Loading...
Please wait, while we are loading the content...
Joint Modeling for Longitudinal Data with Missing Values: A Bayesian Perspective on Human Intelligence
| Content Provider | Scilit |
|---|---|
| Author | Gokul, T. Srinivasan, M. R. |
| Copyright Year | 2021 |
| Description | Joint modeling in longitudinal data is an interesting area of research since it predicts the outcome with covariates that are measured repeatedly over the time. However, there is no proper methodology available in literature to incorporate the joint modeling approach for count-count response data. In addition, there are several situations where longitudinal data might not be possible to collect the complete data and the Missingness may occur due to the absence of the subjects at the follow-up. In this paper, joint modelling for longitudinal count data is adopted using Bayesian Generalized Linear Mixed Model framework to understand the association between the variables. Further, an imputation method is used to handle the missing entries in the data and the efficiency of the methodology has been studied using Markov Chain Monte-Carlo (MCMC) technique. An application to the proposed methodology has been discussed and identified the suitable nutritional supplements in Bayesian perspective without eliminating the missing entries in the dataset. |
| Ending Page | 536 |
| Page Count | 16 |
| Starting Page | 521 |
| ISSN | 20700237 |
| e-ISSN | 20700245 |
| DOI | 10.3329/jsr.v13i2.50479 |
| Journal | Journal of Scientific Research |
| Issue Number | 2 |
| Volume Number | 13 |
| Language | English |
| Publisher | Bangladesh Academy of Sciences |
| Publisher Date | 2021-05-01 |
| Access Restriction | Open |
| Subject Keyword | Statistics and Probability Longitudinal Data Joint Modelling Missing Entries |
| Content Type | Text |
| Resource Type | Article |