Presentation is loading. Please wait.

Presentation is loading. Please wait.

Gl<-glm(SF~s,family=binomial(link='logit')) Response variable; for binomial link can be a two-column matrix with success/failure counts Explanatory variable.

Similar presentations


Presentation on theme: "Gl<-glm(SF~s,family=binomial(link='logit')) Response variable; for binomial link can be a two-column matrix with success/failure counts Explanatory variable."— Presentation transcript:

1 gl<-glm(SF~s,family=binomial(link='logit')) Response variable; for binomial link can be a two-column matrix with success/failure counts Explanatory variable Family = distribution of response link = function of the mean response

2 pl<-predict(gl,data.frame(s=x),type='response') Result of the glm() “s” is the name that we used in our call to glm() “response” = compute the response variable “link” = compute the link function values “x” is the grid on which the predicted values will be calculated

3 Deviance residuals show how much each of the observations contributes to the total deviance

4 ML estimation of the model coefficients; standard error (standard deviation of the estimator); corresponding z-value under H 0 that parameter is 0; and Prob(|z|>|parameter|), where z~N(0,1)

5 Null deviance: Deviance of the NULL model, which assumes that all parameters (except intercept) equal to 0.

6 Residual deviance: Deviance + a constant chosen in such a way that the saturated model’s deviance is 0.

7 Akaike Information Criterion AIC = -2 Log-Likelihood +2 # of parameters


Download ppt "Gl<-glm(SF~s,family=binomial(link='logit')) Response variable; for binomial link can be a two-column matrix with success/failure counts Explanatory variable."

Similar presentations


Ads by Google