TY - JOUR

T1 - Constraints in Random Effects Age-Period-Cohort Models

AU - Luo, Liying

AU - Hodges, James S.

PY - 2020/8/1

Y1 - 2020/8/1

N2 - Random effects (RE) models have been widely used to study the contextual effects of structures such as neighborhoods or schools. The RE approach has recently been applied to age-period-cohort (APC) models that are unidentified because the predictors are exactly linearly dependent. However, research has not fully explained how the RE specification identifies these otherwise unidentified APC models. We address this challenge by first making explicit that RE-APC models have greater—not less—rank deficiency than the traditional fixed-effects model, followed by two empirical examples. We then provide intuition and a mathematical proof to explain that for APC models with one RE, treating one effect as an RE is equivalent to constraining the estimates of that effect’s linear component and the random intercept to be zero. For APC models with two REs, the effective constraints implied by the model depend on the true (i.e., in the data-generating mechanism) nonlinear components of the effects that are modeled as REs, so that the estimated linear components of the REs are determined by the true nonlinear components of those effects. In conclusion, RE-APC models impose arbitrary although highly obscure constraints and thus do not differ qualitatively from other constrained APC estimators.

AB - Random effects (RE) models have been widely used to study the contextual effects of structures such as neighborhoods or schools. The RE approach has recently been applied to age-period-cohort (APC) models that are unidentified because the predictors are exactly linearly dependent. However, research has not fully explained how the RE specification identifies these otherwise unidentified APC models. We address this challenge by first making explicit that RE-APC models have greater—not less—rank deficiency than the traditional fixed-effects model, followed by two empirical examples. We then provide intuition and a mathematical proof to explain that for APC models with one RE, treating one effect as an RE is equivalent to constraining the estimates of that effect’s linear component and the random intercept to be zero. For APC models with two REs, the effective constraints implied by the model depend on the true (i.e., in the data-generating mechanism) nonlinear components of the effects that are modeled as REs, so that the estimated linear components of the REs are determined by the true nonlinear components of those effects. In conclusion, RE-APC models impose arbitrary although highly obscure constraints and thus do not differ qualitatively from other constrained APC estimators.

KW - age-period-cohort model

KW - identification problem

KW - linear and nonlinear effects

KW - linear dependency

KW - random effects models

UR - http://www.scopus.com/inward/record.url?scp=85079725719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85079725719&partnerID=8YFLogxK

U2 - 10.1177/0081175020903348

DO - 10.1177/0081175020903348

M3 - Article

AN - SCOPUS:85079725719

VL - 50

SP - 276

EP - 317

JO - Sociological Methodology

JF - Sociological Methodology

SN - 0081-1750

IS - 1

ER -