Steven Stern

Measuring the Effect of Disability on Labor Force Participation

This paper estimates the effect of disability on labor force participation by using symptoms or diseases as instruments in a simultaneous equations model of endogenous reported disability and labor force participation. The results show that each measure of disability explains a significant amount of variation in labor force participation, though the two are not perfect substitutes. There is only weak evidence of endogeneity of the disability variables. For cases where there is evidence of endogeneity, the bias it causes has the opposite effect of that hypothesized in the literatute (i.e., stress causes health to deteriorate with labor force participation). Furthermore, it has only insignificant effects on the coefficients for other variables.

Estimating family long-term care decisions in the presence of endogenous child characteristics.

This paper estimates the effects of various parent and child characteristics on the choice of care arrangement of the parent taking into account the potential endogeneity of some of the child characteristics. This potential endogeneity is controlled for by using an instrumental variables approach with panel data. The procedure conditions on the parent receiving no significant care in the first year of the panel causing first year variables to be valid instruments for the second year variables. The estimation procedure shows that, after controlling for endogeneity, potentially endogenous child variables have smaller effects. The estimates predict moderate effects of parent sex, age, race, and health and child sex and marital status, and large effects of parent marital status and child distance.

COHABITATION, MARRIAGE, AND DIVORCE IN A MODEL OF MATCH QUALITY

The objective of this research is to develop and estimate an economic model of nonmarital cohabitation, marriage, and divorce that is consistent with current data on the formation and dissolution of relationships. Jovanovics (1979) theoretical matching model is extended to help explain household formation and dissolution behavior. Implications of the model reveal what factors influence the decision to start a relationship, what form this relationship will take, and the relative stability of the various types of unions. The structural parameters of the model are estimated using longitudinal data from a sample of female high school seniors from the U.S. New numerical methods are developed to reduce computational costs associated with estimation. The empirical results are mostly consistent with previous literature but have interesting interpretations given the structural model.

The effect of increased concentrations of homocysteine on the concentration of (E)-4-hydroxy-2-nonenal in the plasma and cerebrospinal fluid of patients with Alzheimer's disease

There is evidence that increased blood concentrations of homocysteine may be a risk factor for Alzheimers disease. (E)-4-hydroxy-2-nonenal (HNE) is a neurotoxic product of lipid peroxidation that is increased in the ventricular fluid and brains of patients with Alzheimers disease. We measured the concentrations of homocysteine, HNE, vitamin B(12) and folate in the plasma of 27 patients with Alzheimers disease and 25 control subjects. There was a statistically significant increase in the plasma concentration of homocysteine (P < 0.001) and HNE (P < 0.001) in the Alzheimers disease patients compared to the control group. There was a significant decrease in the plasma concentration of vitamin B(12) (P < 0.001) and folate (P = 0.002) in the Alzheimers group compared to the controls. There was a significant positive correlation between the plasma concentrations of homocysteine and HNE in the patients with Alzheimers disease (r = 0.661, P < 0.001). A significant negative correlation was found between the plasma concentration of homocysteine and the plasma concentrations of vitamin B(12) (r = -0.605, P = 0.0006) and folate (r = 0.586, P = 0.001). We also measured the concentrations of homocysteine, HNE, vitamin B(12) and folate in the cerebrospinal fluid (CSF) of 8 patients with Alzheimers disease compared to 6 control subjects. The concentrations of homocysteine (P = 0.032) and HNE (P = 0.001) were significantly higher in the CSF of Alzheimers patients than in the control subjects. There were significant positive correlations between the CSF concentrations of homocysteine and HNE (r = 0.924, P = 0.001). There was also a significant positive correlation between the plasma concentration of homocysteine and the CSF concentrations of homocysteine (r = 0.850, P = 0.007) and HNE (r = 0.092, P = 0.002). These results demonstrate that there is a relationship between increased homocysteine concentrations and increased HNE concentrations in Alzheimers disease.

