Consider again the file temp with measurements of the mean temperature in degrees Celsius in the month of July. Consider the mean temperature in July in De Bilt and Eelde.
(B)
Give a (point) estimate and a 95% confidence interval for the difference in expected mean temperature in July in De Bilt and Eelde.
©
Test with a suitable t-test whether there is a significant difference in expected mean
temperature in July in De Bilt and Eelde.
(D)
Investigate with a suitable test whether there is a difference in proportion of times
that the expected mean temperature in July in De Bilt and Eelde is above 18
degrees.
(E)
Conclusion based on b–d?
-------------------------------------------------------------------------------------
Answers
(B)
Code: Selecteer alles
> temp
$debilt
[1] 14.9 13.7 14.2 15.3 14.1 18.1 15.7 17.2 17.2 17.0 15.4 17.8 19.3 17.0 15.4 15.9 15.8 16.3 18.9 20.1
$eelde
[1] 14.6 13.4 14.1 14.9 14.1 17.5 15.1 17.0 17.1 16.7 14.3 16.8 17.9 15.7 14.5 14.9 15.0 15.7 17.9 18.4
$vlissingen
[1] 15.6 13.9 14.5 16.1 14.4 17.6 16.0 18.0 16.8 17.0 15.7 17.6 19.7 16.8 15.5 16.6 15.8 16.3 18.4 19.6
$terbeek
[1] 14.0 13.7 13.9 15.2 13.8 18.4 16.0 18.0 17.3 17.5 15.7 18.1 20.1 16.8 15.5 16.2 15.5 16.8 18.9 20.4
> mean <- mean(temp$debilt) - mean(temp$eelde)
> mean
[1] 0.685
SD <- sd(temp$debilt) - sd(temp$eelde)
> SD
[1] 0.2577624
n <- length(temp$debilt)
> n
[1] 20
error <- qnorm(0.975)*SD/sqrt(n)
> error
[1] 0.1129673
left <- mean-error
> left
[1] 0.5720327
right <- mean+error
> right
[1] 0.7979673Is dit waar?
Ik weet dus ook niet of ze verwachten dat ik aanneem of het van een normale distributie afkomt of een T distribution. Enig idee?
. Het oefenen loont 
! Volgens mij mag je wel normale verdeling gebruiken...