In: Statistics and Probability
Chapter 6 #5- a, b, c, d
Do towns in Massachusetts with higher elevations tend to get more snowfall? To answer this question, a random sample of five towns in Massachusetts, their average yearly snowfall (in inches), and elevation (in feet) were recorded in Table 6.9.
Town |
Average Snowfall (Inches) |
Elevation (Feet) |
Boston |
43.8 |
141 |
Amherst |
37.0 |
295 |
Springfield |
40.5 |
70 |
Pittsfield |
62.1 |
1,039 |
Lowell |
61.6 |
102 |
a) Draw a scatterplot and find the equation for the line of best fit.
b) Find the residual for Springfield.
c) Interpret whether or not you believe there is a significant relationship between the average snowfall and elevation in Massachusetts.
d) Find and interpret a 95% confidence interval for the true population slope parameter.
(a)
The line of best fit is y = 0.0152x + 43.989
(b) For Springfield, y = 0.0152(70) + 43.989 = 45.05
Residual = 40.5 - 45.05 = -4.55
(c) The R^2 value is very low, and there is a low degree of association between elevation and snowfall. It is therefore most likely that no significant correlation exists between elevation and snowfall.
(d)
Regression Analysis | |||||||
r² | 0.266 | n | 5 | ||||
r | 0.516 | k | 1 | ||||
Std. Error | 11.848 | Dep. Var. | Average Snowfall (Inches) | ||||
ANOVA table | |||||||
Source | SS | df | MS | F | p-value | ||
Regression | 152.5446 | 1 | 152.5446 | 1.09 | .3738 | ||
Residual | 421.1154 | 3 | 140.3718 | ||||
Total | 573.6600 | 4 | |||||
Regression output | confidence interval | ||||||
variables | coefficients | std. error | t (df=3) | p-value | 95% lower | 95% upper | std. coeff. |
Intercept | 43.9892 | 0.000 | |||||
Elevation (Feet) | 0.0152 | 0.0146 | 1.042 | .3738 | -0.0312 | 0.0617 | 0.516 |
The 95% confidence interval for the true slope is [-0.0312, 0.0617]. This includes 0. This confirms that elevation is not a significant predictor of snowfall. We are 95% confident that the true slope parameter lies in the above interval