Robust standard errors in dtable

[Kyle Huisman]

When using the by category and test options with the d-table it will conduct a linear regression/two-way t-test and report the p-value. (If there is more than one group, it reports the f-test.)

Is there anyway to get dtable to use robust instead of regular standard errors? As far as I can tell from the documentation the answer is no. But I'm wondering if I might be able to set robust standard errors as a Stata default somehow, or jury rig some other solution to force dtable to use robust standard errors.

Trying to avoid using collect as I have dozens and dozens of statistics to report and already have a dtable program written.

[Jeff Pitblado (StataCorp)]

Do you have survey data? Try dtable's svy option, after you svyset the dataset. You can also svyset an SRS dataset with

svyset _n

Your only other option is to use [pweight=1].