Knowledge that Transforms

Suthathip Yaisawarng, J. Douglass Klein, The Effects of Sulfur Dioxide Controls on Productivity Change in the U.S. Electric Power Industry, The Review of Economics and Statistics, Vol. 76, No. 3 (Aug., 1994), pp. 447-460

This research compares several approaches to inference in the multinomial probit model, based on two Monte Carlo experiments for a seven choice model.The methods compared are the simulated maximum likelihood estimator using the GHK recursive probability,simulator, the method of simulated moments estimator using the GHK recursive simulator and kernel-smoothed frequency simulators, and posterior means using a Gibbs sampling-data augmentation algorithm.Overall, the Gibbs sampling algorithm has a slight edge, with the relative performance of MSM and SML based on the GHK simulator being difficult to evaluate.The MSM estimator with the kernel-smoothed frequency simulator is clearly inferior.I. Introduction T HE multinomial probit is an appealing model of choice behavior because it allows a flexible pattern of conditional covariance among the latent utilities of alternatives.Nevertheless, multinomial probit applications have been limited because the required integrations of the multivariate normal density over subsets of Euclidean space are computationally burdensome.The computational simplicity of the multinomial logit has made it the model of choice for applied work.However, because the multinomial probit model relaxes the assumption of independence of irrelevant alternatives, it is generally preferred in principle to the multinomial logit model (McFadden, 1984, pp.1395-1458).Recently the method of simulated moments (McFadden, 1989; Pakes and Pollard, 1989) and Gibbs sampling with data augmentation (Albert and Chib, 1993; McCulloch and Rossi, 1994) have shown promise of making the required computations in the multinomial probit model practical.The development of the highly accurate GHK probability simulator (see Geweke, 1991; Hajivassiliou and McFadden, 1990; and Keane, 1990, 1994a) has also led to renewed interest in simulated maximum likelihood (Albright, Lerman, and Manski, 1977) as a method for estimating multinomial probit models.The objective of the research reported here is to provide a systematic comparison of the numerical properties of different simulation-based methods of inference in the multinomial probit model.Rather than considering the performance of these methods on a single model for a single data set, we attempt to control for a number of features of the inference problem, such as the number and nature of the unknown parameters of interest and the information content of the data on which inference is based.Also, we investigate for the first time how the performance of MSM estimation is affected by the type of probability simulator employed (i.e., GHK vs. kernel smoothing).While some investigators have examined the performance of particular estimators and computational techniques, Borsch-Supan and Hajivassiliou (1993), Hajivassiliou (1992), and Hajivassiliou, McFadden, and Ruud (1992) have made systematic comparison of alternative probability simulators, we are aware of only one systematic comparison of different estimators per se: Keane (1994a) compares method of simulated moments and simulated maximum likelihood estimators for an eight period binomial probit model in a Monte Carlo study.This paper is the first to compare performance of alternative methods of inference for the multinomial probit model and the first to examine how the relative performance of alternative methods differs across model specifications and across different data sets.In addition to addressing this main objective, this work introduces a new factor structure for the disturbances that may help to alleviate the proliferation of covariance matrix parameter problems in MNP models.We also illustrate Bayesian inference in a multinomial probit model with a factor structure for the first time.(See Elrod and Keane (forthcoming) for a discussion of factor structures for probit models.)

This paper investigates the effect of borrowing constraints on the timing of human capital investment in a developing country by looking at how quickly children with different family backgrounds progress through the primary school system in Peru. The main findings are that children start withdrawing from school earlier, as indicated by repetition of grades, in households with lower income and durable good holdings and when children are more closely spaced. Behavior also differs as predicted between children from households that appear to be borrowing constrained and those that appear unconstrained.

Previous attempts at estimating the economic model of crime with aggregate data relied heavily on cross-section econometric techniques and, therefore, do not control for unobserved heterogeneity. This is even true of studies that estimated simultaneous equations models. Using a new panel data set of North Carolina counties, the authors exploit both single and simultaneous equations panel data estimators to address two sources of endogeneity: unobserved heterogeneity and conventional simultaneity. Their results suggest that both labor market and criminal justice strategies are important in deterring crime but that the effectiveness of law enforcement incentives has been greatly overstated.

Using panel data for the forty-eight contiguous U.S. states in each year between 1970 and 1986, this paper investigates the extent to which government capital and current government services contribute to private production. The paper finds fairly strong evidence that current government educational services are productive but no evidence that the other government activities considered are productive. Indeed, government capital often has statistically significant negative productivity. The results are robust across the many specifications considered.

Over the past decade, a substantial literature on methods for the estimation of discrete choice dynamic programming (DDP) models of behavior has developed. However, the implementation of these methods can impose major computational burdens because solving for agents' decision rules often involves high dimensional integrations that must be performed at each point in the state space. In this paper we develop an approximate solution method that consists of: (1) using Monte Carlo integration to stimulate the required multiple integrals at a subset of the state points, and (2) interpolating the non-simulated values using a regression function. The overall performance of this approximation method appears to be excellent.

A number of studies have suggested a quantitatively important relationship between public-sector capital accumulation and private sector productivity, with the most compelling evidence derived from analyses of state-level data. Estimates herein of production functions that use standard techniques to control for unobserved, state-specific characteristics, however, reveal essentially no role for public-sector capital in affecting private sector productivity. Only estimates of state production functions that do not include such controls find substantial productivity impacts. This result reconciles existing econometric estimates with the findings of Hulten and Schwab based on growth accounting techniques, as such techniques effectively control for state-specific effects. Region-level estimates are essentially identical to those from state data, suggesting no quantitatively important spillover effects across states.

The findings in this paper provide some insight into how small firms are able to innovate. Using a production function approach to relate knowledge generating inputs to innovative output, the empirical results suggest that small firms are the recipients of R&D spillovers from knowledge generated in the R&D centers of their larger counterparts and in universities. Such R&D spillovers are apparently more decisive in promoting the innovative activity of small firms than of large corporations.

Immigrants' ties to their home countries can play a key role in fostering bilateral trade linkages. Immigrant ties include knowledge of home-country markets, language, preferences, and business contacts that have the potential to decrease trading transaction costs. Empirical results for the United States suggest that immigrant links have historically been important in increasing bilateral trade flows with immigrants' home countries.

Charles P. Himmelberg, Bruce C. Petersen, R & D and Internal Finance: A Panel Study of Small Firms in High-Tech Industries, The Review of Economics and Statistics, Vol. 76, No. 1 (Feb., 1994), pp. 38-51