In: Statistics and Probability
DETROIT (Y) ANN ARBOR (X)
2008 59 2008 61
2009 60 2009 58
2010 61 2010 60
2011 69 2011 68
2012 66 2012 67
2013 62 2013 64
2014 64 2014 66
2015 71 2015 70
2016 69 2016 72
2017 66 2017 64
h0 :There is a statistical correlation between the temperatures in two different Michigan cities.
What relationships exist between the data sets? Are they significant and why?
Here we are to test the presense of correlation between the temperatures of two different Michigan cities.
If be the correlation coefficient between the temperatures of the two cities.
We are to test the hypothesis :
versus
If r be the sample correlation coeffecient and n be the sample size which is 10.
The appropriate test statistic would be :
Now, t follows t-distribution with (n-2) degrees of freedom.
We shall reject our null hypothesis if our observed t > t;n-2
Accordingly, t=0.906788 * sqrt(10-2) / sqrt(1-0.9067882)
= 6.0836
If our chosen level of significance
t0.05,8 =1.860
Clearly , Observed t > t0.05,8
So, we reject our null hypothesis at 5% level of significance and conclude that the temperature in the two cities are significantly correlated.