Using an Event History Analysis to Evaluate Social Welfare Programs

Abstract

This article presents an overview of how an event history analysis can be used to evaluate social welfare programs' impacts on events and the timing of events. An overview of event history analysis is presented, including a discussion of events and spells, hazards, censoring, duration intervals, longitudinal databases, design issues, and life table and multivariate analysis techniques. The article concludes with an example of how an event history analysis was used to evaluate the Aid to Families with Dependent Children (AFDC) program.A goal of many social welfare programs is to change people's behavior. They attempt to change behaviors such as child and spouse abuse, drunken driving, substance abuse, suicides, moving into poverty, becoming unemployed, and so on. The list of intended changed behaviors is as long and varied as the list of practice areas and programs.Many of the intended impacts have one thing in common, however. They intend to reduce, to eliminate, to increase, or to encourage the occurrence of an event. The purpose of a child abuse prevention program is to eliminate or reduce the incidence of child abuse. Suicide prevention programs attempt to reduce the incidence of suicide. Employment programs attempt to have people obtain employment. All of these programs focus on events and whether the event occurs. An event marks the occurrence of a qualitative change. The timing of such qualitative changes and the duration of time through which they persist have long been of concern to social work practitioners and program evaluators. In fact, enabling and sustaining desirable behaviors over time is a fundamental social work objective. Until recently, social workers have lacked adequate methodological tools to examine qualitative changes or events over time. Within the last few years researchers have begun to use an &dquo;event history&dquo; analysis technique to

Agenda Setting, Innovation, and State Gay Rights Policy: An Event History Analysis

“…Event history analysis is the study of events, the duration of time between events, and the probability of events occurring at selected points in time (Barton and Pillai 1995). The goal of event history analysis is to explain a qualitative change an "event" that occurs in the behavior of an indi-vidual at a particular point in time (Berry and Berry 1990).…”

“…Central to event history analysis are the concepts of risk set and hazard. The risk set is the group of individuals "at risk" of cases experiencing an event at a particular time (Barton and Pillai 1995;Berry and Berry 1990). In cases where events can only occur once, the number of cases in the risk set decreases once the event is experienced.…”