Loglinear Modelling of Cancer Patients Cases in Nigeria: An Exploratory Study Approach
[1]
Odetunmibi, O. A., Department of Computer and Information Sciences, Covenant University, Otta, Nigeria.
[2]
Adejumo, A. O., Department of Statistics, University of Ilorin, Ilorin, Nigeria.
[3]
O. O. M. Sanni, Department of Statistics, University of Ilorin, Ilorin, Nigeria.
The spread of cancer disease today worldwide is becoming rampant. Curbing the menace that the disease pose to the humanity has been a thing of concern and has put all hands on deck. Those that are health related workers and non-health related workers. The main objectives of this research work are to: test whether treatment Outcome (O) of cancer patients is dependent of Age (A) and Gender (G) from the two hospitals we have; check for the best model among various models that we have from the two locations; compare the result of the two hospitals in order to be able to conclude whether treatment outcome is the same from the two locations; and use the result of the two hospitals to determine what happen to cancer patients in South West region of Nigeria. We observed that Model (AO:GO which uses Age: Outcome of treatment and Gender: Outcome of treatment) has the minimum Akaike Information Criteria (AIC) value from the two hospitals and therefore is accepted to be the best model. We also observed that Age and Gender are individually independent of treatment outcome of cancer patients from the two hospitals. We can therefore conclude that the treatment outcomes from the two hospitals are the same and this implies that South-West region of Nigeria has the same treatment outcome for cancer patients.
Cancer, Loglinear, Exploration, Likelihood Ratio, Treatment Outcome
[1]
Adejumo, A. O (2005), Modelling Generalized Linear (Loglinear) Model for Raters Agreement measures; Published by Peter Lang, Frankfurt am Main. (http://www.peterlang.de).
[2]
Adejumo, A. O. and Arabi, F. J. (2013). “A Study of HIV Sero-Prevalence Surveillance Survey Data Using Loglinear Model”. Global Journal of Pure and Applied Mathematics. Volume 9, Number 1: 73-81, Research India Publication.
[3]
Agresti, A. (2002). Categorical Data Analysis. John Wiley and Sons. 2nd Edition. New York.
[4]
Bishop, Y. M. M, Feinberg, S. E. Holland, P. W. (1975). Discrete Multivariate Analysis. Cambridge MA; MIT Press.
[5]
Christensen, R. (1997). Loglinear Models and Logistics Regression. Springer-Verlag Inc. NeW York. USA.
[6]
Clogg C. C. and Eliason S. R. (1987) Some common problems in log-linear analysis, Sociological. Methods & Research, 16, 8-44.
[7]
Everitt, B. S. (1992). The Analysis of Contingency Tables, London: Chapman & Hall.
[8]
Galindo-Garre, F., and Vermunt, J.K. (2005). Testing Log-Linear Models with Inequality Constraints: A Comparison of Asymptotic, Bootstrap, and Posterior Predictive P Values. Statistica Neerlandica, 59(1), 82-94
[9]
Vermunt, J.K. (1997). Log-linear Models for Event Histories. London: Sage.
[10]
World Health Organization (WHO 2005). WHO Publication on Cancer Diseases WHO report 2005. Geneva.
