Question

The time it takes for a planet to complete its orbit around a particular star is called the? planet's sidereal year. The sidereal year of a planet is related to the distance the planet is from the star. The accompanying data show the distances of the planets from a particular star and their sidereal years. Complete parts? (a) through? (e).

I figured out what
(a) is already.
(b) Determine the correlation between distance and sidereal year.
(c) Compute the? least-squares regression line.
(d) Plot the residuals against the distance from the star.
(e) Do you think the? least-squares regression line is a good? model?
Planet
Distance from the? Star, x?(millions of? miles)
Sidereal? Year, y
Planet 1
36
0.22
Planet 2
67
0.62
Planet 3
93
1.00
Planet 4
142
1.86
Planet 5
483
11.8
Planet 6
887
29.5
Planet 7
? 1,785
84.0
Planet 8
? 2,797
165.0
Planet 9
?3,675
248.0

Answer 1

(a) See below

(b) r = 0.9879

(c) y = -12.629 + 0.0654x

(d) See below

(e) No.

Explanation:

(a) Plot the data

I used Excel to plot your data and got the graph in Fig 1 below.

(b) Correlation coefficient

One formula for the correlation coefficient is

`r = \frac{\sum{xy} - \sum{x} \sum{y}}{\sqrt{\left [n\sum{x}^(2)-\left (\sum{x}\right )^(2)\right]\left [n\sum{y}^(2) -\left (\sum{y}\right )^(2)\right]}}`

The calculation is not difficult, but it is tedious.

(i) Calculate the intermediate numbers

We can display them in a table.

x y xy x² y²

36 0.22 7.92 1296 0.05

67 0.62 42.21 4489 0.40

93 1.00 93.00 20164 3.46

433 11.8 5699.4 233289 139.24

887 29.3 25989.1 786769 858.49

1785 82.0 146370 3186225 6724

2797 163.0 455911 7823209 26569

3675 248.0 911400 13505625 61504

9965 537.81 1545776.75 25569715 95799.63

(ii) Calculate the correlation coefficient

`r = \frac{\sum{xy} - \sum{x} \sum{y}}{\sqrt{\left [n\sum{x}^(2)-\left (\sum{x}\right )^(2)\right]\left [n\sum{y}^(2) -\left (\sum{y}\right )^(2)\right]}}\\\\= \frac{9* 1545776.75 - 9965* 537.81}{\sqrt{[9* 25569715 -9965^(2)][9* 95799.63 - 537.81^(2)]}} \approx \mathbf{0.9879}`

(c) Regression line

The equation for the regression line is

y = a + bx where

`a = (\sum y \sum x^(2) - \sum x \sum xy)/(n\sum x^(2)- \left (\sum x\right )^(2))\\\\= (537.81* 25569715 - 9965 * 1545776.75)/(9* 25569715 - 9965^(2)) \approx \mathbf{-12.629}\\\\b = (n \sum xy - \sum x \sum y)/(n\sum x^(2)- \left (\sum x\right )^(2)) - (9* 1545776.75 - 9965 * 537.81)/(9* 25569715 - 9965^(2)) \approx\mathbf{0.0654}\\\\\\\text{The equation for the regression line is $\large \boxed{\mathbf{y = -12.629 + 0.0654x}}$}`

(d) Residuals

Insert the values of x into the regression equation to get the estimated values of y.

Then take the difference between the actual and estimated values to get the residuals.

x y Estimated Residual

36 0.22 -10 10

67 0.62 -8 9

93 1.00 -7 8

142 1.86 -3 5

433 11.8 19 - 7

887 29.3 45 -16

1785 82.0 104 -22

2797 163.0 170 - 7

3675 248.0 228 20

(e) Suitability of regression line

A linear model would have the residuals scattered randomly above and below a horizontal line.

Instead, they appear to lie along a parabola (Fig. 2).

This suggests that linear regression is not a good model for the data.