In: Statistics and Probability
A measure of goodness of fit for the estimated regression equation is the
Question 5 options:
sample size |
|
mean square due to regression |
|
mean square due to error |
|
multiple coefficient of determination |
The answer is multiple coefficient of determination.
The coefficient of determination is a measure of explanatory power of regression and is defined as the ratio of variation explained by regression to the total variation or in other words it is the proportion of variation explained by regression. It is calculated as
IF the value of is close to 1, variation is explained by regression and the regression fitted is "good".
If the value of is close to zero, no variation is explained by regression and the fitted model can not be used for prediction.
It can also be noted that is the square of correlation between observed and predicted dependent variable.
and it lies between 0 and 1.