Factor screening approach to modeling the causality variables in female genital mutilation

Abstract

Female genital mutilation (FGM) has three major types (Clitoridectomy, Excision, and Infibulation) which arise from the degree to which the external genitalia of the female is affected. Its origin is shrouded in mystery but historical evidences point to Egypt as the source country, before its spread through countries in sub-Saharan Africa, Asia, the Middle East, as well as some migrants in Europe, the United States and Australia. This study examines the factors that cause the FGM practice in order to determine the causality variables in a logistic regression scenario. Based on the multistage stratified random survey conducted by the Public Health Division, Nigeria Institute of Medical Research, Yaba, Lagos State, the tau statistic, τ was used to screen 12 factors presumed to causes FGM in order to select few of the predictors before multiple regression equation is obtained. The need for this may be that the sample size may not be able to sustain having a regression with all the predictors or to avoid multicollinearity. A total of 3,152 respondents, comprising 1,863 adult males and 1,289 adult females were selected from the household survey based on the multistage sampling procedure. The tau-statistic, τ showed that residence, employment status, educational level, aware of FGM problem, support campaign against FGM, wealth of the family, and location are the most highly associated variable to FGM. It was further observed that a large population of the respondents who are not in supports of the campaign against FGM is 2,309 but of this number, 2,159 does not support FGM and several of them (2,090) are educated. Since there is a considerable relationship between Education and employment status ($\tau =0.43$), it could be said that the improvement in Education status could considerably improve enlightenment on the danger of FGM thereby discouraging the belief and the support for female circumcision in the African society.

Keywords:

• African Society
• causality variables
• female genital mutilation
• logistic regression
• Tau statistic

Acknowledgments

We thank the Public Health Division, Institute of Medical Research, Yaba, Lagos, Nigeria for providing us the data and other relevant oral information concerning FGM practice in Nigeria. We are also grateful to the anonymous referee whose helpful comments has greatly improved the quality and presentation of this article.