# PSYC 500 Statistics Exam 3

Q1. According to Cohen’s rules of thumb what would constitute a “small” effect size?

• .20
• 40
• .50
• .80

Q2. Which variable is the most accurate estimate of the magnitude of the effect in ANOVA?

• δ
• d
• ω2
• η2

Q3. If a researcher obtains a power = .75, this means:

• There is a 75% chance of retaining the null
• There is a 75% chance of rejecting the null if it is false
• There is a 75% chance of making a Type II error
• There is a 75% chance that your data has been entered properly

Q4. Tukey’s HSD test is used when:

• We want to find out how much of the variability in our data is due to the effect
• We want to avoid calculating an ANOVA
• We want to avoid calculating a repeated measures ANOVA
• We want to find out which of the treatment means in our ANOVA were significantly different

Q5. Keeping everything else constant, changing from a 1-tailed to a 2-tailed hypothesis will:

• increase power
• decrease power
• not change power
• have an unknown effect on power

Q6. The repeated measures ANOVA breaks the ________ source of variability into 2 parts in order to eliminate the _______ source of variability.

• within(error) – subjects’
• between(group) – subjects’
• total – between
• subjects – between

Q7. If you obtain a significant F statistic you know that:

• at least one mean is statistically different from one other mean
• all the means are different from each other
• all the means come from the same population
• the null hypothesis is probably correct

Q8. For which of the following is it possible to get a negative value?

• F
• t
• ω2
• power

Q9. In an Analysis of Variance test (ANOVA), what term is used to signify (or is equivalent to) variance?

• F-ratio
• sum of squares
• mean square
• degrees of freedom

Q10. A researcher can alter the power of an experiment by

• changing alpha
• changing sample size
• both a and b
• neither a nor b

Q11. Keeping all other factors constant, changing the level of confidence from 99% to 95% will cause the width of the confidence interval to:

• increase
• decrease
• remain unchanged
• change in a random fashion

Q12. If the probability of Type II error is .43, then power is:

• .05
• .43
• .57
• not enough information to solve this problem

Q13. Keeping everything else constant, if s was increased, we would expect power to

• increase
• decrease
• remain unchanged 