STAT 3743 Daily Outline
Up there should be four (4) files:
-
STAT3743_xxxxxx.3gp
(video for mobile phones) -
STAT3743_xxxxxx.ogv
(video in Ogg format) -
STAT3743_xxxxxx.pdf
(scanned lecture transcript) -
STAT3743_xxxxxx.webm
(video in WebM format)
The WebM
video is definitely the highest quality, but
you need a compatible browser/player to watch it.
See How to watch the video for instructions to get one.
Basic hypothesis testing procedure
- set up hypotheses, collect some data
- assume null is true, construct 95% CI for parameter
- if CI doesn't cover null value, reject H0, otherwise, don't reject
More terminology
- Type I error, Type II error
- significance level
- rejection region
- two-sided and one-sided tests
Tests of hypotheses for one proportion (asymptotic)
Draw pictures
Example: observe bunch of shotguns, do hypothesis test
Example: do another hypothesis test, but for different significance levels
p-value of a hypothesis test
Example: find p-value for previous test
Hypothesis testing: "reject H0 if p-value is small"
Tests of hypotheses for two proportions
For one mean and/or one variance
Given SRS(n) from norm
, unknown mean
For means
- σ known: z-tests for one mean
- σ unknown: t-tests for one mean
If σ unknown but n is large then use z-test
Example: SRS(9) from norm
, hypothesis test for the mean, find p-value
Date: 2010-11-05 14:58:44 EDT
HTML generated by org-mode 7.01trans in emacs 23