In: Statistics and Probability
A model for estimating the price of a cell phone has weight (X1), memory size (X2) and display quality(X3) as predictor variables. The model based on 30 samples was Y = 8 – 3X1 + 4X2 +5X3. The standard errors for X1, X2, and X3 are 0.4, 1.3 and 2.2 respectively. If the R2 for the model was 0.74,
a)Find the F-stat. Is the model significant at the 1% significance level?
b)Which of the three variables is statistically more significant in predicting the price of a cell phone? Why?
20 Points
a)Find the F-stat. Is the model significant at the 1% significance level?
Using Fstat table, df1 = 2, df2= 26, we the pvalue = 0
Hypothesis:
Ho : All the beta coefficient are equal to zero.
H1 : At least one of the beta coefficient is not equal to
zero.
We find that the pvalue = 0, which is less than 0.01, hence we
reject the null hypothesis and conclude that the regression
equation is significant.
b)Which of the three variables is statistically more significant in predicting the price of a cell phone? Why?
For each beta coefficient we test the following hypothesis.
Next we check the pvalue for the variable in the regression output and check if the pvalue is less than 0.05, if it is less than 0.05, then we reject the null hypothesis and conclude that the variable is significant