Title of dissertation: ASSESSING FIT OF LATENT CLASS MODELS TO COMPLEX SURVEY DATA: IMPLICATIONS FOR DRUG USE RESEARCH

Title of dissertation: ASSESSING FIT OF LATENT CLASS MODELS TO COMPLEX SURVEY DATA: IMPLICATIONS FOR DRUG USE RESEARCH Carrie Elizabeth Markovitz, Doctor of Philosophy, 2003 Dissertation directed by: Professor C. Mitchell Dayton Department of Measurement, Statistics and Evaluation Simple random sampling is an assumption when using fit statistics to fit latent class (LC) models to data. However, LC models are often fit to datasets collected through complex survey sampling methods that may result in inaccurate estimates of standard errors, parameter estimates and fit statistics. This study examined how various comparison tests functioned for latent class models when using complex survey data. The motivation for this research is the issue of reported drug use patterns and whether changes in drug use have occurred over time. This issue was investigated using reported drug use data from the National Household Survey on Drug Abuse (NHSDA) for 1979 and 1988. Monte Carlo simulations were used to determine how well the various model comparison statistics (chi-square, AIC, BIC, RIC and Wald statistic) functioned for a variety of complex sample designs. In addition, a simulation based on the NHSDA data was used to answer the research question: Do patterns of reported drug use show change over time? The model comparison statistics were most accurate when sample sizes were large and item-specific error rates were low. Intraclass correlation, an indicator of how similar individuals are within the same cluster, appeared to have little effect on the accuracy of the model comparison statistics. Statistics were not as accurate when sampling from unequally weighted groups. The chi-square statistics and AIC were recommended for use with complex survey data based on their high rates of accuracy. More caution was recommended when using BIC and RIC. Results indicated that reported drug use patterns changed between 1979 and 1988. Most patterns of reported drug use increased slightly, with the exception of respondents characterized by alcohol and tobacco use alone that decreased substantially. ASSESSING FIT OF LATENT CLASS MODELS TO COMPLEX SURVEY DATA: IMPLICATIONS FOR DRUG USE RESEARCH

[1]  Edward L. Korn,et al.  Analysis of Health Surveys , 1999 .

[2]  Graham Kalton,et al.  Introduction to Survey Sampling , 1983 .

[3]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[4]  David Knoke,et al.  Analysis of Qualitative Data, Vol. 2: New Developments. , 1981 .

[5]  R. Darrell Bock,et al.  Fitting a response model forn dichotomously scored items , 1970 .

[6]  D. Kandel,et al.  Sequence and stages in patterns of adolescent drug use. , 1975, Archives of general psychiatry.

[7]  J. Graham,et al.  Crossvalidation of Latent Class Models of Early Substance Use Onset. , 1994, Multivariate behavioral research.

[8]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[9]  D. Pfeffermann.  The Role of Sampling Weights when Modeling Survey Data , 1993 .

[10]  R. Hambleton,et al.  Item Response Theory: Principles and Applications , 1984 .

[11]  B. Graubard,et al.  Latent Class Analysis of Complex Sample Survey Data , 2002 .

[12]  Leo A. Goodman,et al.  On scaling models applied to data from several groups , 1986 .

[13]  S. Lai,et al.  The Association Between Cigarette Smoking and Drug Abuse in the United States , 2000, Journal of addictive diseases.

[14]  R. E. Wheeler.  Statistical distributions , 1983, APLQ.

[15]  Robert D. Tortora,et al.  Sampling: Design and Analysis , 2000 .

[16]  S. Lo,et al.  Stages of drug use: a community survey of Perth teenagers. , 1992, British journal of addiction.

[17]  Graham K. Rand,et al.  Quantitative Applications in the Social Sciences , 1983 .

[18]  L. Guttman.  On Festinger's evaluation of scale analysis. , 1947, Psychological bulletin.

[19]  R. Vaughan,et al.  The co-occurrence of smoking and binge drinking in adolescence. , 2000, Addictive behaviors.

[20]  S. Haberman.  Analysis of qualitative data , 1978 .

[21]  M. Aldenderfer,et al.  Cluster Analysis. Sage University Paper Series On Quantitative Applications in the Social Sciences 07-044 , 1984 .

[22]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[23]  George B. Macready,et al.  A probabilistic model for validation of behavioral hierarchies , 1976 .

[24]  L. A. Goodman,et al.  Latent Structure Analysis of a Set of Multidimensional Contingency Tables , 1984 .

[25]  Clifford C. Clogg,et al.  A Comparison of Alternative Models for Analyzing the Scalability of Response Patterns , 1981 .

[26]  Charles H. Proctor,et al.  A probabilistic formulation and statistical analysis of guttman scaling , 1970 .

[27]  Kosuke Imai,et al.  Survey Sampling , 1998, Nov/Dec 2017.

[28]  S. Sclove.  Application of model-selection criteria to some problems in multivariate analysis , 1987 .

[29]  Risto Lehtonen,et al.  Practical Methods for Design and Analysis of Complex Surveys , 1995 .

[30]  D. Kandel,et al.  Patterns of drug use from adolescence to young adulthood: II. Sequences of progression. , 1984, American journal of public health.

[31]  C. Dayton.  Latent Class Scaling Analysis , 1999 .

[32]  Timothy R. C. Read,et al.  Goodness-Of-Fit Statistics for Discrete Multivariate Data , 1988 .

[33]  Bruce D. Johnson,et al.  Variation in youthful risks of progression from alcohol and tobacco to marijuana and to hard drugs across generations. , 2001, American journal of public health.

[34]  Practical Methods for Design and Analysis of Complex Surveys , 2005 .

[35]  D. Kandel,et al.  Stages of progression in drug involvement from adolescence to adulthood: further evidence for the gateway theory. , 1992, Journal of studies on alcohol.

[36]  Leo A. Goodman,et al.  SIMULTANEOUS LATENT STRUCTURE ANALYSIS IN SEVERAL GROUPS , 1985 .

[37]  N. L. Johnson,et al.  Linear Statistical Inference and Its Applications , 1966 .

[38]  Ronald N. Forthofer,et al.  Analysis of Complex Sample Survey Data , 1986 .

[39]  H. Akaike.  Factor analysis and AIC , 1987 .

[40]  E. Ziegel,et al.  Bootstrapping: A Nonparametric Approach to Statistical Inference , 1993 .