Assessing Differences between Nested and Cross-Classified Hierarchical Models

Sociological Methodology - Tập 49 Số 1 - Trang 220-257 - 2019
David Melamed1, Mike Vuolo1
1The Ohio State University, Columbus, OH, USA.

Tóm tắt

In multilevel data, cross-classified data structures are common. For example, this occurs when individuals move to different regions in longitudinal data or students go to different secondary schools than their primary school peers. In both cases, the data structure is no longer fully nested. Estimating cross-classified multilevel models is computationally intensive, so researchers have used several shortcuts to decrease run time. We consider how these shortcuts affect parameter estimates. In particular, we compare parameter estimates from fully nested and cross-classified models using a series of Monte Carlo simulations. When the outcome is continuous, we identify systematic differences in estimated standard errors and some differences in the estimated variance components. When the outcome is binary, we also find differences in the estimated coefficients. Accordingly, we caution researchers to avoid fully nested model specifications when cross-classification exists but suggest some limited conditions under which parameter estimates are unlikely to be different.

Từ khóa


Tài liệu tham khảo

10.18637/jss.v067.i01

Clark Philippa, 2009, Social Science & Medicine, 69

Cohen Jacob, 1988, Statistical Power Analysis for the Behavioral Sciences, 2

10.1177/0003122410396197

Goldstein Harvey, 1999, Multilevel Statistical Models

Goldstein Harvey, 1995, Multilevel Statistical Models, 4

10.1111/j.1467-985X.2007.00491.x

10.2307/2983328

10.1007/s13524-014-0350-5

10.3102/1076998607307355

10.4324/9780203852279

10.1080/03610910802627055

10.1016/j.socscimed.2012.09.032

10.1016/j.socscimed.2011.12.036

Littell Ramon C., 2006, SAS for Mixed Models

10.1080/00273170902794214

10.3102/1076998610394366

10.1207/s15327906mbr4104_3

10.1177/0038040710383519

Raudenbush Stephen W., 2001, Hierarchical Linear Models, 2

Raudenbush Stephen, 2011, HLM 7: Hierarchical Linear and Nonlinear Modeling

10.2307/2983404

10.1111/1467-985X.00206

10.1016/j.socscimed.2015.10.040

StataCorp. 2017. “Stata/MP Performance Report, Revision 3.1.0.”College Station, TX: StataCorp LP. http://www.stata.com/statamp/statamp.pdf.

Vogel Matt, 2017, Social Forces, 95

10.1016/j.ssresearch.2011.06.009

Thông tin
Thông tin xuất bản

Sociological Methodology

Tập 49 Số 1

220-257

Thông tin tác giả