of experienced SAS/IML experts out there, so use the SAS/IML Support Community to tap into that knowledge. 
]]></description>
        <content:encoded><![CDATA[<p>
A regular reader noticed my post on <a href="http://blogs.sas.com/content/iml/2013/02/25/epitition-factors/">initializing vectors by using repetition factors</a> and asked whether that technique would be useful to expand data that are given in value-frequency pairs.  The short answer is "no."  Repetition factors are useful for defining (static) matrix literals. However, if you want to expand data dynamically, I recommend that you use the <a href="http://support.sas.com/documentation/cdl/en/imlug/64248/HTML/default/viewer.htm#imlug_langref_sect251.htm">REPEAT function</a> or the technique in the article on <a href="http://blogs.sas.com/content/iml/2012/05/04/expand-data-by-using-frequencies/">expanding data by using frequencies.</a>
</p>
<p>
For example, the following SAS/IML statement defines a vector for which the value 2.2 is repeated two times and the value 3.3 is repeated three times. The resulting vector has five elements:
</p>
<pre lang="text" escaped="true">
proc iml;
x = {[2] 2.2  [3] 3.3};
</pre>
<p>
This vector is constructed as a matrix literal. If instead you have the values and frequencies in separate vectors, then use the <tt>ExpandFreq</tt> module in <a href="http://blogs.sas.com/content/iml/2012/05/04/expand-data-by-using-frequencies/">my previous post</a>: 
</p>
<pre lang="text" escaped="true">
values = {2.2 3.3};
freq   = {2   3};
load module=(ExpandFreq); /* define or load ExpandFreg module here */
y = ExpandFreq(values, freq);
</pre>


<p>
This is probably a good time to remind everyone about the <a href="https://communities.sas.com/community/support-communities/sas_iml_and_sas_iml_studio">SAS/IML Support Community</a>. You can post your SAS/IML questions there 24 hours a day. That is always better than sending me direct email. There are lots of experienced SAS/IML experts out there, so use the SAS/IML Support Community to tap into that knowledge. 
</p><div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=wdOiVWedqXE:o2qIR7fdJyE:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=wdOiVWedqXE:o2qIR7fdJyE:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=wdOiVWedqXE:o2qIR7fdJyE:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=wdOiVWedqXE:o2qIR7fdJyE:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=wdOiVWedqXE:o2qIR7fdJyE:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=wdOiVWedqXE:o2qIR7fdJyE:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=wdOiVWedqXE:o2qIR7fdJyE:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=wdOiVWedqXE:o2qIR7fdJyE:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/wdOiVWedqXE" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/iml/2013/06/17/repetition-factors-versus-frequency-variables/</feedburner:origLink></item>
	<item>
		<title><![CDATA[Data integration, holistic view of municipal data can show neighborhoods in decline]]></title>
		<link>http://feedproxy.google.com/~r/sasblogs/~3/FUQL9SXjreA/</link>
                <dc:creator>Bill Coleman</dc:creator>
        <sas:authorphoto><img src="http://blogs.sas.com/content/statelocalgov/wp-content/blogs.dir/9/files/userphoto/284.thumbnail.jpg" alt="Bill Coleman" width="60" height="60" class="photo" /></sas:authorphoto>
        <sas:blogname>State and Local Connection</sas:blogname>
        		<guid isPermaLink="false">http://blogs.sas.com/content/statelocalgov/?p=1124</guid>
		<pubDate>Mon, 17 Jun 13 01:05:49 +0000</pubDate>
        <description><![CDATA[Imagine a business offering a multitude of products and services that seemingly have little relationship to one another, and all are supported by different data systems.  This is the plight of local governments.  The products and services produced and managed by local governments range from utilities, solid waste and recycling to parks and culural arts, to public safety, building permits and inspections, social services and many, many more. This array of products and services is supported by one or more finance, budgeting and human resource systems.

The degree of success achieved by any local government is dependent on how well the city or county manager is able to tie these data elements together to create a complete picture of how well the organization is meeting its goals. More importantly, it is critical for the manager to be able to have a holistic view of the relationships of all of these activities to each other in order to be able to identify problems early and respond appropriately.

A good example of how a holistic view can not only help the local government  identify and solve problems early to save money, but can also help improve the community, can be found in the problem of neighborhood deterioration.

Consider this example. A city manager is confronted with a request from the City Council to address blight and crime in Neighborhoood X.  The city manager asks the police chief, the public works director, the planning director, the director of permits and inspections, and the budget director for all relevant data on this neighborhood. Unfortunately, each of these functions operates with a different data information system.

Here’s what they tell him:
Police chief: “The computer aided dispatch system indicates property crime and vandalism are a problem in the area, and the police department is responding in a timely manner.”

Public works director: “The work order system shows that many sidewalks have been repaired in the area, graffiti and trash have been removed from vacant lots and damaged fire hydrants have been repaired or replaced.”

Planning director and inspections director: “Our data systems show code violations and minimum housing code complaints are a problem in the area.”

Budget director: “These problems cannot be too serious because expenditures for these types of activities are down for the fiscal year.”
The city manager asks if these problems are a recent phenomenon. He also asks if these occurrences are confined to a particular part of the neighborhood or are pervasive throughout. All respond that they do not have those answers at hand, but can develop them.  Based on this disjointed information, the city manager asks the police chief to allocate more patrol time to the area and the other departments to address their respective concerns until they have more information.

