| Peer-Reviewed

A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya

Received: 26 May 2015     Accepted: 7 June 2015     Published: 11 October 2018
Views:       Downloads:
Abstract

This study models the relative risk of diabetes, taking obesity and malnutrition as the major risk factors to define exposure, using three different prevalence rates i.e. 3%, 7% and 11% (estimates and projections from various studies). Secondary data consisting of a sample population of 300 children from the Kenya Diabetes Management and Information Centre (DMI), a national central diabetes registry, databases is used. In this research project, the modified Poisson regression approach is used to directly estimate the relative risk of pediatric diabetes in age strata of patients aged between the ages of 0-14years inclusive and for the purpose of model comparison RR estimation is done using Poisson regression which will prove to be less desirable for assessment of risk in this study proving the modified Poisson model gives the best estimates. From the data used in this study it is evident that: exposure (being overweight or underweight) is not a risk factor for diabetes onset in children aged 0-14 years.

Published in American Journal of Theoretical and Applied Statistics (Volume 7, Issue 5)
DOI 10.11648/j.ajtas.20180705.15
Page(s) 193-199
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2018. Published by Science Publishing Group

Keywords

Type 1 Diabetes (T1D), Relative Risk (RR), Generalized Linear Models (GLMs), Generalized Additive Models (GAMs), Poisson Model and Modified Poisson Model

References
[1] World Health Organisation(2010), www.who.int/diabetes/publications/Definition%20and%20diagnosis%20of%20diabetes_new.pdf
[2] World Diabetes Foundation (2012), Celebrating 10 years of making a difference.
[3] Swai A. B, Lutale J. L, McLarty D. G, (1993), Prospective study of Incidence of Juvenile diabetes mellitus over 10 years in Dar es Salaam Tanzania. BioMedical Science journal, 306(6892): 1570-1572.
[4] Barros J. D and Hirakata V, (2003), an empirical comparison of models that directly estimate the prevalence ratio. Bio Med Central Medical Research Methodology, 3: 21.
[5] Parodi S, Bottarelli E. (2006) Poisson Regression model in Epidemiology, Ann. Fac. Medic. Vet. Al. Parma, XXVI: 25-44.
[6] Gyula S, Paterson C, Dahlquist G, (2010), Diabetes in the Young: A Global Perspective International Diabetes Federation, Diabetes Atlas 4th Edition.
[7] Yonas B, Waernbaum I, Lind T, Mollsten A and Dahlquist G, (2011), Thirty years of Prospective Nationwide Incidence of childhood type 1 diabetes. Diabetes Journal, 60: 577-581.
[8] World Health Organisation (2010), Guidelines, www.who.int/mediacentre/factsheets/fs312/en/, 2013.
[9] Zou, G. (2004), A Modified Poisson Regression Approach to Prospective Studies with Binary Data. American Journal of Epidemiology, 159:702-706.
[10] Kleinbaum, D. G, Kupper, L. L, Muller, K. E and Nizam A, (1998). Applied Regression Analysis and other Multivariate Methods. Third Edition, Brooks/Cole Publishing Company, Duxbury. Press, Pacific Grove (CA).
[11] McNutt, L. A, Wu C, Xue X, (2003), Estimating the Relative Rise in Cohort Studies and Clinical Trials of Common Outcomes. American Journal of epidemiology, 157:940-943.
[12] Zochetti C, Consonni D, Berlazzi P. A, (1995). Estimation of Prevalence Rate and Ratios from Cross-sectional Data. International Journal of Epidemiology, 24:1064-1065.
[13] Royal, R. M, (1986). Model Robust Confidence Intervals using Maximum Likelihood Estimates. International Statistic review, 54: 221-226.
[14] Gale, E. A. M, Environmental factors [www.diapedia.org/type-1-diabetes-mellitus/environmental-factors], 2014 Aug 13; Diapedia 21040851139 rev. no. 45. Available from: http://dx.doi.org/10.14496/dia.21040851139.45.
Cite This Article
  • APA Style

