Testing for the presence of measurement error in Stata

Published on 23 September 2019

In this paper, we describe how to test for the presence of measurement error in explanatory variables.

Downloads

Image representing the file: CW4719-Testing-for-the-presence-of-measurement-error-in-Stata.pdf

CW4719-Testing-for-the-presence-of-measurement-error-in-Stata.pdf

PDF | 495.72 KB

In this paper, we describe how to test for the presence of measurement error in explanatory variables. First, we discuss the test of such hypotheses in parametric models such as linear regressions and then introduce a new Stata command [R] dgmtest for a nonparametric test proposed in Wilhelm (2018). To illustrate the new command, we provide Monte Carlo simulations and an empirical application to testing for measurement error in administrative earnings data.

Authors

Daniel Wilhelm
Daniel Wilhelm

Research Associate LMU Munich

Daniel is a Research Associate of the IFS in Cemmap and Professor of Statistics and Econometrics at LMU Munich.

Person graphic

Young Jun Lee

Working Paper details

DOI
10.1920/wp.cem.2019.4719
Publisher
The IFS

Suggested citation

Jun Lee, Y and Wilhelm, D. (2019). Testing for the presence of measurement error in Stata. London: The IFS. Available at: https://ifs.org.uk/publications/testing-presence-measurement-error-stata (accessed: 18 April 2024).

Grant

Advancing microdata models and methods

More from IFS

Understand this issue

Policy analysis

Academic research

Working Paper Cover

Robust analysis of short panels

working paper
Examples of application to some static and dynamic binary, ordered and multiple discrete choice panel data models are presented.

8 January 2024