Question

Discuss the statistics that must be evaluated when reviewing the regression analysis output. Provide examples of what the values represent and an explanation of why they are important. In replies to peers, discuss whether you agree or disagree with the assessment provided by peers and explain why.

Answer 1

The statistics that must be evaluated when reviewing regression analysis output are statistics like F-test, R-square, adjusted R-square and beta coefficients.

The regression analysis output provides with an F-value and significance level of that F-value is computed. The regression model will explain significant amount of variance in the outcome variable if the F-value is statistically significant. For example if p<0.5 then F-value is statistically significant.

R-square is the percent of variance in the outcome variable that is explained by the set of predictor variables. For example if R-square is 0.89 then 89% of the variance in the outcome variable is explained by the set of predictor variables.

The adjusted R-square is that value of R-square that is adjusted based on the number of predictors in the model.

The last statistics that must be evaluated is the beta coefficient. This value can be negative or positive and it shows the degree of change in the outcome variable for every 1-unit of change in the predictor variable. The t-tests determine if the beta coefficient is significantly different from zero. When the beta coefficient is not statistically significant then the variable does not significantly predict the outcome.