Building of Logistic Regression Model for the Incidence Sudanese Females by Breast Cancer

Abstract

This research aimed at building of logistic regression model for the incidence Sudanese females by breast cancer with reference to Khartoum state, Sudan, using logistic regression method, so as to study breast cancer situation in Sudan through a sample of 165 patients.

A case- control study on breast cancer has been carried out to determine the risk factors of breast cancer is Khartoum, Sudan. The data for breast cancer patients were collected from the Statistical Information and Research Center in Radiation and Isotopes Center in Khartoum (RICK). The interview schedule designed for the research included questions regarding risk factors of breast cancer. The sample comprised of 165 breast cancer patients and 165 control in all. Areas of control were selected randomly

The data were analyzed by using descriptive statistics, chi-square test for dependency between independent variables (risk factors of breast cancer) and breast cancer incidence. Univariate analysis was used to identify variables to be included in multivariate analysis using (p >0.25). All the variables of statistical or biological importance were included in the models for multiple logistic regression analysis. logistic regression was applied to the revised data set by using both logistic regression and complementary log- log function approach.

The software package used for the analysis of data were Statistical Package for Social Science (SPSS), Stata10 and LogXact to generate the coefficients of the models and the other statistical test related to them.

The result of the research reveals from all the models, residence and anxiety scale statistically is not significance which it means these variables can not play an important role to develop breast cancer among Sudanese females. For the others variables and from all the logistic regression models applied in this research breast feeding, occupation, education level, parity, menopause status,