00:01
For this problem to begin, let's define the diet group as population 1, and the control group as population 2.
00:18
Now, the null hypothesis for our test would be that there is no significant difference in the mean change for the two.
00:27
So mu1 minus mu2 equals 0, where here mu is the mean bmi change.
00:36
The alternative hypothesis, if the change in bmi is higher for those who eat a healthy diet for three weeks than for those who don't, that would mean that mu1 minus mu2 is greater than 0.
00:54
Now, i can see that there's reference to the data being in stat key, so what i've done is i've downloaded the reference data set, and i'll work through actually doing the analysis here in excel, since this would seem like a case where it is more about using technology and understanding the approach rather than necessarily grinding through it by hand.
01:18
So this is our diet depression data set.
01:22
So we can see we have a whole bunch of stuff, but we're just interested in the bmi difference.
01:27
So we're just interested in this last column, and we're interested in whether this is for diet or control.
01:35
So there are a few different approaches that we can take to this, but the most straightforward approach, the sort of targeting just what we are interested in for this question, would be to go to data analysis, t -test, tosample, let's assume unequal variances...