This paper considers wage-hours contracts in the context of a jobsearch model. The response of a risk-averse worker to a wage translation of the offer distribution is examined. A robust example illustrates that some "natural" results need not hold.

This paper proposes a simple, new diagnostic indicating the presence of uncorrected heterogeneity in exponential models of duration. The use of the diagnostic is illustrated in an example dealing with unemployment duration in the DIME data. The diagnostic is seen to supplement the information on the fit given by the maximized likelihood value.

Journal Article A Note on Regime Classification in Disequilibrium Models Get access Nicholas M. Kiefer Nicholas M. Kiefer University of Chicago and CORE Search for other works by this author on: Oxford Academic Google Scholar The Review of Economic Studies, Volume 47, Issue 3, April 1980, Pages 637–639, https://doi.org/10.2307/2297314 Published: 01 April 1980 Article history Received: 01 December 1978 Accepted: 01 May 1979 Published: 01 April 1980

[The efficiency gain from observing the sample classification in a disequilibrium or switching model is analyzed. The problem is set up as one of comparing the precisions of estimates based on a joint density with those based on a marginal density. Asymptotic results are obtained for a simple model.]

[An efficient estimator for regressions in which the parameter vector can take any of several values is devised. It is shown that although the likelihood function is unbounded, the likelihood equations have a consistent root. An initial consistent estimator is provided. One Newton step provides efficient estimates. Applications to nonlinear models and contaminated normal models are suggested.]

This paper considers a model of earnings over time which incorporates individual effects and time effects without assuming that these effects are orthogonal to the variable of primary interest. The central coefficient is the effect of participation in a Manpower Development and Training Act training program on the earnings of trainees. Since the training status of (some) individuals in the sample changes during the period of the sample, both pre- and posttraining contrasts and trainee-nontrainee contrasts in earnings can be made. An estimate of the cross-section bias in a training coefficient can be made directly. The extent of the analogous bias in the education coefficient in regression studies is a point of current debate. The cross-section bias in the sample analyzed is large, and the estimated effect of training is small and positive.

An approximation to the inconsistency introduced by imposing an incorrect restriction on a parametric model is given. The approximation can be applied to estimators generated by optimizing any objective function satisfying certain regularity conditions. Examples given include analysis of misspecification in discrete choice and time-series models estimated by maximum likelihood, and in a nonlinear regression model. SPECIFICATION ERROR ANALYSIS in the linear regression model has been studied by Theil [1], who gives formulas for, e.g., the effect of leaving out relevant variables on the expected values of the estimators of the coefficients of the included variables. In this paper we suggest analogous formulas for estimators obtained by optimizing an objective function subject to restrictions. We have in mind maximizing (1/n) x loglikelihood and will usually use this terminology. We consider the effect on the limit of the restricted estimator of a small violation of the restrictions. In the linear regression case our formula coincides with that given by Theil. In order to keep our results widely applicable and to avoid a mass of unnecessary detail we make assumptions on the asymptotic behavior of the loglikelihood function itself, rather than on the data-generating process per se. Many alternative sets of assumptions on the data densities can lead to the behavior we require of the loglikelihood functions. These will not be pursued here. The interested reader is referred to, e.g., White [12] for the case of independent observations and Kohn [8] for the time-series case. 1. GENERAL FORMULAS The general approach we take is based on a linear approximation to the likelihood function at the maximum likelihood estimator. It is in this sense that our analysis is local. For some models the local and global specification error results coincide; a well known case is the effect of omitted regressors in the linear regression model. Essentially the only cases involve linearity, although often there is agreement regarding the signs of the inconsistency. We show below that the local and global results even fail to coincide in the case of misspecified AR processes. Generally however, the global results are unknown.2 Taylor expansions are typically used together with assumptions on the data generating process to obtain the asymptotic distribution of the maximum likelihood estimator (Cramer [3]). In this paper we will not concern ourselves with asymptotic distributions of Vn -normed MLE's since these have been worked

[This paper extends the empirical version of a job-search model to permit heterogeneity in the location of wage offer distributions. Population variance in wage offers is decomposed into variance due to heterogeneity and variance facing each individual. Heterogeneity is found to be an important source of offer variance in the population. The amount of "pure wage offer dispersion" facing individuals is found to contribute little to population variance.]