Search

Begin New Search Topic Third World Author David Roodman

1. Estimating Fully Observed Recursive Mixed-Process Models with cmp

Author:
David Roodman
Publication Date:
04-2009
Content Type:
Working Paper
Institution:
Center for Global Development
Abstract:
At the heart of many econometric models is a linear function and a normal error. Examples include the classical small-sample linear regression model and the probit, ordered probit, multinomial probit, Tobit, interval regression, and truncated-distribution regression models. Because the normal distribution has a natural multidimensional generalization, such models can be combined into multi-equation systems in which the errors share a multivariate normal distribution. The literature has historically focused on multi-stage procedures for estimating mixed models, which are more efficiently computationally, if less so statistically, than maximum likelihood (ML). But faster computers and simulated likelihood methods such as the Geweke, Hajivassiliou, and Keane (GHK) algorithm for estimating higher-dimensional cumulative normal distributions have made direct ML estimation practical. ML also facilitates a generalization to switching, selection, and other models in which the number and types of equations vary by observation. The Stata module cmp fits Seemingly Unrelated Regressions (SUR) models of this broad family. Its estimator is also consistent for recursive systems in which all endogenous variables appear on the right-hand-sides as observed. If all the equations are structural, then estimation is full-information maximum likelihood (FIML). If only the final stage or stages are, then it is limited-information maximum likelihood (LIML). cmp can mimic a dozen built-in Stata commands and several user-written ones. It is also appropriate for a panoply of models previously hard to estimate. Heteroskedasticity, however, can render it inconsistent. This paper explains the theory and implementation of cmp and of a related Mata function, ghk2(), that implements the GHK algorithm.
Topic:
Development, Humanitarian Aid, Poverty, and Third World

2. A Short Note on the Theme of Too Many Instruments

Author:
David Roodman
Publication Date:
08-2007
Content Type:
Working Paper
Institution:
Center for Global Development
Abstract:
The “difference” and “system” generalized method of moments (GMM) estimators for dynamic panel models are growing steadily in popularity. The estimators are designed for panels with short time dimensions (T), and by default they generate instruments sets whose number grows quadratically in T. The dangers associated with having many instruments relative to observations are documented in the applied literature. The instruments can overfit endogenous variables, failing to expunge their endogenous components and biasing coefficient estimates. Mean while they can vitiate the Hansen J test for joint validity of those instruments, as well as the difference-in-Sargan/Hansen test for subsets of instruments. The weakness of these specification tests is a particular concern for system GMM, whose distinctive instruments are only valid under a non-trivial assumption. Judging by current practice, many researchers do not fully appreciate that popular implementations of these estimators can by default generate results that simultaneously are invalid yet appear valid. The potential for type I errors—false positives—is therefore substantial, especially after amplification by publication bias. This paper explains the risks and illustrates them with reference to two early applications of the estimators to economic growth, Forbes (2000) on income inequality and Levine, Loayza, and Beck (LLB, 2000) on financial sector development. Endogenous causation proves hard to rule out in both papers. Going forward, for results from these GMM estimators to be credible, researchers must report the instrument count and aggressively test estimates and specification test results for robustness to reductions in that count.
Topic:
Development, Economics, Political Economy, and Third World