Indications and Limitations of Structural Equation Modeling in Complex Surveys: Implications for an Application in the Medical Expenditure Panel Survey (MEPS)

This paper examines some indications and limitations of structural equation modeling (SEM) in complex survey analysis using an example from the Medical Expenditure Panel Survey (MEPS). The primary objectives of this paper are: 1) to provide an overview of basic statistical issues related to SEM, 2) to discuss findings in the literature related to SEM and complex survey design, and 3) to discuss a substantive application of SEM to MEPS. MEPS data are used to develop a preliminary model of the relationship between parental reports of affective behaviors and psychotropic medication utilization for children aged 5-17. Findings are presented from a comparison of SEM analysis, which uses latent variables to model affective behaviors, to a regression analysis which uses indices which are created from observed variables to represent affective behavior. The paper concludes with a discussion of the findings from the two analytical approaches and discussion of next steps in model development.

[1]  J. Woolston.  Combined pharmacotherapy: pitfalls of treatment. , 1999, Journal of the American Academy of Child and Adolescent Psychiatry.

[2]  R. P. McDonald,et al.  Structural Equations with Latent Variables , 1989 .

[3]  L. Snowden,et al.  Racial/ethnic disparities in the use of mental health services in poverty areas. , 2003, American journal of public health.

[4]  S. Zuvekas.  Trends in mental health services use and spending, 1987-1996. , 2001, Health affairs.

[5]  C. Ross,et al.  Social Causes of Psychological Distress , 1990 .

[6]  D. Mager,et al.  Geographic variation in the prevalence of stimulant medication use among children 5 to 14 years old: results from a commercially insured US sample. , 2003, Pediatrics.

[7]  D. Kleinbaum,et al.  Applied Regression Analysis and Other Multivariate Methods , 1978 .

[8]  Victor Clingan,et al.  Mirror on the wall , 1950 .

[9]  The influence of parental separation on smoking initiation in adolescents. , 2002, Journal of health and social behavior.

[10]  D. Safer,et al.  Concomitant psychotropic medication for youths. , 2003, The American journal of psychiatry.

[11]  Cohen Sb,et al.  Estimation procedures in the 1996 Medical Expenditure Panel Survey Household Component. , 1999 .

[12]  H. Feldman,et al.  Prevalence and assessment of attention-deficit/hyperactivity disorder in primary care settings. , 2001, Pediatrics.

[13]  D. Safer,et al.  Stimulant treatment in Maryland public schools. , 2000, Pediatrics.

[14]  Rex B. Kline,et al.  Principles and Practice of Structural Equation Modeling , 1998 .

[15]  F. Volkmar,et al.  Higher-functioning pervasive developmental disorders: rates and patterns of psychotropic drug use. , 1999, Journal of the American Academy of Child and Adolescent Psychiatry.

[16]  Steve Chan,et al.  Mirror, Mirror on the Wall... , 1984 .

[17]  A. Satorra,et al.  Complex Sample Data in Structural Equation Modeling , 1995 .

[18]  M. Jellinek.  Mirror, mirror on the wall: are we prescribing the right psychotropic medications to the right children using the right treatment plan? , 2003, Archives of pediatrics & adolescent medicine.

[19]  B Barnwell,et al.  SUDAAN User's Manual, Release 7.5, , 1997 .

[20]  D. Umbach,et al.  Prevalence of medication treatment for attention deficit-hyperactivity disorder among elementary school children in Johnston County, North Carolina. , 2002, American journal of public health.

[21]  Marsha P. Johnson.  Statistical Methods for Health Care Research , 1996 .

[22]  L. Magder,et al.  Psychotropic practice patterns for youth. , 2003 .

[23]  Richard G. Lomax,et al.  A Beginner's Guide to Structural Equation Modeling , 2022 .

[24]  M. Farmer,et al.  Distress and perceived health: mechanisms of health decline. , 1997, Journal of health and social behavior.