Analysis Of Multiple Longitudinal Data Under The First-Order Autoregressive

Multiple longitudinal data refers to a group of data which are got from repeated measurements of several variables of an unit. Such repeated measurements are taken at different times. Since the response outcomes of an unit might be used to describe the same characteristic of the unit, there might be a cross-sectional correlation among the response outcomes. Measuring each response outcome repeatedly, one might be able to find a longitudinal correlation. Therefore, it is necessary to think about both the longitudinal and the cross-sectional correlation of the multiple longitudinal data which are of such qualities. This dissertation is compiled with a purpose to establish a statistic model for the multiple longitudinal data of such qualities. That might include the formation of a regression model for the observed response outcomes connected with the latent variables, the foundation of a first-order autoregressive model concerning latent variables and covariates ,An EM algorithm is developed to obtain maximum likelihood estimates of model parameters. Simulation studies are performed to assess efficiency gains with software.