00:01
So we have this data for delta, for united, for u .s.
00:07
Airways, and we have data on whether they are late, and this is on time, and we have 39, 51, 56, and this totaled a total late of 146, and on time, we had 26.
00:35
249, 344, and that gives us a total of 854, and then adding up the row totals and column totals.
00:43
This total here is 300.
00:46
We had 300, and we had 400 for usa, and that's a total of 1 ,000 flights that they were looking at.
00:53
And we want to do a hypothesis test, and we would assume that the proportion late, late, is the same for the three airlines and alternately that the proportion late is not the same for the three airlines and this is going to be a kai squared test and i truly i entered the data as a matrix a three by two matrix in my calculator my degrees of freedom i know will be two times one will be two and i'm going to do the software to get that test to and the kye squared value going to stat and test and going to kye squared test.
01:52
Not a goodness of fit, just a regular old kai squared test.
01:55
And i find out that this test statistic comes out to be 2 .2316.
02:01
And the p value associated with this kai squared being greater than or equal to that value comes out to be 0 .3276.
02:12
And i believe your significance level was 5%.
02:14
Well, this is definitely higher than 0 .106.
02:16
Five significance level...