May 1

Statistics
Relationships – Causal and otherwise
Outline
1. The role of randomization in establishing relationships.
2. Headlines.
Sexism Pays
Fan in room cuts SIDS
Breast Implants Boost Suicides
Certified Teachers Boost Student Scores
Eating Pizza Cuts Cancer
Wearing a helmet puts cylcists at risk
Credit cards make you fat
Deep-voiced men have more kids
Tooth loss in elderly linked to mental impairment
May 1, 2009
Statistics
Relationships – Causal and otherwise
May 1, 2009
3. In each of the following stories, identify the explanatory variable, the response variable,
and the statistical method used to determine whether there is a relationship between the
two variables.
(a) A survey is taken of Calvin students. a random sample of 1,000 students is asked
what class they are in (FR, SO, JR, SR) and how many hours a week that they
study.
Explanatory Variable:
Response Variable:
Inference Method (circle)
Two-sample t
ANOVA
Chi-square
(b) People who attend church regularly are less likely to be clinically depressed.
Explanatory Variable:
Response Variable:
Inference Method (circle)
Two-sample t
ANOVA
Chi-square
4. The temperature of a number of Calvin students (all from Psychology 151) is taken. The
gender (1=Female and 2=Male) is also recorded. The following Crunchit output is used
to make an inference.
(a) What are the null and alternate hypotheses?
(b) What conclusion can you draw about the relative temperatures of females and males?
(c) Are we safe in generalizing the conclusion of the last part to the whole Calvin student
body?
Statistics
Relationships – Causal and otherwise
May 1, 2009
5. Each of the statistical tests that we did made some assumptions about the population.
While we can not always be sure that the assumptions are true, we had some conditions
on the various tests that we checked before carrying them out.
(a) Two sample t
Assumptions:
Conditions:
(b) Chi-square
Conditions:
(c) ANOVA
Assumptions:
Conditions: