150 likes | 315 Views
Warm-Up. Grab a half sheet and start working on it! It says QUIZ at the top, so NO TALKING! . Section 11.2. Finding Expected Counts. Expected count for French wine bought when there was no music playing: . Does background music influence what customers buy?.
E N D
Warm-Up • Grab a half sheet and start working on it! • It says QUIZ at the top, so NO TALKING!
Finding Expected Counts • Expected count for French wine bought when there was no music playing:
Does background music influence what customers buy? • You already have the observed counts… • Fill in the table with expected counts…
Chi-Squared test for Homogeneity • The null hypothesis is that the distribution of this categorical variable is the same for all the populations or treatments. • Remember…this is when we are imposing treatments! • What would the hypotheses be for this problem?
Still have to check conditions! • For this problem… • Random – • Large sample size – each expected count in your table still has to be at least 5. • Independent –
Find chi-squared for the sum of the nine terms • P-value = • Conclusion?
Using your calculator • Go to STAT and look at the chi-squared test…it uses matrices! • Let’s test the last problem!
Chi-Squared test for association/independence • The null hypothesis states that there is no association between two categorical variables in the population of interest. • : The two categorical variables are independent in the population of interest.
Do angry people have more heart disease? • A study followed a random sample of 8474 people with normal blood pressure (and no heart disease) for about 4 years. Each person took and Anger Test to measure how prone a person is to sudden anger. Researchers also recorded whether each person developed coronary heart disease (CHD) below.
State: • Plan:
Do: • Conclude:
Choose the right test! • Are men and women equally likely to suffer lingering fear from watching scary movies as children? Researched asked a sample of 117 college students to write narratives of their exposure to scary movies before the age of 13.
How to tell? • If it is an associations test – does this variable have anything to do with this other variable – one sample • If it is a homogeneity test – multiple samples(experiments count as multiple samples) – does the distribution of each sample match?
Homework • Pg 724 (29-33, 35-41, 44, 50, 53-58)