In: Statistics and Probability
1a) Here is a bivariate data set.
x | y |
---|---|
26.1 | 41.5 |
26.6 | 46.9 |
37.2 | 44.2 |
37.2 | 46.6 |
34.1 | 44.1 |
33.8 | 38.4 |
39.9 | 30 |
12.4 | 66.8 |
8.1 | 49.6 |
13.4 | 61.6 |
15 | 52.4 |
21.8 | 61.6 |
3.6 | 53.9 |
-9.3 | 97.2 |
28.3 | 39.4 |
29.4 | 44.9 |
29.8 | 41.2 |
Find the correlation coefficient and report it accurate to three
decimal places.
r =
What proportion of the variation in y can be explained by
the variation in the values of x? Report answer as a
percentage accurate to one decimal place.
r² = %
part b)You wish to determine if there is a negative linear
correlation between the two variables at a significance level of
α=0.005α=0.005. You have the following bivariate data
set.
x | y |
---|---|
23.3 | 60.3 |
17 | 54.3 |
-2.7 | 68.7 |
14.7 | 59.5 |
49.6 | 41.7 |
10.5 | 57.7 |
21.8 | 48.5 |
14.9 | 56.7 |
37.2 | 46.4 |
29.2 | 42.5 |
30.4 | 50.7 |
10.2 | 58.1 |
What is the correlation coefficient for this data set?
r =
To find the p-value for a correlation coefficient, you need to
convert to a t-score:
t=√r2(n−2)1−r2t=r2(n-2)1-r2
This t-score is from a t-distribution with
n–2 degrees of freedom.
What is the p-value for this correlation coefficient?
p-value =
Your final conclusion is that...
can you please show the work on a ti 84 plus as well please thank you so much
1)
ΣX | ΣY | Σ(x-x̅)² | Σ(y-ȳ)² | Σ(x-x̅)(y-ȳ) | |
total sum | 387.4 | 860.3 | 2977.457647 | 3706.3 | -2760.22 |
mean | 22.79 | 50.61 | SSxx | SSyy | SSxy |
correlation coefficient , r = Sxy/√(Sx.Sy)
= -0.8309
.........
R² = (Sxy)²/(Sx.Sy) = 0.6904
69% of the variation in y can be explained by the
variation in the values of x
........
correlation hypothesis test
Ho: ρ = 0
Ha: ρ ╪ 0
n= 17
alpha,α = 0.005
correlation , r= -0.8309
t-test statistic = r*√(n-2)/√(1-r²) =
-5.783
DF=n-2 = 15
p-value = 0.0000
Decison: p value < α , So, Reject
Ho
...................
2)
ΣX | ΣY | Σ(x-x̅)² | Σ(y-ȳ)² | Σ(x-x̅)(y-ȳ) | |
total sum | 256.1 | 645.1 | 2122.009167 | 705.6 | -1072.98 |
mean | 21.34 | 53.76 | SSxx | SSyy | SSxy |
correlation coefficient , r = Sxy/√(Sx.Sy)
= -0.8768
correlation hypothesis test
Ho: ρ = 0
Ha: ρ ╪ 0
n= 12
alpha,α = 0.005
correlation , r= -0.8768
t-test statistic = r*√(n-2)/√(1-r²) =
-5.767
DF=n-2 = 10
p-value = 0.0002
Decison: p value < α , So, Reject
Ho
There is sufficient sample evidence to support the claim that there is a statistically significant negative correlation between the two variables.
..................
THANKS
revert back for doubt
please upvote