Partial Likelihood Estimation of IRT Models with Censored Lifetime Data: An Application to Mental Disorders in the ESEMeD Surveys

Carlos G. Forero, Josue Almansa, Nuria D. Adroher, Jeroen K. Vermunt, Gemma Vilagut, Ron De Graaf, Josep-Maria Haro, Jordi Alonso Caballero*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)

Abstract

Developmental studies of mental disorders based on epidemiological data are often based on cross-sectional retrospective surveys. Under such designs, observations are right-censored, causing underestimation of lifetime prevalences and correlations, and inducing bias in latent trait models on the observations. In this paper we propose a Partial Likelihood (PL) method to estimate unbiased IRT models of lifetime predisposition to develop a certain outcome. A two-step estimation procedure corrects the IRT likelihood of outcome appearance with a function depending on (a) projected outcome frequencies at the end of the risk period, and (b) outcome censoring status at the time of the observation. Simulation results showed that the PL method yielded good recovery of true frequencies and intercepts. Slopes were best estimated when events were sufficiently correlated. When PL is applied to lifetime mental health disorders (assessed in the ESEMeD project surveys), estimated univariate prevalences were, on average, 1.4 times above raw estimates, and 2.06 higher in the case of bivariate prevalences.

Original languageEnglish
Pages (from-to)470-488
Number of pages19
JournalPsychometrika
Volume79
Issue number3
DOIs
Publication statusPublished - Jul-2014
Externally publishedYes

Keywords

  • data censorship
  • survival analysis
  • mental disorders
  • internalising psychiatric disorders
  • psychiatric epidemiology
  • psychometric epidemiology
  • COMORBIDITY SURVEY REPLICATION
  • AGE-OF-ONSET
  • REGRESSION-ANALYSIS
  • CASE-COHORT
  • PREVALENCE
  • EFFICIENCY
  • ANXIETY
  • COMMON
  • RISK
  • TIME

Cite this