Math 127B, Notes for lecture 11
Mrinal Raghupathi
Monday, February 28th, 2011
Administrivia
Today we will discuss tests of significance.
Reminders
1. Homework 7 is due Thursday, 3/17 in recitation.
2. Quiz in recitation over chapter 26 on 3/17.
3. This week’s recitation will be a discussion of problems from chapter 26.
1
What is a test of significance?
A test of significance is used to test a claim about a population parameter. Examples of parameters
could be the average number of credit hours taken by freshmen, the average GPA and a certain
university, the average rainfall in Nashville in the month of February, the amount of sugar in
chocolate, or the the time taken to service a maintenance request.
A test of significance involves formulating a null hypothesis, which is a claim about the popu
lation parameter. All the examples we will look at will be formulated in terms of a box model. So
our null hypotheses will be claims about a box.
Our data will usually indicate a suitable alternative hypothesis.
We will study three tests of significance in the next three weeks.
1. Tests for averages or percentages. There are two test statistics, the
z
test, and the
t
test.
2. Tests for the difference of two averages. Tests like are used to determine whether two popu
lations are different. For example are high school dropout rates different in Tennessee and
Kentucky.
1
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
3. Tests for goodnessoffit.
The
χ
2
test (
χ
is the Greek letter “chi”, rhymes with “tie”) will
be our focus.
These tests determine whether observations fit a certain model, i.e., do the
observations come from a specified box.
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '11
 Staff
 Math, Statistics, Null hypothesis, Hypothesis testing, Statistical hypothesis testing, MRINAL RAGHUPATHI

Click to edit the document details