Question

Explain reasons for using statistical measures R2, RAAE and RMAE when evaluating response surfaces.
I need perfect answer for this question asap

Answer 1

• R^2, RAAE and RMSE are the Regression Metrics they are used to identify how much your Regression model is good. It measures the accuracy of your regression model.
• RAAE and RMSE compare the your predicted results with your actual values and measure the what difference between actual and predicted values if this difference is high that means your prediction is poor.   

RMSE (Root Mean Square Error): RMSE is calculate the error rate of the model.

RMSE =   

Where, Yact is the Actual value of target variable

Ypred is the predicted value of target variable

n is the no of observation

If RMSE value is closer to zero that means your model is good. RMSE value closer to zero means your model predict the accurate values of target variable.

RAAE (Relative Absolute Error):

RAAE is measures the magnitude of difference between exact value and approximation.

If RAAE value is closer to zero that means your model is good. RAAE value closer to zero means your model predict the accurate values of target variable.

R^2( Coefficient of Determination):

R^2 = 1 - (SSE / SST)

where,

SSE is sum of square due to error

SSE =  

SST is total sum of square

SST =

It measure the proportion of variance of dependent variable explained by the regression model.

The value of R^2 is between 0 and 1

it closer to 1 means your dependent variable explain the variability of model

R^2 close to 1 then model is good

For building good regression model to predict best future results we use this parameters.