New Methods - Speakers and Presentations

Sunday, October 15, 8:30-9:30 a.m.

"Extensions of growth modeling of family processes to applications with binary and zero-inflated count data"
Presentation outline is available by clicking here, and tables here.

Dr. Alan C. Acock, Professor of Sociology and Human Development, Department of Human Development and Family Science, Oregon State University.

Alan C. Acock's substantive research has been on the effects of family structure on the well-being of family members and on intergenerational relations. His methodological research has focused on structural equation modeling, missing values, and growth curve modeling. He is currently investigating the effects of fathers returning to families after incarceration. He is a Fellow of the National Council on Family Relations and a winner of the Reuben Hill Award. Dr. Acock has held elected offices in the American Sociological Association and the National Council on Family Relations.

Abstract: "Extensions of growth modeling of family processes to applications with binary and zero-inflated count data"
(Presentation outline is available by clicking here, and tables here. You may visit Dr. Acock's website where he has also posted a Binary and Zero Inflated Growth Models document, and an introduction to growth curve analysis that would be useful for participants that don't already have that background.)

We will focus on growth curves involving binary and count outcomes. Different covariates may account for the onset of a behavior (binary question) than account for growth in the frequency of a problem behavior (count). A brief discussion of latent class analysis will be shown followed by the use of Mplus for estimating growth curves for both binary and count outcomes. We will then cover two-part or hurdle regression approaches to growth curves where both the unset and growth in the frequency of the outcome are estimated. This will be compared to a zero inflated growth curve model. These methods will be applied with a complex sample design. Although there is a growing technical literature on these techniques, they have not often been applied to family studies and the literature has not clarified how they are implemented and how the results are interpreted. Our focus will be on assumptions made to estimate the models and how to interpret the various parameters being estimated.

Selected Publications:

Acock, A. (2006). A gentle introduction to Stata. Stata Press.

Acock, A. C., van Dulmen, M., Allen, K. & Piercy, F. (2005). Contemporary and emerging methods in studying families. In Bengston, V., Acock, A. C., Allen, K., Dillworth-Anderson, P., & Klein, D. (eds.) Sourcebook of Marriage and Family Theory and Research. Sage Press. Pp. 59-90.

Richards, C., Acock, A. C., & Walker, A. (2003). Gender and investment in housework. Journal of Family Issues.

Acock, A. C., & Demo, D. H. (1999). Dimensions of family conflict and their influence on child and adolescent adjustment. Sociological Inquiry, 69, 641-58.

Bengtson, V., Acock, A. C., Allen, K., Dillworth-Anderson, P., & Klein, D. (2005). Sourcebook of Marriage and Family Theory and Research. Sage Press. We were selected as co-editors by the National Council on Family Relations. This book is published every 10-15 years and is a statement of the direction of the discipline.

Li, F., Duncan, T. E., Duncan, S. C., Fang-Jonsson, F., Acock, A., Hops, H. (2001). Interaction models in latent growth curves. In G. A. Marcoulides and R. E. Schumacker (Eds.), Advanced structural equation modeling: New developments and techniques. Mahwah, New Jersey: Lawrence Erlbaum.

Rosenkoetter, L. I., Rosenkoetter, S. E., Ozretich, R. A., & Acock, A. C. (2004). Mitigating the harmful effects of violent television. Applied Developmental Psychology 25:25-47.

Kosma, M., Wood, T.M., Rintala, P., & Acock, A.C. (2004). A comparison of the effects of health-related fitness and motor ability on adaptive behavior among adults with intellectual disabilities. Journal of Human Movement Studies, 47 (4), 303-326.