An Interactive Network security for Evaluating Linear Regression Models in Cancer Mortality Analysis and Self-Correlation of Errors by Using Durbin-Watson Tests in Babylon/Iraq

Abstract

Abstract The present study addresses Interactive Network security of the model of simple and frequent linear regression constructing method in describing the phenomenon of deaths of patients with cancer for the time variable in two aspects, one of which provides a theoretical background of the construction of the model of simple linear regression and the adoption of the principle of errors in the description of the standard deviation between the estimated value of the model and its true value, the other one is practical which shows the mechanism of building the model of simple linear regression and multiplexing and analysis of the results using two programs ( SPSS and Minitab ). And the study of the behaviour of errors for each model and drawn in the form of normal probability plot was also used the coefficient of selection R2 and Coefficient Selection Factor(adj) R2 in comparing the models and determining the best model in explaining the growth phenomenon of cancer deaths.