1. NCCU Academic Hub
  2. 學術產出
  3. 理學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 A Comparison of Approaches for Estimating Covariate Effects in Nonparametric Multilevel Latent Class Models
作者 Park, Jungkyu
游琇婷
Yu, Hsiu-Ting
貢獻者 心理系
關鍵詞 covariate effects; latent class models; multilevel modeling
日期 2018-08
上傳時間 18-十二月-2018 15:57:09 (UTC+8)
摘要 The inclusion of covariates improves the prediction of class memberships in latent class analysis (LCA). Several methods for examining covariate effects have been developed over the past decade; however, researchers have limited to the comparisons of the performance among these methods in cases of the single-level LCA. The present study investigated the performance of three different methods for examining covariate effects in a multilevel setting. We conducted a simulation to compare the performance of the three methods when level-1 and level-2 covariates were simultaneously incorporated into the nonparametric multilevel latent class model to predict latent class membership at each level. The simulation results revealed that the bias-adjusted three-step maximum likelihood method performed equally well as the one-step method when the sample sizes were sufficiently large and the latent classes were distinct from each other. However, the unadjusted three-step method significantly underestimated the level-1 covariate effect in most conditions.
關聯 Structural Equation Modeling: A Multidisciplinary Journal, Vol.25, No.5, pp.778-790
資料類型 article
DOI http://dx.doi.org/10.1080/10705511.2018.1448711
dc.contributor 心理系
dc.creator (作者) Park, Jungkyuen_US
dc.creator (作者) 游琇婷zh_TW
dc.creator (作者) Yu, Hsiu-Tingen_US
dc.date (日期) 2018-08
dc.date.accessioned 18-十二月-2018 15:57:09 (UTC+8)-
dc.date.available 18-十二月-2018 15:57:09 (UTC+8)-
dc.date.issued (上傳時間) 18-十二月-2018 15:57:09 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/121420-
dc.description.abstract (摘要) The inclusion of covariates improves the prediction of class memberships in latent class analysis (LCA). Several methods for examining covariate effects have been developed over the past decade; however, researchers have limited to the comparisons of the performance among these methods in cases of the single-level LCA. The present study investigated the performance of three different methods for examining covariate effects in a multilevel setting. We conducted a simulation to compare the performance of the three methods when level-1 and level-2 covariates were simultaneously incorporated into the nonparametric multilevel latent class model to predict latent class membership at each level. The simulation results revealed that the bias-adjusted three-step maximum likelihood method performed equally well as the one-step method when the sample sizes were sufficiently large and the latent classes were distinct from each other. However, the unadjusted three-step method significantly underestimated the level-1 covariate effect in most conditions.en_US
dc.format.extent 573207 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Structural Equation Modeling: A Multidisciplinary Journal, Vol.25, No.5, pp.778-790
dc.subject (關鍵詞) covariate effects; latent class models; multilevel modelingen_US
dc.title (題名) A Comparison of Approaches for Estimating Covariate Effects in Nonparametric Multilevel Latent Class Modelsen_US
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.1080/10705511.2018.1448711
dc.doi.uri (DOI) http://dx.doi.org/10.1080/10705511.2018.1448711