    Christine Gacheri Mutuura, Anthony Kibira Wanjoya, Isaiah Njoroge Mwangi. (2018). A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya. American Journal of Theoretical and Applied Statistics, 7(5), 193-199. https://doi.org/10.11648/j.ajtas.20180705.15

    Copy | Download

    ACS Style

    Christine Gacheri Mutuura; Anthony Kibira Wanjoya; Isaiah Njoroge Mwangi. A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya. Am. J. Theor. Appl. Stat. 2018, 7(5), 193-199. doi: 10.11648/j.ajtas.20180705.15

    Copy | Download

    AMA Style

    Christine Gacheri Mutuura, Anthony Kibira Wanjoya, Isaiah Njoroge Mwangi. A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya. Am J Theor Appl Stat. 2018;7(5):193-199. doi: 10.11648/j.ajtas.20180705.15

    Copy | Download

  • @article{10.11648/j.ajtas.20180705.15,
      author = {Christine Gacheri Mutuura and Anthony Kibira Wanjoya and Isaiah Njoroge Mwangi},
      title = {A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya},
      journal = {American Journal of Theoretical and Applied Statistics},
      volume = {7},
      number = {5},
      pages = {193-199},
      doi = {10.11648/j.ajtas.20180705.15},
      url = {https://doi.org/10.11648/j.ajtas.20180705.15},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajtas.20180705.15},
      abstract = {This study models the relative risk of diabetes, taking obesity and malnutrition as the major risk factors to define exposure, using three different prevalence rates i.e. 3%, 7% and 11% (estimates and projections from various studies). Secondary data consisting of a sample population of 300 children from the Kenya Diabetes Management and Information Centre (DMI), a national central diabetes registry, databases is used. In this research project, the modified Poisson regression approach is used to directly estimate the relative risk of pediatric diabetes in age strata of patients aged between the ages of 0-14years inclusive and for the purpose of model comparison RR estimation is done using Poisson regression which will prove to be less desirable for assessment of risk in this study proving the modified Poisson model gives the best estimates. From the data used in this study it is evident that: exposure (being overweight or underweight) is not a risk factor for diabetes onset in children aged 0-14 years.},
     year = {2018}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya
    AU  - Christine Gacheri Mutuura
    AU  - Anthony Kibira Wanjoya
    AU  - Isaiah Njoroge Mwangi
    Y1  - 2018/10/11
    PY  - 2018
    N1  - https://doi.org/10.11648/j.ajtas.20180705.15
    DO  - 10.11648/j.ajtas.20180705.15
    T2  - American Journal of Theoretical and Applied Statistics
    JF  - American Journal of Theoretical and Applied Statistics
    JO  - American Journal of Theoretical and Applied Statistics
    SP  - 193
    EP  - 199
    PB  - Science Publishing Group
    SN  - 2326-9006
    UR  - https://doi.org/10.11648/j.ajtas.20180705.15
    AB  - This study models the relative risk of diabetes, taking obesity and malnutrition as the major risk factors to define exposure, using three different prevalence rates i.e. 3%, 7% and 11% (estimates and projections from various studies). Secondary data consisting of a sample population of 300 children from the Kenya Diabetes Management and Information Centre (DMI), a national central diabetes registry, databases is used. In this research project, the modified Poisson regression approach is used to directly estimate the relative risk of pediatric diabetes in age strata of patients aged between the ages of 0-14years inclusive and for the purpose of model comparison RR estimation is done using Poisson regression which will prove to be less desirable for assessment of risk in this study proving the modified Poisson model gives the best estimates. From the data used in this study it is evident that: exposure (being overweight or underweight) is not a risk factor for diabetes onset in children aged 0-14 years.
    VL  - 7
    IS  - 5
    ER  - 

    Copy | Download

Author Information
  • Department of Statistics and Actuarial Sciences, School of Mathematical Sciences, Jomo Kenyatta University of Agriculture and Technology, Juja, Kenya

  • Department of Statistics and Actuarial Sciences, School of Mathematical Sciences, Jomo Kenyatta University of Agriculture and Technology, Juja, Kenya

  • Centre for Respiratory Disease Research, Kenya Medical Research Institute, Nairobi, Kenya

  • Sections