Follow us
Publications Commentary Research People Events News Resources and Videos About IFS
Home Publications bootwildct


Bansi Malde and Molly Scott

This command implements the wild-cluster bootstrap-t procedure, with a specified null hypothesis, as described in Cameron et al (2007). This procedure is shown to improve inference in cases with few clusters.

It is a post-estimation command, which works for linear models with clustered standard errors and with simple hypotheses only. The command should work with versions of stata above 10.1. Note that varlist should include ALL the right hand side variables included in the linear model for which one estimates these t-statistics.

The zip folder contains an ado file and a help file.

More on this topic

Cemmap Working Paper CWP49/19
We propose a new nonparametric test of stochastic monotonicity which adapts to the unknown smoothness of the conditional distribution of interest, possesses desirable asymptotic properties, is conceptually easy to implement, and computationally attractive.
Cemmap Working Paper CWP50/19
The multinomial logit model with random coefficients is widely used in applied research. This paper is concerned with estimating a random coefficients logit model in which the distribution of each coefficient is characterized by finitely many parameters.
Cemmap Working Paper CWP52/19
We establish nonparametric identification in a class of so-called index models using a novel approach that relies on general topological results.
Cemmap Working Paper CWP47/19
In this paper, we describe how to test for the presence of measurement error in explanatory variables.
Cemmap Working Paper CWP48/19
This paper proposes a simple nonparametric test of the hypothesis of no measurement error in explanatory variables and of the hypothesis that measurement error, if there is any, does not distort a given object of interest.