A Transition Model for Multivariate Categorical Longitudinal Data
نویسندگان
چکیده
Riassunto: Per l’analisi di dati categorici longitudinali, viene proposta un’estensione multivariata del modello logistico dinamico. Il modello permette di utilizzare diversi tipi di logit e log-odds ratio per parametrizzare la distribuzione delle variabili risposta (ciascuna delle quali può essere ordinale o non ordinale) in funzione delle covariate, di un vettore di effetti non osservabili e delle variabili risposta ritardate. Gli effetti non osservabili possono variare nel tempo sulla base di una catena di Markov del primo ordine. Per la stima dei parametri del modello viene proposto un algoritmo di tipo EM e viene trattato il problema della selezione del numero di stati e della verifica di ipotesi. L’approccio è illustrato tramite l’analisi di dati longitudinali riguardanti fertilità e partecipazione al mercato del lavoro di un campione di donne.
منابع مشابه
Marginalized transition random effects models for multivariate longitudinal binary data
Generalized linear models with random effects and/or serial dependence are commonly used to analyze longitudinal data. However, interpretation and computation of marginal covariate effects can be difficult. Heagerty has proposed marginally specified logistic-normal models (1999) and marginalized transition models (2002) for longitudinal binary and categorical data in which the marginal mean is ...
متن کاملAnalysis of Dynamic Longitudinal Categorical Data in Incomplete Contingency Tables Using Capture-Recapture Sampling: A case Study of Semi-Concentrated Doctoral Exam
Abstract. In this paper, dynamic longitudinal categorical data and estimation of their parameters in incomplete contingency tables are evaluated. To apply the proposed method, a study has been conducted on the data of the semi-concentrated doctoral exam of the National Organization for Educational Testing (NOET). The results of studies such as the obtained confidence intervals and calculating t...
متن کاملTransition Models for Analyzing Longitudinal Data with Bivariate Mixed Ordinal and Nominal Responses
In many longitudinal studies, nominal and ordinal mixed bivariate responses are measured. In these studies, the aim is to investigate the effects of explanatory variables on these time-related responses. A regression analysis for these types of data must allow for the correlation among responses during the time. To analyze such ordinal-nominal responses, using a proposed weighting approach, an ...
متن کاملمقایسه مدلهای داده های طولی در انبساط آبی سه کامپوزیت متداول
Background: Longitudinal studies are widely used in medical and social sciences. According to repeated measurements in these studies, independence assumption is not observed and therefore suitable models should be selected. In this study, application of marginal and transition models for analyzing the longitudinal data related to hygroscopic expansion of composite is shown. Methods: ...
متن کاملExtension of Logic regression to Longitudinal data: Transition Logic Regression
Logic regression is a generalized regression and classification method that is able to make Boolean combinations as new predictive variables from the original binary variables. Logic regression was introduced for case control or cohort study with independent observations. Although in various studies, correlated observations occur due to different reasons, logic regression have not been studi...
متن کاملکاربرد مدلهای طولی انتقال و انتقال حاشیهایشده در بررسی عوامل مؤثر بر اختلال رشد کودکان کمتر از دو سال در شهر طارم
Background and Objective: Failure To Thrive (FTT) is one of the important health issues in children; not dealing with this disorder may lead to more serious consequences like increased death rate and appearance of other physical disabilities. The aim of this study was application of longitudinal transition model and longitudinal marginalized transition model in analysis of longitudinal data abo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008