Mathematical Models and Statistical Methods
Longitudinal Patterns of Disability Program Participation and Mortality Across Childhood SSI Award Cohorts
This article follows six annual cohorts of childhood Supplemental Security Income (SSI) disability awardees between 1980 and 2000, for a time horizon up to 30 years after initial SSI award, in many cases well into adulthood. The authors compare trajectories of successive awardee cohorts as the SSI program evolves from 1980 to recent years. The results show that the proportion of awardees in SSI-only status declines over the life cycle, with over half transitioning to other statuses roughly after 10 to 15 years. Many awardees transition from the SSI program to concurrent or Disability Insurance–only benefit status, and increasing proportions of awardees are deceased or off the rolls and alive. These patterns are common for all awardee cohorts, but there are major changes in trajectories across cohorts. Compared with the early cohorts, the more recent cohorts display sharper declines in mortality and steeper increases in the proportion off the disability rolls for other reasons. These two trends have opposite effects on the duration of disability program participation over the life cycle, with important policy implications.
Recruitment in the Mental Health Treatment Study: A Behavioral Health/Employment Intervention for Social Security Disabled-Worker Beneficiaries
The recent development of evidence-based behavioral health and vocational rehabilitation interventions for persons with serious psychiatric impairments created the impetus for exploring the efficacy of those interventions if they were widely available to Social Security Disability Insurance beneficiaries. As a first step in this endeavor—a multisite randomized trial for providing interventions to beneficiaries with psychiatric impairments—the Mental Health Treatment Study was implemented. The authors report on the subject recruitment patterns for the study, including assessment of take-up rates, and on the statistical analysis of the relationships between beneficiaries' characteristics and the probability of enrollment. Results indicated that take-up rates among potential MHTS subjects with confirmed telephone contacts met or exceeded rates for previous Social Security Administration randomized trials, and beneficiaries with administrative records of recent vocational or labor-market activity were most likely to enroll. The authors discuss implications of their analyses on recruitment in similar interventions in the future.
The Effects of Alternative Demographic and Economic Assumptions on MINT Simulations: A Sensitivity Analysis
The Social Security Administration's (SSA's) Modeling Income in the Near Term (MINT) estimates income/wealth of future retirees. Estimates are based on demographic information from the Survey of Income and Program Participation: individual earnings histories and projections of interest rates, wage growth, mortality rates, and disability rates. Historically, MINT simulations were based exclusively on SSA's Office of the Chief Actuary's (OCACT's) intermediate-cost projections of key demographic/economic variables. The authors present the results of a sensitivity analysis in which they ran MINT using OCACT's low-cost/high-cost projections of mortality and disability trends. Those simulations estimated characteristics of the population aged 65 or older in 2040 under alternative projections of mortality/disability trends. The authors then describe simulations in which future real rates of return on stocks held in retirement accounts differ from the historical mean real rate of return used in baseline simulations. Sensitivity analyses can help MINT users choose model parameters with the greatest impact on simulation results.
Outcome Variation in the Social Security Disability Insurance Program: The Role of Primary Diagnoses
This article investigates the role that primary impairments play in explaining heterogeneity in disability decisions. Using claimant-level data within a hierarchical framework, the author explores variation in outcomes along three dimensions: state of origin, adjudicative stage, and primary diagnosis. The findings indicate that the impairments account for a substantial portion of claimant-level variation in initial allowances. Furthermore, the author finds that the predictions of an initial and a final allowance are highly correlated when applicants are grouped by impairment. In other words, diagnoses that are more likely to result in an initial allowance also tend to be more likely to receive a final allowance.
Workplace injuries and illnesses are an important cause of disability. States have designed their workers' compensation programs to provide cash and medical-care benefits for those injuries and illnesses, but people who become disabled at work may also be eligible for Social Security Disability Insurance (DI) and related Medicare benefits. This article uses matched state workers' compensation and Social Security data to estimate whether workplace injuries and illnesses increase the probability of receiving DI benefits and whether people who become DI beneficiaries receive benefits at younger ages.
