In 2013 I published 110 blog posts. Some of these articles were more popular than others, often because they were linked to from a SAS newsletter such as the SAS Statistics and Operations Research News. In no particular order, here are some of my most popular posts from 2013, organized into categories. I've included two posts from December of 2012 because December articles rarely get a chance to appear on these "Best of" lists.
Although I generally write about statistical topics and programming, sometimes I just like to have a little fun:
- Like fractals? Like Christmas? Then you will enjoy seeing the fractal Christmas tree that I created for Christmas 2012.
- Do you know how old your version of SAS is? Read the main article to discover the dates of SAS releases going back to SAS version 8.0, and read the comments to go back in time to 1972!
The International Year of Statistics
To celebrate 2013 as the International Year of Statistics, I wrote several historical articles:
- Are you impressed when you hear that many thousands of students enroll in a massive open online courses (MOOC) in statistics and data analysis? Read the story of a statistics course that attracted 1.2 million students in 1960!
- The biography of Jerome Cornfield, the statistician who established risk factors for lung cancer and heart disease.
As the preceding titles indicate, often "popular" is correlated with "less technical." But not always. In 2013 I published Simulating Data with SAS, and several of my more popular articles dealt with how to efficiently carry out simulation with SAS software.
- How to generate multiple samples from the multivariate normal distribution.
- How to use the inverse CDF method to simulate from a univariate distribution.
- How to use simulation to estimate the power of a statistical test.
- A personal favorite: Why you should stop using the RANUNI function to generate random numbers.
Statistical Graphics and Data Analysis
Statistical data analysis and graphics are the "bread and butter" of my blog. Here are a few articles that attracted more readers than usual.
- How to use PROC SGPLOT to display the slope and intercept of a regression line on a graph.
- Why quantile regression is better than connecting the sample quantiles of binned data.
- The residual-fit spread plot is one of the plots that are created automatically by procedures such as PROC REG. This article describes how to interpret a residual-fit spread plot.
- The distance between observations is used in clustering and nearest-neighbor computations. This article describes three ways to compute the distance between observations in SAS.
- In SAS 9.4 it is easy to show percentages for bar charts by using PROC SGPLOT. In SAS 9.3, it is not so easy. This article describes how to show percentages for bar charts in SAS 9.3.
Start your new year by (re-)reading some of these popular posts from 2013. Next week I'll resume posting new articles on topics in statistics, programming, graphics, and simulation. Happy New Year to all my readers!