In: Statistics and Probability
Question: Compute F and use it to test whether the overall model is significant using a p-value (α = 0.05).
The estimated regression equation for a model involving two independent variables and 65 observations is:
yhat = 55.17+1.1X1 -0.153X2
Other statistics produced for analysis include: SSR = 12370.8, SST = 35963.0, Sb1 = 0.33, Sb2 = 0.20.
The model being estimated is
where is the intercept
are the slope coefficients for
is a random disturbance
to test whether the overall model is significant, the hypotheses are
n=65 is the number of observations
k=2 is the number of independent variables
The sum of square regression (SSR) is
The degrees of freedom for SSR = k=2
The sum of square total is
The sum of square errors is
The degrees of freedom for SSE = n-k-1=65-2-1=62
The F statistics is
ans: F statistics is 16.26
The numerator degrees of freedom =2 and the denominator df=62
The using the F table for alpha=0.05 and numerator degrees of freedom =2 and the denominator df=60 (the closest to 62), we get a critical value of 3.15.
We will reject the null hypothesis if the test statistics is greater than the critical value for alpha=0.05.
Here, the test statistics is 16.26 and it is greater than the critical value 3.15. Hence we reject the null hypothesis.
ans: We conclude that there is sufficient evidence to support the claim that the overall model is significant.