Skip to content
Stata code for Re-scaled Regression Prediction (RRP)
Stata TeX
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.


Stata code for Re-scaled Regression Prediction (RRP)

Recent Updates

  • version 0.2 18 June 2019
    • update for unequal sample sizes
  • version 0.1 26 Feb 2019
    • First Version


This is a development version, to download it and use, open Stata and run the following:

cap ado uninstall rrp
net install rrp, from("")


This repository contains the Stata package implementing the Rescaled Regression Prediction (RRP) using two samples in two steps, as described in Crossley et al. (2019).


The command requires the user to first run the first-stage regression in the dataset that contains the dependent variable and the proxies, and store it. For example:

reg y1 z1
est store stage1

Then, in the other dataset, the user may run rrp, keeping the order of the proxies the same as in the first stage. The command returns the output of the regression table with the corrected Standard Errors, and creates the RRP imputed dependent variable, named yhatRRP. For example:

rrp x2 , proxies(z2) first(stage1)


Crossley, T.F., Levell, P., and Poupakis, S. (2019). Regression with an Imputed Dependent Variable, Working Paper.

You can’t perform that action at this time.