quantitative methods unit 4
Questions and Complete
Solutions Graded A+
3 reasons ANOVA is better than multiple t-tests - Answer: 1) you have to perform multiple t-
tests, and as the number of groups increase, you have to do more comparisons (5 groups = 10
comparisons)
2) more comparisons are possible with ANOVA ( can compare all averages, and average of 2
groups against 1)
3) inflating alpha; the probability of making a type 1 error increases every time we add another
t-test b/c of addition rule of probability; p(.05) + p(.05 + p(.05) = .14; anova keeps probability
at .05
power curve - Answer: a graph that shows the relationship of the power as a function of the
time using that product
power table - Answer: table for a hypothesis testing procedure showing the statistical power of
a study for various effect sizes and sample sizes
within-groups variance - Answer: variability among participants due to individual differences,
inherent in each group
population variance - Answer: Equals the mean squared deviation. Variance is the average
squared distance from the mean.
mean squares (variance) - Answer: sum of squares divided by degrees of freedom
Post hoc test - Answer: when used with an ANOVA, a means of comparing all possible pairs of
groups to determine which ones differ significantly from each other; distance/difference
, measure; any difference between 2 means that exceeds the value of HSD is statistically
significant
between-groups variance - Answer: includes within group variance plus any treatment effect
from the IV
f ratio - Answer: ratio of the between-groups population variance estimate to the within-groups
population variance estimate
inflating alpha - Answer:
post hoc comparisons - Answer: statistical comparisons made between group means after
finding a significant F ratio
factorial design - Answer:
inherent variation - Answer: variation due to chance factors
In 1 way ANOVA, if H0 is true - Answer: all variation is within group variance
In 1 way ANOVA, if H0 is false - Answer: within group variance cannot account for all variability;
groups means differ more than you would expect from chance/sampling error
ANOVA compares the size of ____ and ____ variance - Answer: between and within
as between-group variance increases - Answer: F increases (no alternative hypothesis)
underlying assumptions of 1 way ANOVA - Answer: (same as independent t-test)
Questions and Complete
Solutions Graded A+
3 reasons ANOVA is better than multiple t-tests - Answer: 1) you have to perform multiple t-
tests, and as the number of groups increase, you have to do more comparisons (5 groups = 10
comparisons)
2) more comparisons are possible with ANOVA ( can compare all averages, and average of 2
groups against 1)
3) inflating alpha; the probability of making a type 1 error increases every time we add another
t-test b/c of addition rule of probability; p(.05) + p(.05 + p(.05) = .14; anova keeps probability
at .05
power curve - Answer: a graph that shows the relationship of the power as a function of the
time using that product
power table - Answer: table for a hypothesis testing procedure showing the statistical power of
a study for various effect sizes and sample sizes
within-groups variance - Answer: variability among participants due to individual differences,
inherent in each group
population variance - Answer: Equals the mean squared deviation. Variance is the average
squared distance from the mean.
mean squares (variance) - Answer: sum of squares divided by degrees of freedom
Post hoc test - Answer: when used with an ANOVA, a means of comparing all possible pairs of
groups to determine which ones differ significantly from each other; distance/difference
, measure; any difference between 2 means that exceeds the value of HSD is statistically
significant
between-groups variance - Answer: includes within group variance plus any treatment effect
from the IV
f ratio - Answer: ratio of the between-groups population variance estimate to the within-groups
population variance estimate
inflating alpha - Answer:
post hoc comparisons - Answer: statistical comparisons made between group means after
finding a significant F ratio
factorial design - Answer:
inherent variation - Answer: variation due to chance factors
In 1 way ANOVA, if H0 is true - Answer: all variation is within group variance
In 1 way ANOVA, if H0 is false - Answer: within group variance cannot account for all variability;
groups means differ more than you would expect from chance/sampling error
ANOVA compares the size of ____ and ____ variance - Answer: between and within
as between-group variance increases - Answer: F increases (no alternative hypothesis)
underlying assumptions of 1 way ANOVA - Answer: (same as independent t-test)
