(This article was originally published at The DO Loop, and syndicated at StatsBlogs.)
I began 2015 by compiling a list of popular articles from my blog in 2014. Although this "People's Choice" list contains many interesting articles, some of my favorites did not make the list. Today I present the "Editor's Choice" list of articles that deserve a second look. I've highlighted one article from each month of 2014.
I've grouped the articles into three broad topics: simulating data, statistical graphics, and matrix computations.
Simulating data and resampling
- Many SAS programmers need to know how to sample with replacement in SAS or how to sample with replacement in SAS/IML.
- A related task is how to sample without replacement in SAS.
- For simulation studies, you sometimes need to know how to simulate data from a logistic regression model.
- Resampling techniques are closely related to simulating data. The SAS/IML language enables you to implement resampling and permutation tests in SAS with only a few lines of code.
Statistical graphics
- Learn how to color scatter plot markers by values of a continuous variable.
- Learn how to add a prediction ellipse to a scatter plot in SAS.
- Have you ever wrestled with the task of choosing bins for a histogram? Learn two ways to choose bins for histograms in SAS.
- When you create a box plot or bar chart, it is often useful to sort the categories according to some criterion. Learn how to order categories by values of a statistic.
Matrix computations
- Have you ever tried to create a big matrix, only to receive the error message "Unable to allocate sufficient memory"? Learn how much RAM you need to create a large matrix in SAS/IML.
- Textbooks and journal articles often provide matrix formulas for computing statistical quantities. But a straightforward coding of some formulas might not be efficient. In particular, never multiply with a large diagonal matrix.
- I believe in the saying, "All work and no play makes Jack a dull boy." Blog posts about Wolfram's cellular automata and Conway's "game of life" might not help you with your next work project, but they sure are fun!
- Similarly, computing Pascal's triangle in SAS is not something that many statisticians do, but the self-similar structures in the triangle are breathtaking!
Many of the previous articles use the SAS/IML language. In 2014 SAS made the SAS/IML language freely available. The IML procedure is included as part of the SAS University Edition, which is free for students, professors, researchers, and adult learners.
Two additional articles from 2014 are worth highlighting because of their importance to SAS/IML programmers:
- Create standard ODS statistical graphs from within a SAS/IML program (requires SAS/IML 12.3).
- Browse the SAS/IML File Exchange to download ready-to-use programs. You can also share programs that you have written by uploading them to the File Exchange.
There you have it, 12 topics that I think are worth a second look. What was your favorite article from The DO Loop in 2014? Leave a comment.
Please comment on the article here: The DO Loop
