In: Statistics and Probability
PSYC 2054: Worksheet 6
1. Research Study: We want to figure out what characteristics of boys are most attractive to high-school girls. High-school girls were randomly assigned three groups to hear about a guy with trendy clothes, a nice car, or a confident attitude. There were 9 girls in each group. They gave ratings on a scale from 1 to 10, with 1 being “not interested” and 10 being “very interested.”
Question: Is there a significant difference between the attractiveness ratings given by the three groups of girls?
What is the factor?
What are the levels of the factor?
Step 1: State Hypotheses
Step 2: Determine Comparison Distribution
Step 3: Set the Criteria for a Decision
dfW=
Step 3: Compute the Test Statistic
Trendy Clothes |
Nice Car |
Confident Attitude |
8 |
6 |
10 |
6 |
7 |
9 |
9 |
8 |
10 |
6 |
6 |
10 |
8 |
4 |
8 |
6 |
5 |
9 |
7 |
5 |
10 |
6 |
6 |
9 |
6 |
8 |
8 |
Step 5: Make a Decision
Reject/Fail to Reject the null?
What does this mean (be sure to talk about significance)?
Factor : Characteristics of boys
Levels of the factor : Trendy clothes, a nice car, or a confident attitude
Hypothesis :
Null: There is no significant difference between the attractiveness ratings given by the three groups of girls
Research: There is a significant difference between the attractiveness ratings given by the three groups of girls
Distribution : F distribution
Degrees of freedom for the comparison distribution : df1 = 2 and df2 = 24
Critical region :
F(2,24,0.95) = 0.051
F(2,24,0.05) = 3.403
If any value lies outside ( 0.051, 3.403) then we reject null hypothesis at 5% level of significance.
Rejection region is in upper tail because value of F distribution lies in the first quadrant and is always positive.
So, we would expect a test statistic value greater than 3.403 to reject null hypothesis.
Since, P-value = 0 < 0.05 (level of significance), we reject null hypothesis and conclude that There is a significant difference between the attractiveness ratings given by the three groups of girls at 5 % level of significance.