c-bun / glmnanobit_honors_thesis_tran Goto Github PK

The coefficient estimate in the output indicate the average change in the log odds of the response variable associated with a one unit increase in each predictor variable.

The standard error give us an idea of the variability associated with the coefficient estimate.

z-value = coef. est / std. error

p- value tells how well each predictor variable is able to predict the value of the response variable in the model. Depending on our preference of significant level, the predictor is whether statistically significant. The smaller the p-value, the more significant the predictor is.

AIC ( The Akaike information criterion) is a metric that is used to compare the fit of different regression models. The lower the value, the better the regression model is able to fit the data.

The number of Fisher Scoring iterations: indicates how many times the algorithm was run to estimate the parameters of the model. More iterations may be required for complex models or when the convergence criteria are set to be more stringent.