The accompanying Credit Approval Decisions data provide information on credit history for a sample of banking customers. Use regression analysis to identify the best model for predicting the credit score as a function of the other numerical variables, using both the p-value and t-statistic criteria. How do the models compare?Which would you choose? Use a level of significance of 0.05.E Click the icon to view the Credit Approval Decisions data.What is the best model using the p-value criteria? Select the best answer below and fill in the answer boxes to complete your choice.(Type integers or decimals rounded to three decimal places as needed.)O A. Credit Score =Years + () Balance+O B. Credit Score =UtilizationOC. Credit Score =BalanceO D. Credit Score =YearsO E. Credit Score =Years +Balance +UtilizationO F. Credit Score =Balance +UtilizationO G. Credit Score =Years +Utilization Credit Score Years of Credit History Revolving Balance ($) Revolving Utilization (%)72821114200.23576873000.7168013201000.5262817129000.685301058000.777982191000.14736353000.226236229000.6459418166000.516632293000.3470318221000.1650315126000.84568778000.726234375000.887771262000.0880511106000.046438174000.5752613271000.7881422135000.057664113000.72558426000.98620885000.3564514161000.23691234000.116521376000.0569817204000.247048118000.136386.292000.855103210016801477000.074886.11000.84585286000.6370218129000.2870624101000.2158817311000.796236163000.566981898000.127771262000.0680511106000.05643174000.5853918271000.7780422135000.04763113000.72570623000.9760311121500.8470513118000.186397292000.83512421000.9959819291000.7773612131000.25

Given information: The response variable is Credit score and the predictor variables are Years of credit history, Revolving balance and revolving utilization. Multiple linear regression model: A multiple linear regression model is given as y = b0 + b1x1 + b2x2 + …+ bkxk where y is the predicted value of response variable, and x1, x2,…, xk are the k predictor variables. The quantities b1, b2,…, bk are the estimated slopes corresponding to x1, x2,…, xk respectively and b0 is the estimated intercept of the line, from the sample data. A multiple regression equation describes the combined effect of all the predictors in the model. Even when the effect of a particular predictor is being studied from a multiple regression equation, it assumes that the effects of all the other predictors are accounted for. Step 3 Multiple regression equation: EXCEL software can be used to obtain the multiple regression equation. Software Procedure: Step-by-step software procedure to perform a multiple linear regression model using EXCEL software is as follows: Open an EXCEL file. Enter the data of Credit score in columns A and name it as Credit score. Enter the data of the variables Years of credit history, Revolving balance and revolving utilization in columns B, C, D and name them as Years of credit history, Revolving balance and revolving utilization. Go to Data > Data Analysis > Regression. Enter Input Y Range as $A$1:$A$7, enter Input X Range as $B$1:$B$7. Select Labels, Confidence Level and enter the confidence level as 95%. Click OK. The output is: From the obtained regression output, the estimated regression equation is Credit score = 768.9124 – 1.5847*Years of experience + 0.0014*Revolving balance – 238.84*Revolving utilization. Test for the significance of the regression coefficients: Decision rule based on P-value approach: If P-value ≤ α, then reject the null hypothesis H0. If P-value > α, then fail to reject the null hypothesis H0. The level of significance α = 0.05. The P-values of the predictor variables Years of credit history, Revolving balance and revolving utilization are 0.2823, 0.1231 and 0. The P-values of the predictor variables Years of credit history, Revolving balance 0.2823, 0.1231 are greater than 0.05. Conclusion based on P-value approach: The P-value is 0 and α value is 0.05. Here, P-value is less than the α value. That is, 0 (=P-value) < 0.05s (=α). By the rejection rule, reject the null hypothesis H0. Therefore, the predictor variable revolving utilization is useful in predicting the response variable Credit score. Thus, the best model is Credit score = nothing + Utilization.