Under this scenario, which is typical, the city manager does not know crime and vandalism began increasing three years ago and has been isolated to a four block area. He is also unaware that the code and housing issues began 18 months ago and are confined to that same area. The budget director can’t tell that while expenditures are down for infrastructure maintenance and rectifying code violations, expenditures for those activities in the area in question were up over 80%, and that property values in the area were decreasing.

The city manager is only going to know these important facts if the town’s databases are integrated, tracked over time and the relationships are identified and subjected to analytics. All of this information could have been displayed on a dashboard accessible to the city manager and the department directors on a daily basis.  The relationships between crime and vandalism, increased public works costs, maintenance costs and code violations would have been obvious and pointed to a neighborhood in serious deterioration.  With analytics, decisions could have been made to allocate resources through a community policing program and/or additional recreation programs to deter the crime and vandalism which led to the decline. The end result would be a clean, safe neighborhood, and the saving of hundreds of thousands of tax dollars.]]></description>
        <content:encoded><![CDATA[Imagine a business offering a multitude of products and services that seemingly have little relationship to one another, and all are supported by different data systems.  This is the plight of local governments.  The products and services produced and managed by local governments range from utilities, solid waste and recycling to parks and culural arts, to public safety, building permits and inspections, social services and many, many more. This array of products and services is supported by one or more finance, budgeting and human resource systems.

The degree of success achieved by any local government is dependent on how well the city or county manager is able to tie these data elements together to create a complete picture of how well the organization is meeting its goals. More importantly, it is critical for the manager to be able to have a holistic view of the relationships of all of these activities to each other in order to be able to identify problems early and respond appropriately.

A good example of how a holistic view can not only help the local government  identify and solve problems early to save money, but can also help improve the community, can be found in the problem of neighborhood deterioration.

Consider this example. A city manager is confronted with a request from the City Council to address blight and crime in Neighborhoood X.  The city manager asks the police chief, the public works director, the planning director, the director of permits and inspections, and the budget director for all relevant data on this neighborhood. Unfortunately, each of these functions operates with a different data information system.

Here’s what they tell him:
<blockquote>Police chief: “The computer aided dispatch system indicates property crime and vandalism are a problem in the area, and the police department is responding in a timely manner.”

Public works director: “The work order system shows that many sidewalks have been repaired in the area, graffiti and trash have been removed from vacant lots and damaged fire hydrants have been repaired or replaced.”

Planning director and inspections director: “Our data systems show code violations and minimum housing code complaints are a problem in the area.”

Budget director: “These problems cannot be too serious because expenditures for these types of activities are down for the fiscal year.”</blockquote>
The city manager asks if these problems are a recent phenomenon. He also asks if these occurrences are confined to a particular part of the neighborhood or are pervasive throughout. All respond that they do not have those answers at hand, but can develop them.  Based on this disjointed information, the city manager asks the police chief to allocate more patrol time to the area and the other departments to address their respective concerns until they have more information.

Under this scenario, which is typical, the city manager does not know crime and vandalism began increasing three years ago and has been isolated to a four block area. He is also unaware that the code and housing issues began 18 months ago and are confined to that same area. The budget director can’t tell that while expenditures are down for infrastructure maintenance and rectifying code violations, expenditures for those activities in the area in question were up over 80%, and that property values in the area were decreasing.

The city manager is only going to know these important facts if the town’s databases are integrated, tracked over time and the relationships are identified and subjected to analytics. All of this information could have been displayed on a dashboard accessible to the city manager and the department directors on a daily basis.  The relationships between crime and vandalism, increased public works costs, maintenance costs and code violations would have been obvious and pointed to a neighborhood in serious deterioration.  With analytics, decisions could have been made to allocate resources through a community policing program and/or additional recreation programs to deter the crime and vandalism which led to the decline. The end result would be a clean, safe neighborhood, and the saving of hundreds of thousands of tax dollars.<div class="feedflare">
<a href="http://feeds.feedburner.com/~ff/sasblogs?a=FUQL9SXjreA:8gBzKlXaKi8:yIl2AUoC8zA"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=yIl2AUoC8zA" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FUQL9SXjreA:8gBzKlXaKi8:V_sGLiPBpWU"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=FUQL9SXjreA:8gBzKlXaKi8:V_sGLiPBpWU" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FUQL9SXjreA:8gBzKlXaKi8:qj6IDK7rITs"><img src="http://feeds.feedburner.com/~ff/sasblogs?d=qj6IDK7rITs" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FUQL9SXjreA:8gBzKlXaKi8:gIN9vFwOqvQ"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=FUQL9SXjreA:8gBzKlXaKi8:gIN9vFwOqvQ" border="0"></img></a> <a href="http://feeds.feedburner.com/~ff/sasblogs?a=FUQL9SXjreA:8gBzKlXaKi8:F7zBnMyn0Lo"><img src="http://feeds.feedburner.com/~ff/sasblogs?i=FUQL9SXjreA:8gBzKlXaKi8:F7zBnMyn0Lo" border="0"></img></a>
</div><img src="http://feeds.feedburner.com/~r/sasblogs/~4/FUQL9SXjreA" height="1" width="1"/>]]></content:encoded>
        	<feedburner:origLink>http://blogs.sas.com/content/statelocalgov/2013/06/17/data-integration-holistic-view-of-municipal-data-can-show-neighborhoods-in-decline/</feedburner:origLink></item>
</channel>
</rss>
