# Monthly Archives: August 2013

## Uncertainty in parameter estimates using multilevel models

August 3, 2013
By

David Hsu writes: I have a (perhaps) simple question about uncertainty in parameter estimates using multilevel models — what is an appropriate threshold for measure parameter uncertainty in a multilevel model? The reason why I ask is that I set out to do a crossed two-way model with two varying intercepts, similar to your flight The post Uncertainty...

## Gibbs Sampler in C++

August 3, 2013
By

Markov Chain Monte Carlo (MCMC) is a popular simulation method. As it is somewhat demanding, it is also frequently used to benchmark different implementations or algorithms. One particular algorithm has been compared a number of times, starting with an article by Darren Wilkinson, and Darren’s follow–up article which in turns responded in part to our article. This post...

## Demand for R jobs on the rise, while SAS jobs decline

August 2, 2013
By

Job-tracking site indeed.com shows the rate at which certain terms appear in job advertisements. As you can see from the chart below, demand for R language skills is on the rise, while the number of SAS-related job postings peaked in late 2010 and has been declining steadily since early 2012. I included the word "statistics" in the search to...

## Dashboards in R with Shiny and GoogleVis

August 2, 2013
By

Previously on this post, I introduced limitedly some features of the Shiny package. However, I felt the need of doing a new post related to Dashboards due to many reasons: a) Shiny has changed most of its functions and the … Continue reading →

## N armed bandit simulation

August 2, 2013
By

As i learn more and more about machine learning and AI algorithms in general, i came across this book by Sutton & Barto, which is all about reinforcement learning. As i read through the action-value topic, it seemed a nice R-challenge, so here's the complete code: To test one greedy player and two epsilon...

## Delimited file where delimiter clashes with data values

August 1, 2013
By

A comma-separated values (CSV) file is a typical way to store tabular/rectangular data. If a data cell contain a comma, then the cell with the commas is typically wrapped with quotes. However, what if a data cell contains a comma … Continued

## Package sqldf eases the multivariable sorting pain

August 1, 2013
By

This will be a quick one.  I was trying to sort my dataframe so that it went in ascending order on one variable and descending order on another variable.  This was really REALLY bothersome to try to figure out with … Continue reading →

## Model Scale Parameterization for MCMC Efficiency

August 1, 2013
By
$Model Scale Parameterization for MCMC Efficiency$

I recently came across a very interesting paper by Y. Yu and X. Meng who present an interweaving strategy between different model parameterizations to improve mixing. It is well known that different model parameterizations can perform better than others under certain conditions. Papaspiliopoulos, Roberts and Sköld present a general framework for how to parameterize The post Model...

## Statisticians: an endangered species?

August 1, 2013
By

by Joseph Rickert Every month I look forward to getting my copy of AMSTATNEWS, the monthly magazine of the American Statistical Association, in the mail. This July, I was both pleased and bemused by ASA President Marie Davidian’s article Aren’t We Data Science?. I was pleased to see a follow up to last month’s article The ASA and Big...