Hans van Ophem

A GENERAL METHOD TO ESTIMATE CORRELATED DISCRETE RANDOM VARIABLES

In this paper a method is presented to estimate correlated discrete random variables with known univariate distribution functions up to some parameters. We also present an empirical illustration on Dutch recreational data.

Modeling Selectivity in Count-Data Models

This article presents a method for modeling endogenous selectivity in count data. As in the case of the switching-regression model, two regimes are distinguished with potentially different data-generating processes. The regime choice is allowed to be correlated with the observed count in each of the regimes. An estimable model is obtained by transforming the underlying processes to the bivariate normal distribution. An empirical application on trip count is provided.

Multichoice logit: modeling incomplete preference rankings of classical concerts

In this article we develop an econometric model to analyze data on incomplete information on preferences. The available information consists of groups of alternatives that are preferred to other groups of alternatives. Only for the most preferred group is a full ranking observed. The resulting model is estimated on data concerning preferences on classical concerts.

Simulating the Risk of Investment in Human Capital

Abstract The risk of investment in schooling has largely been ignored. We mimic the investment decision facing a student and simulate risky earnings profiles in alternative options, with parameters taken from the very limited evidence. The distribution of rates of return appears positively skewed. Our best estimate of ex ante risk in university education is a coefficient of variation of about 0.3, comparable with that in a randomly selected financial portfolio with some 30 stocks. With risk attitudes varying by parental background, this may be relevant for differences in schooling participation rates. Allowing for stochastic components in earnings also markedly affects expected returns.

On-the-job search and the cyclical sensitivity of job mobility

Abstract We document empirical relations between job search, job offers and mobility for Dutch employees during the eighties. Our earlier research suggested little stability in structural models of job mobility. Our stripped-down model of the search decision shows modest variability in coefficients across a strong business cycle.

Testing the relevance of job search for job mobility

Statistical tests for differences in the mobility (and the search) behavior of male and female, searching and not searching individuals indicate that there indeed exist differences, particularly with respect to whether the individual is searching or not.

An empirical test of the segmented labour market theory for the Netherlands

In this paper an orthodox segmented labour market theory (SLM theory)is tested by means of the data provided by the research project, Quality of Labour 1977 (Zanders et al., 1977). The segmented labour market theory is restricted to the dual labour market approach, although a major extension is taken into account (a primary segment consisting of two tiers). The segments are created by making use of an objectivemethod. Nine quality characteristics of jobs are taken into account. A number of logit estimations are carried out to test the competing theories of human capital and the segmented labour market. The conclusion is that although discrimination in the labour market appears to exist, the SLM theory has to be rejected.

Determinants of football transfers

The analysis of football transfers is hampered by selectivity bias. In most empirical estimations, simple regression is used and selectivity is ignored. In this article we propose an estimation method that corrects for sample selectivity and allows the use of more observations in a simple manner. The ordered probit estimates point in a similar direction as the estimates from commonly applied estimation techniques but the significance is higher.

Wages and Measurement Errors

In this paper two wage observations which relate to the same point in time will be compared and the differences analyzed. The OSA-labor market survey contains information about wages received in April 1985 as reported in April 1985 and as reported in October 1986 by the same respondents. Large differences appear to exist. This paper intends to investigate whether these differences are random, by developing and estimating a maximum likelihood model. The estimation results indicate that the differences are not random. In particular, changes in the individuals labor market position seem to be important in the explanation of the observed differences. This conclusion casts strong doubt on the quality of wage variables as reported from the memories of individuals.

Starting wages respond to employer's risk

Firms hiring fresh graduates face uncertainty on the future productivity of workers. Intuitively, one expects starting wages to reflect this. Formal analysis supports the intuition. We use the dispersion of exam grades within a field of education as an indicator of the heterogeneity that employers face. We find solid evidence that starting wages are lower if the variance of exam grades is higher and that starting wages are lower if the skew is higher: employers shift quality risk to new hires, but pay for the opportunity to catch the really good workers.