StatLab Articles

Multivariate Multiple Regression is a method of modeling multiple responses, or dependent variables, with a single set of predictor variables. For example, we might want to model both math and reading SAT scores as a function of gender, race, parent income, and so forth. This allows us to evaluate the relationship of, say, gender with each score. You may be thinking, "why not just run separate regressions for each dependent variable?" That's actually a good idea! And in fact that's pretty much what multivariate multiple regression does.

Proportional-odds logistic regression is often used to model an ordered categorical response. By "ordered", we mean categories that have a natural ordering, such as "Disagree", "Neutral", "Agree", or "Everyday", "Some days", "Rarely", "Never". For a primer on proportional-odds logistic regression, see our post, Fitting and Interpreting a Proportional Odds Model.

If you're wondering what exactly the purrr package does, then this blog post is for you.

Sometimes we have data with dates and/or times that we want to manipulate or summarize. A common example in the health sciences is time-in-study. A subject may enter a study on February 12, 2008, and exit on November 4, 2009. How many days was the person in the study? (Don’t forget 2008 was a leap year; February had 29 days.) What was the median time-in-study for all subjects?

The Wilcoxon Rank Sum Test is often described as the non-parametric version of the two-sample t-test. You sometimes see it in analysis flowcharts after a question such as "is your data normal?" A "no" branch off this question will recommend a Wilcoxon test if you're comparing two groups of continuous measures.

So what is this Wilcoxon test? What makes it non-parametric? What does that even mean? And how do we implement it and interpret it? Those are some of the questions we aim to address in this post.

Pairwise comparison means comparing all pairs of something. If I have three items, A, B and C, that means comparing A to B, A to C, and B to C. Given n items, I can determine the number of possible pairs using the binomial coefficient: $$ \frac{n!}{2!(n - 2)!} = \binom {n}{2}$$ Using the R statistical computing environment, we can use the choose() function to quickly calculate this.

There are times we need to do some repetitive tasks in the process of data preparation, analysis, or presentation. For instance, we may need to compute a set of variables in the same manner, rename or create a series of variables, or repetitively recode values of a number of variables. In this post, we show a few simple example "loops" using the Stata commands foreach, local and forvalues to handle some common repetitive tasks.

In this post, we demonstrate how to convert datasets between wide form and long form. This is also known as "reshaping data". Reshaping is often needed when you work with datasets that contain variables with some kinds of sequences, say, time-series data. It is fairly easy to transform data between wide and long forms in Stata using the reshape command, however you'll want to be careful when you do so to eliminate possible mistakes in the process of transforming. First, let's see how the wide and long forms look.

When we first start working with data, usually in a statistics class, we mostly use clean and completed datasets as examples. Later on, we realize data is not always clean or complete when doing research or data analysis for other purposes. In reality, we often need to put two or more datasets together to begin whatever statistical analysis tasks we would like to perform. In this post, we demonstrate how to combine datasets using append and merge, which are row-wise combining and column-wise combining, respectively.

Sometimes only parts of a dataset mean something to you. In this post, we show you how to subset a dataset in Stata by variables or by observations. We use the census.dta dataset installed with Stata as the sample data.