ARCHIVED: In Stata, how do I get the p-values for correlation coefficients?

This content has been archived, and is no longer maintained by Indiana University. Information here may no longer be accurate, and links may no longer be available or reliable.

In Stata, you can use either the .correlate or .pwcorr command to compute correlation coefficients. The following examples produce identical correlation coefficient matrices for the variables income, gnp, and interest:

  .correlate income gnp interest
  .pwcorr income gnp interest

The .correlate command produces a correlation coefficient matrix and a variance-covariance matrix using the covariance option, but it does not give p-values for correlation coefficients, for example:

  .correlate income gnp interest, covariance

In contrast, the .pwcorr command generates a correlation coefficient matrix with p-values using the sig option, but it does not give a variance-covariance matrix. Consider the following examples for obtaining correlation coefficients and their p-values:

  .pwcorr income gnp interest, sig
  .pwcorr income gnp interest, sig print(.05)
  .pwcorr income gnp interest, sig star(.05)

The first command generates a correlation coefficient matrix with p-values. The second line outputs correlation coefficients and p-values only when their p-values are less than .05; that is, the coefficients with greater than the .05 significance level are left blank. The print(.05) specifies the significance level of coefficients to be suppressed. The third command generates correlation coefficients and p-values, and places an asterisk (*) next to the coefficients only when the p-value is .05 or lower. The star(.05) option requests that an asterisk be printed for correlation coefficients with p-values of .05 or lower.

If you have questions about using statistical and mathematical software at Indiana University, contact the UITS Research Applications and Deep Learning team.

This is document alya in the Knowledge Base.
Last modified on 2023-05-09 14:37:37.