MTH-416, REGRESSION ANALYSIS Lecture Notes - Lecture 4: Logistic Regression, Indian Institute Of Technology Kanpur, Mathematical Optimization
Document Summary
The log-link function is x i ln( x i g i i i i i g. Note that in identity link function, the predicted values of y can be negative but in log-link function, the predicted values of y are nonnegative. We use the method of maximum likelihood estimation to estimate the parameters of the poisson regression model. The likelihood function is based on poisson distribution with parameter and then. " s are estimated through the link function. The likelihood function of y is y y. 1 i p y i i exp( i i n i. 1 i y i i i y i exp y i n. L y n ln( i y i n n i ln( y i. " s through the link function i can be related to. 1 i y i x i g exp( 1 g x i x x i x .