"T" Party
This type of t test is used when a researcher has one sample, knows the population mean, but does NOT know the population standard deviation.
What is a single-sample t test?
ANOVA is preferred over running multiple t tests because it does this to the overall risk of Type I error.
What is reduces/controls it (keeps the familywise error rate at alpha)?
If a researcher rejects the null hypothesis, they must consider the possibility of committing this type of error.
What is a Type I error?
The formula for between-groups degrees of freedom is this.
What is k – 1?
If a 95% confidence interval for a paired-samples t test captures zero, this is the appropriate conclusion.
What is fail to reject the null hypothesis (the result is not statistically significant)?
A repeated-measures ANOVA is an extension of this type of t test.
What is a paired-samples t test?
In the F ratio, this term serves as the denominator.
What is MSWithin (mean square within-groups, also called MSResidual)?
Setting one's alpha level to a very low level (e.g., .001) increases the risk of committing this type of error.
What is a Type II error?
A researcher records bar presses for 12 rats: 2, 4, 8, 5, 6, 7, 9, 1, 5, 3, 1, 6. The median of this data set is this value.
What is 5? (Ordered: 1, 1, 2, 3, 4, 5, 5, 6, 6, 7, 8, 9 → average of 6th and 7th values = 5)
Eta squared indicates the percentage of this.
What is the variance in the dependent variable that is accounted for (explained) by the independent variable?
A student affairs director has 29 students each experience both a student-created video and a live lecture, then tests their memory.
What is a paired-samples t test?
This is the minimum number of conditions (levels of the IV) required to run a repeated-measures ANOVA.
What is 3 (or 2 but can be done with a t-test as well)?
If a nonrobust assumption is violated in a repeated-measures design, this is what happens to the results.
What is the results cannot be trusted / the researcher should not proceed with the analysis?
If n = 20, k = 4, and N = 80, dfTotal equals this value.
What is 79? (N – 1 = 80 – 1 = 79)
The abbreviation sM stands for this.
What is the estimated standard error of the mean?
If the observed value of a two-tailed, single-sample z test is 2.54 and the critical value is ±1.96, this is the most appropriate decision.
What is reject the null hypothesis? (The observed value exceeds the critical value.)
An ANOVA can only be used when outcome variables are measured at these two levels of measurement.
What are the interval and ratio scales (continuous/scale data)?
Dr. Schram wanted to match pairs by IQ AND have partners tested together in the same room during the experimental condition. She is in danger of violating this assumption for paired-samples t tests.
What is the independence of observations assumption?
Daily Double!!!!!!!!
Given that SSBetween = 20.96 and there are k = 3 groups, MSBetween equals this value.
Cohen's d is an improper choice for reporting effect size in paired-samples t tests because it would do this to the effect size.
What is overestimate the effect size?
Dr. Chapman calculated t = 3.57 with α = .01, df = 5, and tcv = ±4.032. Because the calculated value was less extreme than the critical value, he should make this decision.
What is fail to reject (retain) the null hypothesis?
In the phrase "between-subjects, one-way ANOVA," this specific term indicates that independent samples were analyzed.
What is "between-subjects"?
If a researcher violates the random samples assumption in a one-way, repeated-measures ANOVA, this would be the major concern about the results.
What is the results may not generalize to the larger population (limited external validity)?
Using the F table with 3 groups and 6 total cases (numerator df = 2, denominator df = 3) at α = .05, Fcv equals this value.
What is 9.55?
Dr. Aron tested 27 dogs on a thunderstorm anxiety medication. Results: t(26) = 2.25, p < .05 and 95% CIμDiff = [8.20, 10.37]. The dependent variable ranged from 5 to 35 minutes. Given these results, the study can be said to have this/these type(s) of significance.
What is both statistical significance and practical significance? (p < .05 confirms statistical significance; the 8–10 minute effect on a 30-minute range suggests practical significance as well.)