Predicting the needs of people living with a disability using the two-level logit-skewed exponential power model

The impact of high cost of living and movement of medical personnel in Nigeria to other countries. has a major impact on families/households. These has affected Person’s living with disabilities (PLWD) with special needs which require regular visitation to clinic and additional expenses. Therefore t...

Full description

Saved in:
Bibliographic Details
Main Authors: Abayomi Ajayi, Olaniyi Olayiwola, Fadeke Apantaku, Idowu Osinuga, Oluwaseun Wale-Orojo
Format: Article
Language:English
Published: Nigerian Society of Physical Sciences 2024-07-01
Series:African Scientific Reports
Subjects:
Online Access:https://asr.nsps.org.ng/index.php/asr/article/view/181
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The impact of high cost of living and movement of medical personnel in Nigeria to other countries. has a major impact on families/households. These has affected Person’s living with disabilities (PLWD) with special needs which require regular visitation to clinic and additional expenses. Therefore this study proposed predictive models with generalized distributed (combination of normal and non-normal) error term under Two Stage Sampling. Data from the Nigeria Living Standard Survey (NLSS) 2018 on frequency of doctor’s visit and cost by households with difficulty in remembering were used. Logit Skewed Exponential Power (LSEP-II) were developed for two-level Random Effect Model using Bayesian framework. The parameters for LSEP-II were estimated using the Markov Chain Monte-Carlo (MCMC) algorithm with JAGS software. Cartograms were used to determine the spatial distribution for the proportion of doctor’s visit and cost using the predicted values. R-hat showed that the posterior distribution converges. The study revealed that Logit Skewed Exponential Power for two-level Random Effect Model modelled and predicted doctor’s visit and additional cost for PLWDs in two-Stage Stratified Random Sampling Design.
ISSN:2955-1625
2955-1617