Direct and Cross Demand Elasticities in a Model with Many Sectors, Econometrica (Apr. 1959). Goldberger, A. S., Econometric Theory (New York: John Wiley & Sons, Inc., 1964). Jorgenson, D. W., Lecture Notes: Economics 241 Part IV: The Multivariate Structural Model (Berkeley, California: Committee on Econometrics and Mathematical Economics, Institute of Business and Economic Research, University of California at Berkeley, 1962). Lemke, C. E., A Method of Solution for Quadratic Programs, Management Science (Aug. 1962), 442-453. Mangasarian, 0. L., Duality in Nonlinear Programming, Quarterly Journal of Applied Mathematics 20 (1962), 300-302.

Peter Schmidt, The Small Sample Effects of Various Treatments of Truncation Remainders in the Estimation of Distributed Lag Models, The Review of Economics and Statistics, Vol. 57, No. 3 (Aug., 1975), pp. 387-389

Michael Thomson, Peter Schmidt, A Note on the Comparison of the Mean Square Error of Inequality Constrained Least Squares and Other Related Estimators, The Review of Economics and Statistics, Vol. 64, No. 1 (Feb., 1982), pp. 174-176

We study the results of elections of Fellows of the Econometric Society. We aremotivated largely by the question of whether these elections are “fair,” where our defini-tion of fairness is that votes are based solely on the quality of the candidates. If so, thenconditional on quality other characteristics of the candidates (such as geographic locationor subspecialty) should not influence the probability of election. We find that, conditionalon a number of measures of the quality of the candidates, other characteristics do sig-nificantly predict election. For example, an Australian econometrician is less likely to beelected than a North America-based economic theorist. This is true whether or not wecontrol for quality measures.One might object that even fully informed individuals may differ in their assessment ofquality, and that neither the voters nor the authors of this study are fully informed aboutcandidates’ quality. This is true in any study of the impact of ascriptive characteristics onoutcomes. We discuss various interpretations of our findings in the conclusion, but readersmust draw their own conclusions about what the results imply about the roles of qualityand fairness in this electoral process.1 the electoral institutionMost members of the economics profession consider election as a Fellow as an honor.It recognizes prior professional achievements (within what are the more technical areasof economics). There are roughly 500 living Fellows. Names are placed on the ballot inone of two ways: (i) by the Nominating Committee of the Society, or (ii) by petition ofat least three members (who need not be but usually are current Fellows). The ballotcontains the candidate’s name and current affiliation; a list of at most six publications; ashort statement of the candidate’s contribution to economics; and an indication of whetherthe nomination was by Committee or by endorsers and, if the latter (from 1990 through2000), the names of all the endorsers. The ballot deadline is April 30.The electorate, dues-paying current Fellows, receive the ballot in early autumn alongwith the nomination form for each candidate, mark their ballots, and return them tothe Society’s office. Results are announced in December. Names on the ballot are inalphabetical order, with a different starting point in each annual election. Voters checkthe names of individuals whom they wish to be elected. A candidate is elected who isapproved on at least 30 percent of the ballots returned. (Typically about half the eligibleFellows cast votes.) Losing candidates can be nominated in later years by either of thetwo methods, but the process must be undertaken de novo.

In this paper we present a specification test for the Tobit model. Specifically, we test the Tobit model against the alternative of a two-part model in which one set of parameters determines the probability of a limit observation while a second set of parameters determines the distribution of the non-limit observations. An advantage of our test is that it is easily calculated from the Tobit residuals.

IN AN IMPORTANT RECENT PAPER, Hausman and Taylor (1981)-hereafter HT-considered the instrumental-variable estimation of a regression model using panel data, when the individual effects may be correlated with a subset of the explanatory variables. They provided a simple consistent estimator and an efficient estimator. More recently, Amemiya and MaCurdy (1986)-hereafter AM-have suggested an alternative estimator which is more efficient than the HT estimator, under certain conditions and given stronger assumptions than HT made. However, the relationship between the HT and AM papers is less clear than it might be, in part because of notational differences between the two papers. In this paper we clarify the relationship between the HT and AM estimators, and we show that the difference between these estimators lies in the treatment of the time-varying explanatory variables which are uncorrelated with the effects: HT use each such variable as two instruments (means and deviations from means), while AM use such variables as T + 1 instruments (as deviations from means and also separately for each of the T available time periods). This enables us to make clear the conditions under which the AM estimator is more efficient than the HT estimator. We also present each estimator in a form which allows it to be calculated using standard instrumental-variables (two-stage least squares) software. Following the AM path one step further, we then define a third (BMS) estimator which, under yet stronger assumptions, is more efficient than the AM estimator. Both HT and AM use as instruments the deviations from means of the time-varying variables which are correlated with the effects. A more efficient estimator may be obtained by using separately the (T - 1) linearly independent values of these deviations from individual means. Consistency requires that these be legitimate instruments, and whether this is so depends on why these time-varying variables are correlated with the effects. For example, if such correlation arises solely because of a time-invariant component which is removed in taking deviations from individual means, these instruments are legitimate.