# QMS442: Multiple Regression for Business SPSS INDIVIDUAL PROJECT - Draft WINTER 2022 DUE: April 7, 2022, by 11:59 pm. MARKS: Total marks = 100 (or 20% of the final grade) PENALTY: There will be a...

How much does it cost? I’m in rush please give me details asap

Answered 1 days AfterApr 08, 2022

## Answer To: QMS442: Multiple Regression for Business SPSS INDIVIDUAL PROJECT - Draft WINTER 2022 DUE: April 7,...

Manoj answered on Apr 09 2022
Model 1. First order multiple regression model.
We find that the value of R squared is 0.486. Which means multiple linear regression model explains 48.6% variability in the data.
The durbin Watson test statistic is 1.783, which is between two critical values (1.5,2.5). Therefore we can assume that there is first
order auto-correlation in our data. We find that the all values of Tolerance are greater than 0.1 and VIFs are close to 1. We can assume that there is no multicollinearity present in the data. Now we check the normality of residuals with a normal P-P plot. We can see that the all points follow the normal line with no deviations. It indicates that the residuals are normally distributed.
The first order multiple regression equation is given by,
y = 183.721 – 3.827(FLOOR) + 1.725 (DIST) + 40.133 (VIEW) + 4.183 (END) – 32.452 (FURNISH)
Now we check the significance of the model.
The p-value of F test is 0 which is less than the level of significance. We can reject the null hypothesis that and conclude that model provides a better fit than the intercept-only model.
The p-values of all independent variables expect END are less than level of significance. We can say that the variables FLOOR, DIST, VIEW and FURNISH are statistically significant. Independent variable END can be removed from the model since it is statistically insignificant.
Model 2: second order multiple regression for the quantitative variables.
Dependent Variable: Price: in hundreds of dollars (PRICE100)
Independent Variable:
1. DIST
2. DIST2
From the SPSS output, we find the value of R-Squared is 0.186, Which means multiple linear regression model explains 18.6% variability in the data.
The durbin Watson test statistic is1.294, which is between two critical values (1.5,2.5). Therefore we can assume that there is first order auto-correlation in our data.
We see that the value of tolerance for DIST and DIST2 are less than 0.1and VIF for DIST and DIST2 are too high. Its means there is high correlation between these two variables. There is a presence on multicollinearity. Now we check the normality of residuals with a normal P-P plot. We can see that the all points follow the normal line with no deviations. It indicates that the residuals are normally distributed.
The fitted second order multiple regression for the quantitative variables given by,
PRICE100 = 209.762 – 8.093(DIST) + 0.669 (DIST2)
T test for the significance of regression coefficient.
From the output, we can find that the p-values for all independent variables are less than the level of significance. We can say that these three variables are statistically significant.
F test for overall significance.
The null and alternative hypotheses of the F test given by,
Null Hypothesis: The model with no independent variables fits the data as well as your model.
Alternative Hypothesis: Model fits the data better than the intercept only model.
From the ANOVA table of output we find that the p-value of F test is 0 and which is less than the level of significance 0.05, we reject the null hypothesis. There is enough evidence to claim that Model...
SOLUTION.PDF