\(\newcommand{\Eb}{{\bf E}}\)This post was written jointly with Enrique Pinzon, Senior Econometrician, StataCorp.

The generalized method of moments (GMM) is a method for constructing estimators, analogous to maximum likelihood (ML). GMM uses assumptions about specific moments of the random variables instead of assumptions about the entire distribution, which makes GMM more robust than ML, at the cost of some efficiency. The assumptions are called moment conditions.

GMM generalizes the method of moments (MM) by allowing the number of moment conditions to be greater than the number of parameters. Using these extra moment conditions makes GMM more efficient than MM. When there are more moment conditions than parameters, the estimator is said to be overidentified. GMM can efficiently combine the moment conditions when the estimator is overidentified.

We illustrate these points by estimating the mean of a \(\chi^2(1)\) by MM, ML, a simple GMM estimator, and an efficient GMM estimator. This example builds on Efficiency comparisons by Monte Carlo simulation and is similar in spirit to the example in Wooldridge (2001). Read more…

I make three improvements to the command that implements the ordinary least-squares (OLS) estimator that I discussed in Programming an estimation command in Stata: Allowing for sample restrictions and factor variables. First, I allow the user to request a robust estimator of the variance-covariance of the estimator (VCE). Second, I allow the user to suppress the constant term. Third, I store the residual degrees of freedom in e(df_r) so that test will use the \(t\) or \(F\) distribution instead of the normal or \(\chi^2\) distribution to compute the \(p\)-value of Wald tests.

This is the ninth post in the series Programming an estimation command in Stata. I recommend that you start at the beginning. See Programming an estimation command in Stata: A map to posted entries for a map to all the posts in this series. Read more…

I modify the ordinary least-squares (OLS) command discussed in Programming an estimation command in Stata: A better OLS command to allow for sample restrictions, to handle missing values, to allow for factor variables, and to deal with perfectly collinear variables.

This is the eighth post in the series Programming an estimation command in Stata. I recommend that you start at the beginning. See Programming an estimation command in Stata: A map to posted entries for a map to all the posts in this series. Read more…

I use the syntax command to improve the command that implements the ordinary least-squares (OLS) estimator that I discussed in Programming an estimation command in Stata: A first command for OLS. I show how to require that all variables be numeric variables and how to make the command accept time-series operated variables.

This is the seventh post in the series Programming an estimation command in Stata. I recommend that you start at the beginning. See Programming an estimation command in Stata: A map to posted entries for a map to all the posts in this series. Read more…

\(
\newcommand{\betab}{\boldsymbol{\beta}}
\newcommand{\xb}{{\bf x}}
\newcommand{\yb}{{\bf y}}
\newcommand{\Xb}{{\bf X}}
\)I show how to write a Stata estimation command that implements the ordinary least-squares (OLS) estimator by explaining the code. I use concepts that I introduced in previous #StataProgramming posts. In particular, I build on Programming an estimation command in Stata: Using Stata matrix commands and functions to compute OLS objects, in which I recalled the OLS formulas and showed how to compute them using Stata matrix commands and functions and on
Programming an estimation command in Stata: A first ado command, in which I introduced some ado-programming concepts. Although I introduce some local macro tricks that I use all the time, I also build on Programing an estimation command in Stata: Where to store your stuff.

This is the sixth post in the series Programming an estimation command in Stata. I recommend that you start at the beginning. See Programming an estimation command in Stata: A map to posted entries for a map to all the posts in this series. Read more…

\(\newcommand{\epsilonb}{\boldsymbol{\epsilon}}
\newcommand{\ebi}{\boldsymbol{\epsilon}_i}
\newcommand{\Sigmab}{\boldsymbol{\Sigma}}
\newcommand{\betab}{\boldsymbol{\beta}}
\newcommand{\eb}{{\bf e}}
\newcommand{\xb}{{\bf x}}
\newcommand{\zb}{{\bf z}}
\newcommand{\yb}{{\bf y}}
\newcommand{\Xb}{{\bf X}}
\newcommand{\Mb}{{\bf M}}
\newcommand{\Eb}{{\bf E}}
\newcommand{\Xtb}{\tilde{\bf X}}
\newcommand{\Vb}{{\bf V}}\)I present the formulas for computing the ordinary least-squares (OLS) estimator, and I discuss some do-file implementations of them. I discuss the formulas and the computation of independence-based standard errors, robust standard errors, and cluster-robust standard errors. I introduce the Stata matrix commands and matrix functions that I use in ado-commands that I discuss in upcoming posts.

This is the fifth post in the series Programming an estimation command in Stata. I recommend that you start at the beginning. See Programming an estimation command in Stata: A map to posted entries for a map to all the posts in this series. Read more…

I discuss the code for a simple estimation command to focus on the details of how to implement an estimation command. The command that I discuss estimates the mean by the sample average. I begin by reviewing the formulas and a do-file that implements them. I subsequently introduce ado-file programming and discuss two versions of the command. Along the way, I illustrate some of the postestimation features that work after the command.

This is the fourth post in the series Programming an estimation command in Stata. I recommend that you start at the beginning. See Programming an estimation command in Stata: A map to posted entries for a map to all the posts in this series. Read more…

I discuss a pair of examples that illustrate the differences between global macros and local macros. You can view this post as a technical appendix to the previous post in the #StataProgramming series, which introduced global macros and local macros.

In every command I write, I use local macros to store stuff in a workspace that will not alter a user’s data and to make my code easier to read. A good understanding of the differences between global macros and local macros helps me to write better code. The essential differences between global macros and local macros can be summarized in two points. Read more…

If you tell me “I program in Stata”, it makes me happy, but I do not know what you mean. Do you write scripts to make your research reproducible, or do you write Stata commands that anyone can use and reuse? In the series #StataProgramming, I will show you how to write your own commands, but I start at the beginning. Discussing the difference between scripts and commands here introduces some essential programming concepts and constructions that I use to write scripts and commands.

This is the second post in the series Programming an estimation command in Stata. I recommend that you start at the beginning. See Programming an estimation command in Stata: A map to posted entries for a map to all the posts in this series. Read more…

Distributing a Stata command that implements a statistical method will get that method used by lots of people. They will thank you. And, they will cite you!

This post is the first in the series #StataProgramming about programing an estimation command in Stata that uses Mata to do the numerical work. In the process of showing you how to program an estimation command in Stata, I will discuss do-file programming, ado-file programming, and Mata programming. When the series ends, you will be able to write Stata commands.

Stata users like its predictable syntax and its estimation-postestimation structure that facilitates hypothesis testing, specification tests, and parameter interpretation. To help you write Stata commands that people want to use, I illustrate how Stata syntax is predictable and give an overview of the estimation-postestimation structure that you will want to emulate in your programs. Read more…