In: Statistics and Probability
Let x be a random variable representing percentage change in neighborhood population in the past few years, and let y be a random variable representing crime rate (crimes per 1000 population). A random sample of six Denver neighborhoods gave the following information.
x | 26 | 2 | 11 | 17 | 7 | 6 |
y | 179 | 34 | 132 | 127 | 69 | 53 |
In this setting we have Σx = 69, Σy = 594, Σx2 = 1175, Σy2 = 74,320, and Σxy = 9134.
(a) Find x, y, b, and the equation of the least-squares line. (Round your answers for x and y to two decimal places. Round your least-squares estimates to four decimal places.)
x | = | |
y | = | |
b | = | |
ŷ | = | + x |
Find the sample correlation coefficient r and the coefficient of determination. (Round your answers to three decimal places.)
r = | |
r2 = |
What percentage of variation in y is explained by the
least-squares model? (Round your answer to one decimal
place.)
%
(d) Test the claim that the population correlation coefficient ρ is
not zero at the 1% level of significance. (Round your test
statistic to three decimal places.)
t =
Find or estimate the P-value of the test statistic.
P-value > 0.2500.125 < P-value < 0.250 0.100 < P-value < 0.1250.075 < P-value < 0.1000.050 < P-value < 0.0750.025 < P-value < 0.0500.010 < P-value < 0.0250.005 < P-value < 0.0100.0005 < P-value < 0.005
For a neighborhood with x = 19% change in population in
the past few years, predict the change in the crime rate (per 1000
residents). (Round your answer to one decimal place.)
crimes per 1000 residents
(f) Find Se. (Round your answer to three
decimal places.)
Se =
(g) Find an 80% confidence interval for the change in crime rate
when the percentage change in population is x = 19%.
(Round your answers to one decimal place.)
lower limit | crimes per 1000 residents |
upper limit | crimes per 1000 residents |
(h) Test the claim that the slope β of the population
least-squares line is not zero at the 1% level of significance.
(Round your test statistic to three decimal places.)
t =
Find or estimate the P-value of the test statistic.
P-value > 0.2500.125 < P-value < 0.250 0.100 < P-value < 0.1250.075 < P-value < 0.1000.050 < P-value < 0.0750.025 < P-value < 0.0500.010 < P-value < 0.0250.005 < P-value < 0.0100.0005 < P-value < 0.005
Find an 80% confidence interval for β and interpret its meaning. (Round your answers to three decimal places.)
lower limit | |
upper limit |
ΣX = 69
ΣY = 594
ΣX * Y = 9134
ΣX2 = 1175
ΣY2 = 74320
Part a)
X̅ = Σ( Xi / n ) = 69/6 = 11.5
Y̅ = Σ( Yi / n ) = 594/6 = 99
Equation of regression line is Ŷ = a + bX
b = 6.037
a =( Σ Y - ( b * Σ X) ) / n
a =( 594 - ( 6.0367 * 69 ) ) / 6
a = 29.578
Equation of regression line becomes Ŷ = 29.578 + 6.037
X
Part b)
r = 0.947
= 0.896
Explained variation = 0.896* 100 = 89.6%
Part d)
To Test :-
H0 :- ρ = 0
H1 :- ρ ≠ 0
Test Statistic :-
t = (r * √(n - 2) / (√(1 - r2))
t = ( 0.9466 * √(6 - 2) ) / (√(1 - 0.8961) )
t = 5.873
To Test :-
H0 :- ρ = 0
H1 :- ρ ≠ 0
Test Statistic :-
t = (r * √(n - 2) / (√(1 - r2))
t = ( 0.9466 * √(6 - 2) ) / (√(1 - 0.8961) )
t = 5.87339
P - value = P ( t > 5.8734 ) = 0.0042
0.0005 < P-value < 0.005
When X = 19
Ŷ = 29.578 + 6.037 X
Ŷ = 29.578 + ( 6.037 * 19 )
Ŷ = 144.3
Part f)
Standard Error of Estimate S = √ ( Σ (Y - Ŷ ) / n - 2) =
√(1611.4862 / 4) = 20.0717
Part g)
Confidence Interval of
Ŷ = 29.578 + 6.0367 X
Ŷ = 144.281
t(α/2) = t(0.2/2) =1.533
80% confidence interval is ( 127.0 <
< 161.5 ).
Part h)
To Test :-
H0 :- ß = 0
H1 :- ß ≠ 0
Test Statistic :-
t = ( b - ß) / ( S / √(S(xx)))
t = ( 6.0367 - 0 ) / ( 20.0717 / √(381.5))
t = 5.874
P - value = P ( t > 5.8744 ) = 0.00419
0.0005 < P-value < 0.005
Confidence Interval for ß
t(α/2) = t(0.2/2) =1.533
80% confidence interval is ( 6.037 < β̂ <
1.028 )
We are 80% confidence that the slope lies within the interval.