Research and Analysis by Barry V. Bye
Markov models have been widely used for the analysis and prediction of shifts in population distribution over time. The point of departure for most of these analyses has been the finite state, time stationary Markov chain. The usual Markov chain model has, however, been shown to be inadequate for most social science applications.
This paper presents a particular kind of discrete time nonstationary Markov chain. Such chains will be built using a mathematical quantity called a causative matrix.
Covariance Estimates for Regression Parameters from Complex Sample Designs: Application of the Weighted Maximum Likelihood Estimator to Linear and Logistic Regression Analysis in Which Observations Might Not be Independent
Statistical methods of variance estimation are presented in this paper for the analysis of survey data involving complex sample designs. With certain complex sample design, estimation of the covariance matrices in linear and logistic regression is not straightforward. The design may be complex because of disproportionate sampling of strata, necessitating the use of weights, or because the observations are not independent, or possibly both. Examples are given from projects at the Social Security Administration, and computer programs written in SAS (Statistical Analysis System) are provided.
This article describes the statistical development of the geographic coding system used to identify worker location for the Continuous Work History Sample. The new system—which is planned for implementation for data year 1993—will provide more accurate geographic distributions of workers within a residence concept than the old system could provide within an employer location concept. The article also presents the results of a pilot study that tested the operational aspects of the new system. The results provide some preliminary estimates of the effect of the revised codes on the geographic distribution of workers.
Estimation of Disability Status as a Single Latent Variable in a Model with Multiple Indicators and Multiple Causes
In this paper, we are concerned with the underlying structure of self-definitions of disability. Our purpose is to identify the contribution of exertional and nonexertional impairment and the contributions of such nonmedical factors as age, sex, and education to the individuals' assessment of their own situations. On a statistical level, we seek to accomplish a substantial reduction of a large number of data items into a form that can be used conveniently in subsequent behavioral analyses.
Labor-Force Participation and Earnings of SSI Disability Recipients: A Pooled Cross-Sectional Time Series Approach to the Behavior of Individuals
This article examines two important aspects of work behavior, labor-force participation, and earnings among persons who since 1976 have become entitled to SSI disability benefits and received payments for a full calendar year or longer during the intervening time period. A data set was developed containing the records of a random sample of all individuals who had ever received Supplemental Security Income (SSI) disability benefits and matched to earnings records maintained by the Social Security Administration (SSA). A multivariate analysis based on a pooled cross-sectional time series approach was employed using individual-level data to first estimate the probability of an SSI recipient performing work and then to estimate, among those who worked, the level of earnings. For this analysis, the SSI population was divided into three distinct groups based on their diagnosis: the nondevelopmentally disabled, the developmentally disabled (other than the mentally retarded), and the mentally retarded.
The analysis provides information about the impact that individual characteristics (such as age, education, diagnosis, and so forth) play in the decision to work and in determining the level of earnings. The analysis also addresses yearly variations in labor-force participation and earnings.
A Note on Maximum Likelihood Estimation of Discrete Choice Models from the 1978 Survey of Disability and Work
This paper demonstrates an alternative maximum likelihood procedure for estimating discrete choice models in retrospective samples, such as a model of SSA disability beneficiaries or application status in the 1978 Survey of Disability and Work.
A Note on Sampling Variance Estimates for Social Security Program Participants From the Survey of Income and Program Participation
Sampling Variance Estimates for SSA Program Recipients From the 1990 Survey of Income and Program Participation
Statistical Methods for the Estimation of Costs in the Medicare Waiting Period for Social Security Disabled Worker Beneficiaries
This paper presents the statistical methods used to estimate Medicare costs in the waiting period that were presented in text tables 2–3 of Bye and Riley (1989). The first part describes the development of Medicare utilization equations for each Social Security Disability Insurance (DI) program status group. The second part describes how these equations were used to predict expected costs per month and how the monthly estimates were aggregated to yield estimates of costs in the full 2-year waiting period and in the second year only. Finally, there is a brief discussion of the accuracy of the predictions.