Billions of dollars a year are spent subsidising tuition of Australian university students. A controversial report last year by the Grattan Institute, Graduate Winners, asked ‘is this the best use of government money?’

In this talk, Jim Savage, one of the researchers who worked on the report, walks us through the process of doing the analysis in R. The talk will focus on potential pitfalls/annoyances in this sort of research, and on causal inference when all we have is observational data. He will also outline his new method of building synthetic control groups of observational data using tools more commonly associated with data mining.

Jim Savage is an applied economist at the Grattan Institute, where he has researched education policy, the structure of the Australian economy, and fiscal policy. Before that, he worked in macroeconomic modelling at the Federal Treasury.

Additional Resources:

• Slides for the talk
• Grattan Institute
• Complete play list of Melbourne R User videos here

Content: Greenplum is a massively parallel relational database platform. R is one of the top languages in the data scientist/applied statistician community. In this talk, Hong gives an overview of how they work together, both with R on the desktop and as an embedded in-database analytics tool.  It’ll be a variation of a talk recently presented at the UseR 2012 Conference.

Speaker: Hong Ooi graduated from Macquarie University with a BEc in actuarial studies, then worked with NRMA Insurance/IAG in Sydney for many years. Completed a Masters in Applied Stats from Macquarie in 1997, and a PhD in statistics from ANU from 2000-2004. Displayed impeccable timing by switching jobs to St George Bank on the eve of the global financial crisis.Moved to Melbourne in 2009, before joining the Greenplum data science team in 2012.

Resources

• Talk home page
• Other Melbourne R User Videos
• Hong’s 2011 talk on “Experiences with using SAS and R in insurance and banking”

Talk Overview: Complex designs are common in survey data. In practice, collecting random samples from a populations is costly and impractical. Therefore the data are often non-independent or disproportionately sampled, and violate the typical assumption of independent and identically distributed samples (IDD). The Survey package in R (written by Thomas Lumley) is a powerful tool that incorporates survey designs to the data. Standard statistics, from linear models to survival analysis, are implemented with the corresponding mathematical corrections. This talk will provide an introduction to survey statistics and the Survey package. There will be a brief overview of complex designs and some of the theory behind their analysis, followed by a demonstration using the Survey package.

About the presenter: Sebastián Duchêne is a Ph.D. candidate at The University of Sydney, based at the Molecular Phylogenetics, Ecology, and Evolution Lab. His broad area of research is virus evolution. His current projects include an R package for evolutionary analysis, and the development of statistical models for molecular epidemiology. In addition to his PhD studies, he is a reviewer for the PLoS ONE academic journal in the area of evolution and bioinformatics. Before coming to Sydney, he was a data analyst at the National Oceanic and Atmospheric Administration (NOAA) in the USA. A list of his publications can be found here.

See here for the full list of Melbourne R User Videos.

• Getting R help
• Debugging R functions
• R style guides
• Making good use of Rprofiles.
• Having a good R workflow
• Version control facilities
• Using R with LaTeX (without using sweave or knitr)
• Turning functions into packages

Prof Rob J Hyndman has used R and its predecessors (S and S+) almost every working day (and some weekends) for the past 25 years. He thought it might be helpful to discuss some of what he has learned and the tricks and tools that he uses. Topics to be discussed will possibly include:

Rob J Hyndman is Professor of Statistics at Monash University and Director of the Monash University Business and Economic Forecasting Unit. He completed a science degree at the University of Melbourne in 1988 and a PhD on nonlinear time series modelling at the same university in 1992. He has worked at the University of Melbourne, Colorado State University, the Australian National University and Monash University. Rob is Editor-in-Chief of the “International Journal of Forecasting” and a Director of the International Institute of Forecasters. He has written over 100 research papers in statistical science. In 2007, he received the Moran medal from the Australian Academy of Science for his contributions to statistical research. Rob is co-author of the well-known textbook “Forecasting: methods and applications” (Wiley, 3rd ed., 1998) and of the book “Forecasting with exponential smoothing: the state space approach” (Springer, 2008). He is also the author of the widely-used “forecast” package for R. For over 25 years, Rob has maintained an active consulting practice, assisting hundreds of companies and organizations on forecasting problems. His recent consulting work has involved forecasting electricity demand, tourism demand and the Australian government health budget. More information is available on his website at robjhyndman.com.

