Last time | Next time |
Let us continue our work in this class, in order to maintain some sense of the normal (no pun intended!:).
There has been no change in our exam schedule!
I will be supplementing my own presentations of our packets with additional material provided by other instructors, who happened to have videos at the ready. You might check those out, in case they provide useful additional insights.
that I recently encountered in my research.
What is illustrated here is a couple of months that look nothing like the rest of the months. We might call them "outliers", but they are not errors: they are simply exceptional elements of the data set, which don't seem to "fit the data". To what extent would we be justified in "throwing them out" of the data set?
At left is the distribution of the population.
By taking samples of multiple variable values, and turning them into sample means, the original distribution (at left, which was far from normal) morphs into a more normal distribution for the means, tucked about the population mean of the original variable.
Furthermore, the standard deviation of the sample means decreases with increasing sample size.
So one of the important points is that we're back to dealing with normals, if we're willing to work with sample means taken from sufficiently large samples.
Sorry about the horrible audio in the following. This should improve when I move to the iPad for recording, but it will be a little harder to mark up the pdfs. Trade-offs....
I've prepared a video summary of the final filled-in packet, if you can't stand to go through the intro and examples with me....
Stat -> Tables -> Contingency ->
(then either data or summary, depending on what you have)