The transformational dimension in the realization of business value from information technology

Econometric studies have highlighted factors that appear to explain the differential effects of information technology (IT) on productivity at the firm level. Central to these explanations is the concept of organizational transformation; that value realization from IT depends on time-consuming investments in organizational change and results in new, often intangible, organizational assets. The aim of this study was to further investigate the concept of IT-enabled organizational transformation as a component of the value realized from IT at the firm level. Survey data was analyzed from respondents from 1050 businesses of varying sizes and across industries. Transformational benefits were found to exist as a distinct benefit category and to be closely related to other forms of IT-generated business benefits. They were also an important component of overall IT business value. Qualitative data illustrated these findings and pointed to possible complex causal relationships in the generation of IT value. The findings have implications for models of IT business value generation and for managerial practice.

Shared Caregiving Responsibilities of Adult Siblings with Elderly Parents

This paper uses a nonstructural, ordered discrete choice model to measure the effects of various parent and child characteristics upon the independent caregiving decisions of the adult children of elderly parents sampled in the 1982 and 1984 National Long Term Care Survey (NLTCS). While significant effects are noted, emphasis is placed on test statistics constructed to measure the independence of caregiving decisions. The test statistic results are conclusive: the caregiving decisions of adult children are dependent across time and family members. Structural models taking dependencies among family members into account note effects similar to those in the nonstructural model.

A Method for Smoothing Simulated Moments of Discrete Probabilities in Multinomial Probit Models

THERE HAS BEEN MUCH INTEREST over the years in estimating discrete choice models. However, with the exception of multinomial logit models, agents have been restricted to few choices so that multivariate integrals could be feasibly integrated numerically.2 Pakes and Pollard (1989) and McFadden (1989) have independently developed the method of simulated moments (MSM) to deal with estimating a wide class of models of which high order discrete choice models are a subset. One of the problems a researcher must handle when using MSM for a discrete choice model is how to smooth the discrete simulated random variables. This is necessary to keep small the number of draws required to simulate derivatives and to simulate variation in the data. Geweke (1989) and McFadden (1989) have suggested importance sampling methods (and other methods) to smooth the simulated variables for general error structures. In this paper, I present a factor analytic smoothing method that can be applied to probit problems. Although it is not as general as the methods Geweke and McFadden suggest, it is easy to use and has clear intuition. Furthermore, simulated probabilities will be unbiased, will be bounded between zero and unity, and will have smaller variances than unsmoothed probabilities always and smaller variances than importance sampling estimates for a large class of probabilities. The second section of this paper develops notation, defines the problem, and presents the smoothing method and an algorithm to employ it. The last section presents Monte Carlo comparisons of the smoothing method to the importance sampling method.

Semiparametric estimation of count regression models1

This paper develops a semiparametric estimation approach for mixed count regression models based on series expansion for the unknown density of the unobserved heterogeneity. We use the generalized Laguerre series expansion around a gamma baseline density to model unobserved heterogeneity in a Poisson mixture model. We establish the consistency of the estimator and present a computational strategy to implement the proposed estimation techniques in the standard count model as well as in truncated, censored, and zero-inflated count regression models. Monte Carlo evidence shows that the finite sample behavior of the estimator is quite good. The paper applies the method to a model of individual shopping behavior.

Feasible nonparametric estimation of multiargument monotone functions

Abstract This article presents a two-stage estimation procedure that uses an ad hoc but very easily implemented isotonization of a kernel estimator. This procedure yields an isotonic estimator with the convergence properties of the kernel estimator. Although the isotonization in the second stage does not satisfy the least squares condition, this hybrid estimator may be considered to be a multidimensional generalization of similar procedures for the one-dimensional case suggested by Friedman and Tibshirani and by Mukarjee. We derive some of the asymptotic properties of our estimator and demonstrate other statistical properties with Monte Carlo studies. We conclude by providing a real data example.

Estimating a Simultaneous Search Model

The primary goal of this article is to specify and estimate a structural simultaneous search model and then determine the empirical importance of simultaneous search. The results indicate that new labor force entrants search simultaneously. A secondary goal is to identify and estimate job offer arrival rates and wage offer rejection probabilities separately. The results indicate that a significant portion of unemployment spells are caused by slow arrival rates, but policies intended to speed arrival rates would increase the average length of unemployment spells.