You may run an ANOVA, or Regression, or some other estimation procedure in Stata and get the error… too many variables or values (matsize too small) r(146); By default, Stata…
Read More

This page shows how to obtain Monte Carlo standard errors and confidence intervals for indirect effects in a mediation analysis. We will illustrate the process using the hsbdemo dataset. For…
Read More

A user-written command called meansdplot that will produce this type of graph. To get this program just type the following into the Stata command box and follow the instructions: search…
Read More

Mediator variables are variables that sit between independent variable and dependent variable and mediate the effect of the IV on the DV. Recently, we received a question concerning mediation analysis…
Read More

Little and Rubin (2002 p. 87) recommend a three step procedure for using multiple imputation with bootstrap standard errors: Generate bootstrap samples from the unimputed data; Impute missing values in…
Read More

NOTE:  Code for this page was tested in Stata 12. Computing indirect effects with multiply imputed data takes a few more step than for a conventional non-imputed model. Let’s begin…
Read More

NOTE:  Code for this page was tested in Stata 12. Mediation analysis with multiply imputed data takes a few more step than for a conventional non-imputed model. We looked at…
Read More

How can I perform multiple imputation on longitudinal data using ICE? Imputing longitudinal or panel data poses special problems. If  the data are in long form, each case has multiple…
Read More

R2 and adjusted R2 are often used to assess the fit of OLS regression models. Below we show how to estimate the R2 and adjusted R2 using the user-written command…
Read More

The margins command introduced in Stata 11 is a very popular post-estimation command. However, it can be tricky to use in conjunction with multiple imputation and survey data. Let’s begin…
Read More