The following model was fitted to a sample of 28 families in order to explain household bread consumption:

where
y = bread consumption, in loaves per week
x₁ = weekly income, in hundreds of pounds
x₂ = family size
The least squares estimates of the regression parameters were as follows:

b₀ = -0.022; b₁ = 0.056; b₂ = 1.15
The total sum of squares and regression sum of squares were found to be as follows:
SST = 162.1 and SSR = 91.3
A third independent variable—number of teenagers in the household—was added to the regression model. The sum of squared errors when this augmented model was estimated by least squares was found to be 72.6. Test the null hypothesis that, all other things being equal, the number of teenagers in the household does not linearly affect the consumption of bread.

Transcribed Image Text:

y = Bo + Biến + B2X2 + &