Parametric/Inferential Statistics
What "ANOVA" stands for.
What is "Analysis of Variance"?
This theorem states that the distribution of sample means will be approximately normal if the sample is large enough.
What is the Central Limit Theorem?
A non-parametric statistic for testing differences between the means of two unrelated samples.
Mann-Whitney U test.
A researcher is interested in comparing the performance of two groups of participants in a naming task, with 10 people in each group. The best statistic to use to compare the performance of these two groups is this.
What is a t-test?
When your ANOVA has a significant effects, you do this next, to determine where the difference might be.
What is a post-hoc test? (Or, any of the following: Bonferroni, Tukey, Newman-Keuls)
This type of test can be used with continuous, interval or ratio-level data.
What is ANOVA?
This is a distribution that contains scores that are expressed in standardized (z) scores.
What is the Standard Normal Distribution?
The nonparametric alternative to the one-way analysis of variance.
Kruskal-Wallis Test
If a research question asks, "Is an observed difference between two conditions within the same subjects attributable to chance?" (aka paired data, or repeated measures), you can use this type of analysis to test the means.
What is the t-test for related samples?
When a researcher has more than two groups or conditions, they use this kind of statistical analysis.
The ANOVA.
The outcome of an ANOVA is this type of statistic.
What is the F statistic?
This type of score might be helpful when comparing measures of varying scales (e.g. scores with a mean of 100 and a sd of 15 to scores with a mean of 10 and a sd of 3) or from different tests (e.g. the PPVT and the TACL).
Z-Scores
Chi-squared tests can be done with this kind of data.
What are categorical or nominal data?
To determine if there is a practical difference in a result, a researcher might report this.
What is an effect size?
You can use this to determine an effect size when you have a small sample (20 participants or fewer).
What is the Hedge's g?
This type of test requires an n<30
What is the Student's T-Test?
This is a measure of peakedness of a distribution.
What is kurtosis?
This is the most common type of effect size reported in both ANOVA and chi-squared results.
What is Cohen's d?
If you have an n < 30, you can use this particular distribution when conducting your comparisons.
What is the Student's t distribution?
This is a quantitative measure of the magnitude of some phenomenon, such as the magnitude of the difference between two means.
What is the effect size?
This type of analysis usually requires an n>30.
What is ANOVA or Z-test
The following are true for what kind of statistical assumption?
- It is unimodal
- It is symmetrical
- it is continuous
- it is asymptotic
What is the normal distribution?
This is the purpose of the chi-squared test.
What is to determine whether the observed frequencies (or counts) differ significantly from the frequencies expected by chance.
Four assumptions that must be met in order to use the Student's t-test.
What are:
1. Subjects are independently and randomly sampled.
2. The two groups are independent and unrelated.
3. The variance between the means must be normally distributed.
4. The groups need to have near-equal variances (reported via the F statistic.)
A study reported the change in opinion (how the participants felt) within one group in a pre- and post-intervention study. This type of test was probably used to analyze the results.
Chi-Squared test?