Additional Resources:

• Slides for the talk
• Melbourne R Users Meetup page
• Robert Hyndman’s Webpage
• Rob’s previous talk on Forecasting time series using R
• Complete play list of Melbourne R User videos here

Andrew Robinson is deputy director of ACERA and senior lecturer in applied statistics at the University of Melbourne. He is co-author of 2.95 books on R: “Forest Analystics with R” and “Introduction to Scientific Programming and Simulation Using R“, and the hopefully soon to be completed “Methods of Statistical Model Estimation“.

Additional Resources:

• Slides for the talk
• Melbourne R Users Meetup page
• Andrew Robinson’s Home Page
• Andrew Robinson’s 150+ page introduction to R “IcebreakR” available as PDF
• Complete play list of Melbourne R User videos here

I summarized (with short demos) a few of the talks from the useR! 2012 conference. We are planning one more meetup to cover more talks.

Topics discussed: byte-code compiling, the devtools package, ggmap, Rstudio‘s latest features (projects, git/svn, knitr-markdown integration for reproducible research), cranvas, Simon Urbanek’s talk on interactive graphics in the browser (with Rserve and FastRWeb on the backend), tabplot and httr.

This is just a very small slice of the excellent talks I have attended. It was an awesome conference, thanks to the organizers, the speakers and to the participants. I’ll try to cover some more talks in a following Los Angeles R users group meetup, though the choice of topics will still be heavily biased by my main interests (and even within that subset I cannot really cover all the interesting talks). I encourage you to attend next year, so you can have it all.

To quote the outline of the talk :

R is a brilliant piece of software but learning it by yourself, particularly
if you have not used command line software before, can be daunting. This
presentation is aimed at introducing beginner to intermediate users of R to
some of the basic features of the program (through to programming a basic
function). Experienced R users are also encouraged to attend to help share
their knowledge and help the first-timers.

This presentation will be interactive, so if you are able to bring a laptop
with R ( http://cran.r-project.org/ ) already installed this will help you
participate (but is not mandatory). Two other handy pieces of software are
the R Studio development interface ( http://rstudio.org/ ) and the Tinn-R
text editor ( http://sourceforge.net/projects/tinn-r/ ), both of which help
you to organise and save your R code.

Lyndon Walker has been using R for nearly half his life. He studied and worked
at the UniveRsity of Auckland, the birthplace of R, and is currently a Senior
Lecturer in Applied Statistics at Swinburne University of Technology in
Melbourne.

• Slides from the talk can be seen here in Prezi
  format.
• Also see the complete play list of Melbourne R User videos
  here

Recent advances in medical imaging allow us to routinely acquire highly detailed images of the living human brain. These images can be used to inform us about how structural and functional changes in the brain are associated with disease and the environment. The wealth of information captured with these imaging methods has lead to additional challenges in processing and interpreting the data. In this talk I will describe how an MRI scan is acquired; how image analysis techniques help us understand neurological disorders, with a focus on epilepsy; and some challenges that face medical image analysis. Along the way I will talk about how R has helped my research.

Heath Pardoe is a postdoc at the Florey Neuroscience Institutes. He started out doing experimental physics, but would now almost describe himself as a neuroscientist. He uses image analysis methods to explore facets of the relationship between brain changes and neurological disorders. The primary neurological disorder he investigates is epilepsy. His current research interests include how the structure of the brain may be different in people with epilepsy, the impact of epileptic seizures on the brain, and how the brain changes during treatment with antiepileptic medication.

Also, see here for the complete play list of Melbourne R User Videos.

Eu Jin is a Senior Analyst with Deloitte Analytics in Melbourne. He has over four years experience in data mining and statistical modelling in various industries, developing solutions to solve difficult problems. Prior to joining Deloitte, Eu Jin worked for NAB (National Australia Bank) and TNS in marketing research.

Other than being a senior analyst at Deloitte, Eu Jin is also a competitive data miner (he recently won a Kaggle competition on credit scoring with fellow MelbURNian Alec Stephenson). In this presentation he’ll talk about the benefits of R from a data mining competitor’s point of view and from the point of view of an employee at Deloitte. The key insight from his experiences with R is that although R is the top favourite for recreational use, it’s not quite there yet for full commercial deployment. He’ll show what are some of the good things that R does well and some that it doesn’t do quite well, from his experience working in Deloitte versus using it for recreational purposes.

Unfortunately, we had to fall back on a secondary camera which resulted in some audio issues.
You can also see the complete play list of Melbourne R User Videos.

• Slides from the talk can be seen here in Prezi
  format.

Many thanks to Revolution Analytics for
providing support for our end of year party, and Pedro Olaya for filming.

Also see the complete play list of Melbourne R User videos
here