The Sensitivity of Proposed Social Security Benefit Formula Changes to Lifetime Earnings Definitions
Several Social Security proposals have included benefit formula changes that apply to earners above a specified percentage of the combined male and female (unisex) lifetime earnings distribution. This study finds that if Social Security's median unisex average indexed monthly earnings (AIME) amount is used to define an earnings threshold below which benefits will be held unreduced, the percentage of fully insured men subject to benefit reductions (70 percent) will exceed the unisex estimate of the population subject to benefit reductions (50 percent) by 20 percentage points. If policymakers wish to adjust future benefits and focus benefit reductions on middle or high primary or full-time wage earners in a household, the male, rather than unisex, AIME would come closer to achieving such a goal.
Using Matched Survey and Administrative Data to Estimate Eligibility for the Medicare Part D Low-Income Subsidy Program
This article uses matched survey and administrative data to estimate, as of 2006, the size of the population eligible for the Low-Income Subsidy (LIS), which was designed to provide "extra help" with premiums, deductibles, and copayments for Medicare Part D beneficiaries with low income and limited assets. The authors employ individual-level data from the Survey of Income and Program Participation and the Health and Retirement Study to cover the potentially LIS-eligible noninstitutionalized and institutionalized populations of all ages. The survey data are matched to Social Security administrative data to improve on potentially error-ridden survey measures of income components and program participation.
This paper evaluates the out-of-sample performance of two stochastic models used to forecast age-specific mortality rates: (1) the model proposed by Lee and Carter (1992); and (2) a set of univariate autoregressions linked together by a common residual covariance matrix (Denton, Feavor, and Spencer 2005).
The Board of Trustees of the Federal Old-Age and Survivors Insurance and Disability Insurance (OASDI) Trust Funds reports on the current and projected future financial status of the trust funds annually. The Trustees project trust fund finances 75 years into the future. Mortality is one key demographic assumption that feeds into these long-range projections. This article reviews a range of predictions about long-term mortality improvement and assesses where the Trustees' 75-year mortality projection falls within this range. In general, the predictions of future mortality declines in the 2004 Social Security Trustees Report tend to be in the mainstream of professional actuarial and international official government opinion and to be lower than the majority of the small group of demographers who produce comparable estimates.
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.
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.
Testing the Predictive Power of a Proportional Hazards Semi-Markov Model of Postentitlement Histories of Disabled Male Beneficiaries
In the Disability Amendments of 1980 (P.L. 96-265), Congress mandated that certain experiments be carried out which are designed to encourage disabled beneficiaries to return to work and save trust fund monies. A research plan has been developed which would offer alternative program provisions, experimentally, to different samples of beneficiaries. An observation period of three to four years will be possible before a report to Congress must be written. However, a period of this length is not sufficient to observe, fully, the postentitlement experience of disabled beneficiaries. In order to estimate the long run effects of the experiments, a method is needed which can project postentitlement behavior beyond the observation period.
This paper tests the ability of proportional hazards semi-Markov model to make accurate predictions in this type of setting. The data are divided into two segments: the first 14 calendar quarters and the last 16 quarters. Various types of rate functions including proportional hazards rate functions are estimated on the first segment, then projected over the entire 30 quarters and compared to the actual data. The proportional hazards rate functions are then used in a simulation to estimate monthly benefit cost to the social security disability trust fund over the last 16 quarters, using an age-dependent, absorbing, semi-Markov model. The model does a very good job of capturing the dynamics of the process and should prove quite useful as one of the major components in an analysis of the Work Incentive Experiments.
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.
For the past few years, the Division of Disability Studies has been using simple random and stratified random sampling procedures for many of its studies. The beneficiary sample for the 1978 Survey of Disability and Work was a stratified random sample drawn from the Master Benefit Record. The samples used in the Study of Consistency and Validity of Initial Disability Decisions and the Trial Work Period Folder Study also used simple random sampling procedures. Simple random subsampling has been used to enable multivariate analysis to be performed on files that would otherwise have been too large for existing software.
Because of the Division of Disability Studies' wide use of simple and stratified random sampling designs, software was developed to efficiently accomplish these sampling schemes. This paper describes the algorithm and presents the computer programs that are currently being used in the division.
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.