Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in Nigeria
Background: Estimates of Under-Five mortality (U5M) have taken advantage of indirect methods but U5M risk factors have been identified using fixed statistical models with little considerations for the potentials of mixture models. Mixture models such as Poisson-Mixture models exhibit flexibility ten...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Medical and Dental Consultants Association of Nigeria, OOUTH Sagamu
2018-12-01
|
| Series: | Annals of Health Research |
| Subjects: | |
| Online Access: | http://www.annalsofhealthresearch.com/index.php/ahr/article/view/120 |
| _version_ | 1818807923541803008 |
|---|---|
| author | Kolawole Oritogun Elijah Bamgboye |
| author_facet | Kolawole Oritogun Elijah Bamgboye |
| author_sort | Kolawole Oritogun |
| collection | DOAJ |
| description | Background: Estimates of Under-Five mortality (U5M) have taken advantage of indirect methods but U5M risk factors have been identified using fixed statistical models with little considerations for the potentials of mixture models. Mixture models such as Poisson-Mixture models exhibit flexibility tendency, which is an attribute of robustness lacking in fixed models.
Objective: To examine the robustness of Poisson-Mixture models in identifying reliable determinants of U5M.
Methods: The data on 18,855 women used in this study were obtained from the 2008 Nigeria Demographic and Health Survey (NDHS). Six different Poisson-Mixture models namely: Poisson (PO), Zero-Inflated Poisson (ZIP), Poisson Hurdle (PH), Negative Binomial (NBI), Zero-Inflated Negative Binomial (ZINBI) and Negative Binomial Hurdle (NBIH) were fitted separately to the data. The Akaike Information Criteria (AIC) and diagnostic check for normality were used to select robust models. All tests were conducted at p = 0.05.
Results: The models and AIC values for U5M were: 38763.47 (PO), 38654.55 (ZIP), 44270.77 (PH), 38526.26 (NBI), 38513.71 (ZINBI) and 44269.30 (NBIH). The PO, ZIP, PH and NBIH met normality test criteria, and the ZIP model was of best fit. The model identified breastfeeding, paternal education, toilet type, maternal education, place of delivery, birth-order and antenatal-visits as significant determinants of U5M at the national level.
Conclusion: The Zero-Inflated Poisson model provided the best robust estimates of Under-five Mortality in Nigeria, while maternal education and birth-order were identified as the most important determinants. The Poisson-mixture models are recommended for modelling Under-five Mortality in Nigeria. |
| first_indexed | 2024-12-18T19:33:23Z |
| format | Article |
| id | doaj.art-4ef8b419bbfc47fbafbe7bb1b663f13f |
| institution | Directory Open Access Journal |
| issn | 2476-8642 2536-6149 |
| language | English |
| last_indexed | 2024-12-18T19:33:23Z |
| publishDate | 2018-12-01 |
| publisher | Medical and Dental Consultants Association of Nigeria, OOUTH Sagamu |
| record_format | Article |
| series | Annals of Health Research |
| spelling | doaj.art-4ef8b419bbfc47fbafbe7bb1b663f13f2022-12-21T20:55:40ZengMedical and Dental Consultants Association of Nigeria, OOUTH SagamuAnnals of Health Research2476-86422536-61492018-12-014214115410.30442/ahr.0402-6-17Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in NigeriaKolawole Oritogun0Elijah Bamgboye1Department of Community Medicine and Primary Care, Obafemi Awolowo College of Health Sciences, Olabisi Onabanjo University, Sagamu, NigeriaDepartment of Epidemiology & Medical Statistics, University of Ibadan, Ibadan, NigeriaBackground: Estimates of Under-Five mortality (U5M) have taken advantage of indirect methods but U5M risk factors have been identified using fixed statistical models with little considerations for the potentials of mixture models. Mixture models such as Poisson-Mixture models exhibit flexibility tendency, which is an attribute of robustness lacking in fixed models. Objective: To examine the robustness of Poisson-Mixture models in identifying reliable determinants of U5M. Methods: The data on 18,855 women used in this study were obtained from the 2008 Nigeria Demographic and Health Survey (NDHS). Six different Poisson-Mixture models namely: Poisson (PO), Zero-Inflated Poisson (ZIP), Poisson Hurdle (PH), Negative Binomial (NBI), Zero-Inflated Negative Binomial (ZINBI) and Negative Binomial Hurdle (NBIH) were fitted separately to the data. The Akaike Information Criteria (AIC) and diagnostic check for normality were used to select robust models. All tests were conducted at p = 0.05. Results: The models and AIC values for U5M were: 38763.47 (PO), 38654.55 (ZIP), 44270.77 (PH), 38526.26 (NBI), 38513.71 (ZINBI) and 44269.30 (NBIH). The PO, ZIP, PH and NBIH met normality test criteria, and the ZIP model was of best fit. The model identified breastfeeding, paternal education, toilet type, maternal education, place of delivery, birth-order and antenatal-visits as significant determinants of U5M at the national level. Conclusion: The Zero-Inflated Poisson model provided the best robust estimates of Under-five Mortality in Nigeria, while maternal education and birth-order were identified as the most important determinants. The Poisson-mixture models are recommended for modelling Under-five Mortality in Nigeria.http://www.annalsofhealthresearch.com/index.php/ahr/article/view/120Akaike Information CriteriaChild mortalityUnder-five MortalityZero-Inflated Poisson modelPoisson-mixture modelsMaternal education |
| spellingShingle | Kolawole Oritogun Elijah Bamgboye Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in Nigeria Annals of Health Research Akaike Information Criteria Child mortality Under-five Mortality Zero-Inflated Poisson model Poisson-mixture models Maternal education |
| title | Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in Nigeria |
| title_full | Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in Nigeria |
| title_fullStr | Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in Nigeria |
| title_full_unstemmed | Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in Nigeria |
| title_short | Robustness of Poisson Mixture models in identifying risk factors for Under-Five mortality in Nigeria |
| title_sort | robustness of poisson mixture models in identifying risk factors for under five mortality in nigeria |
| topic | Akaike Information Criteria Child mortality Under-five Mortality Zero-Inflated Poisson model Poisson-mixture models Maternal education |
| url | http://www.annalsofhealthresearch.com/index.php/ahr/article/view/120 |
| work_keys_str_mv | AT kolawoleoritogun robustnessofpoissonmixturemodelsinidentifyingriskfactorsforunderfivemortalityinnigeria AT elijahbamgboye robustnessofpoissonmixturemodelsinidentifyingriskfactorsforunderfivemortalityinnigeria |