t-Tests
In Scenario 1, this is an appropriate one-tailed research question.
Do first generation students have less knowledge about resources available on campus than non-first generation students?
In Scenario 2 (Stroop task), this F-value, p-value, and effect size were reported. (Round to two numbers)
What is F(2,68) = 5.86, p = .01, η² = .11?
In Scenario 7, this test correction was recommended when the chi-square assumption was violated.
What is Fisher's exact test?
In Scenario 4, this correlation coefficient and p-value were reported between course satisfaction and difficulty. (Round to two decimals)
What is rs(34) = .01, p = .53?
This test assumption is needed for both independent and paired samples t-tests but not for non-parametric tests.
What is normality?
In Scenario 1, this assumption (name the test) must be checked to determine if there is equal variance between the two groups.
What is Levene's test for homogeneity of variance?
In Scenario 5 (pop quiz reactions), this F-value and p-value were reported for academic self-efficacy. (Round to two numbers)
What is F(2,32) = 1.07, p = .36?
This p-value was reported with Fisher's exact test in Scenario 7 examining first-generation status and pop quiz reactions.
What is p = .57?
In Scenario 6, this correlation coefficient and p-value were reported between self-efficacy and resource knowledge. (Round to two decimals)
What is r(33) = -.11, p = .73?
The difference between Type I and Type II errors in hypothesis testing is this.
What is "Type I is rejecting a true null; Type II is failing to reject a false null"?
In Scenario 3 about the meme intervention, this was the effect type and size (number) reported.
What is Cohen's d = -0.31?
This post-hoc comparison in the Stroop task scenario was the only one that was statistically significant.
What is "silence versus classical music"?
In Scenario 8, this chi-square value and p-value were reported when comparing the sample's first-generation proportion to Fresno State's. (Round to two decimals)
What is χ²(1, N=35) = 0.74, p = .39?
The non-significant correlation between course satisfaction and difficulty in Scenario 4 indicates this possible type of error.
What is Type II error?
When interpreting effect sizes, this value of Cohen's d (0.62) and this value of eta squared (0.11) indicate the same strength of effect.
What is "medium effect size"?
In Scenario 1, this t-value, p-value, and degrees of freedom are the statistical notation for the research question: Do first generation students have less knowledge about resources available on campus than non-first generation students? (Round to two decimals)
What is t(33) = 1.81, p = .04?
The Q-Q plot in Scenario 2 (Stroop task) and Mauchley's test of Sphericity indicated this about assumptions.
What is "normality and sphericity assumptions were met"?
In Scenario 7, this specific chi-square assumption was violated, requiring the use of Fisher's exact test.
What is "expected cell frequencies greater than 5"?
In Scenario 6, this confidence interval for the correlation between self-efficacy and resources was reported.
What is CI₉₅ = [-.38, 1.00]?
The negative t-value in Scenario 3 (t = -1.82) and the positive F-value in Scenario 2 (F = 5.86) both led to this same conclusion.
What is "reject the null hypothesis" (or "statistically significant result")?
In Scenario 3, this t-value, p-value, and degrees of freedom are the statistical notation for the alternative hypothesis: Students will score higher on a statistics test after a meme intervention than they did before the intervention. (Round to two decimals)
What is t(34) = -1.82, p=.04?
In Scenario 5, this is why no post hoc test was necessary for the ANOVA comparing academic self-efficacy across pop quiz reaction groups.
What is "the F-test was not significant" (or "p = .36, greater than .05")?
In Scenario 8, these are the frequencies being compared.
In Scenario 4, this type of correlation was used because the variables were measured at this level.
What is "Spearman's correlation; ordinal variables"?
Across all statistical tests, this statistical significance level determines whether our p-value indicates rejecting or failing to reject the null hypothesis.
What is alpha?