E Michael Foster1. 1. Department of Health Policy & Administration, Pennsylvania State University, Philadelphia, Pennsylvania 16802-6500, USA. emfoster@psu.edu
Abstract
BACKGROUND: Health services researchers are often interested in the effect of a treatment or a service in situations in which randomization is difficult or impossible. One useful alternative involves propensity score methods, a means for matching members of different groups based on a range of characteristics. Under certain assumptions, comparisons of the matched groups reveal the impact of the treatment of interest. OBJECTIVES: This article reviews propensity score methods and illustrates their use in an analysis of dose response, the relationship between the volume of services received, and treatment outcomes. In mental health policy, this question is central to key issues such as parity. RESEARCH DESIGN: Data for the illustrative analysis are taken from a well-known study of children's mental health services. This analysis estimates the impact of outpatient therapy based on comparisons of individuals receiving different treatment doses. Those comparisons are adjusted for preexisting observed differences among the groups using propensity score methods. SUBJECTS: The study includes 301 participants aged 5 to 18 years treated at the study sites. MEASURES: The analyses are based on family characteristics and the mental health status of children and adolescents reported in interviews with parents as well as administrative data on service use. RESULTS: Analyses using propensity score matching suggest that added services improve treatment outcomes, especially child functioning. However, at least for the services and outcomes considered, the marginal benefits to high levels of treatment are limited. CONCLUSIONS: These analyses illustrate the potential value of propensity score methods to health services researchers.
BACKGROUND: Health services researchers are often interested in the effect of a treatment or a service in situations in which randomization is difficult or impossible. One useful alternative involves propensity score methods, a means for matching members of different groups based on a range of characteristics. Under certain assumptions, comparisons of the matched groups reveal the impact of the treatment of interest. OBJECTIVES: This article reviews propensity score methods and illustrates their use in an analysis of dose response, the relationship between the volume of services received, and treatment outcomes. In mental health policy, this question is central to key issues such as parity. RESEARCH DESIGN: Data for the illustrative analysis are taken from a well-known study of children's mental health services. This analysis estimates the impact of outpatient therapy based on comparisons of individuals receiving different treatment doses. Those comparisons are adjusted for preexisting observed differences among the groups using propensity score methods. SUBJECTS: The study includes 301 participants aged 5 to 18 years treated at the study sites. MEASURES: The analyses are based on family characteristics and the mental health status of children and adolescents reported in interviews with parents as well as administrative data on service use. RESULTS: Analyses using propensity score matching suggest that added services improve treatment outcomes, especially child functioning. However, at least for the services and outcomes considered, the marginal benefits to high levels of treatment are limited. CONCLUSIONS: These analyses illustrate the potential value of propensity score methods to health services researchers.
Authors: Laura Ferrer-Wreder; Hans Saint-Eloi Cadely; Celene E Domitrovich; Meg L Small; Linda L Caldwell; Michael J Cleveland Journal: J Prim Prev Date: 2010-12
Authors: Zachary A Marcum; Julia Driessen; Carolyn T Thorpe; Walid F Gellad; Julie M Donohue Journal: J Am Geriatr Soc Date: 2014-01-21 Impact factor: 5.562