click below
click below
Normal Size Small Size show me how
Quant Exam 2
| Question | Answer |
|---|---|
| Test Used To Compare The Means Of Two Groups | independent sample t-test |
| Null Of Independent Samples T-Test | means of the two populations are the same |
| Statistical Hypothesis Of Independent Samples T-Test | M1 - M2 = 0 |
| Assumptions Of Independent Samples T-Test | normality, independence, homogeneity of variance |
| Pooled Standard Deviation | combines the standard deviations of two or more independent groups into one weighted average estimate |
| To Estimate Standard Deviation, We Divide By... | N-1 |
| When We Have Two Distributions, Our Standard Error For The Difference Of The Means Will Be... | the sum of the standard error |
| For Each Estimated Mean, We Lose A... | degree of freedom (2 means, N-2) |
| Standard Effect Size Interpretations For Independent Samples T-Test | large=.8, moderate=.5, small=.2 |
| Our Alpha In Psychology Is... | 0.05 |
| When "t" Is Greater Than Our Critical Value, Our Result Is... | significant |
| Leven's Test Is Used To Check... | homogeneity of variance |
| Steps For Independent Samples T-Test | 1) calculate weights for pooled sd // 2) calculate pooled sd // 3) calculate the standard error of the difference // 4) calculate the t-value |
| ANOVA Stands For... | analysis of variance |
| Variance | the spread of your distribution (standard deviation squared) |
| The More Spread, The Less Likely You Are To Find... | a statistically significant result |
| Grand Mean | the average of all individual data points across multiple groups, samples, or subsamples (the mean of all the scores in a study) |
| The Test Statistic For An ANOVA Is The... | F-Statistic |
| One-Way ANOVA F-Statistic | between group variability / within-group variability |
| One-Way ANOVA Table Includes... | sum of squares, degrees of freedom, variance estimate (mean square), F ratio |
| There Is Just One Critical Value For A... | one-way ANOVA (right tail of distribution) |
| Sum Of Squares | a total of squared deviations |
| Between-Group Sum Of Squares Measures... | how much group means differ from the overall grand mean |
| Within-Group Sum Of Squares Measures... | how much individual data points vary around their own group means |
| Between-Group Degrees Of Freedom | G-1 |
| Within-Group Degrees Of Freedom | N-G |
| Total Degrees Of Freedom | N-1 |
| We Calculate Mean Squares For Between-Groups & Within-Groups, But Not For... | the total |
| P-Value Is Obtained With A... | calculator |
| Effect Size Values For An ANOVA? | small: 0.02 // medium: 0.13 // large 0.26 |
| Running Multiple Independent Samples T-Tests Could Inflate Your... | type 1 error |
| Post-Hoc Pairwise Comparison Options | Tukey's HSD & Bonferroni |
| The Post-Hoc Pairwise Comparison That May Increase Type 2 Error Is... | Bonferroni |
| Assumptions Of The One-Way ANOVA | homogeneity of variance, independence, normality of residuals |
| ... | ... |
| Normality Assumption Definition | each of our distributions is normal |
| Independence Assumption Definition | each observation is independent from one another |
| Homogeneity Of Variance Assumption Definition | the standard deviations & variances of our populations are the same (homoscedasticity) |
| Normality Of Residuals Assumption Definition | each group observation should be normally distributed (residuals = within-subject variance) |
| We Will Most Often Use Bar Graphs To Represent Findings From... | z-tests, t-tests, & one-way ANOVAs |
| Standard Error Bars | lines on a bar graph that show measurement uncertainty |
| If The Standard Error Bars Overlap, The Results Are... | likely not statistically significant, but you can't know for sure!!! |
| If The Standard Error Bars Do Not Overlap, The Results Are... | inconclusive (can't tell statistical significance from SE bars) |
| Assumptions For Factorial ANOVAs | homogeneity of variance, normality of residuals, independence |
| The Test We Use When We Want To Test The Effect Of Two Or More Categorical IVs (Factors) On A Single Continuous DV Is... | a factorial ANOVA |
| The Test We Use When We Want To Compare The Means Of Three Or More Independent Groups Based On ONE Categorical Independent Variable Is... | a one-way ANOVA |
| The Test We Use When We Want To Determine Whether The Mean Of A Single Sample Is Significantly Different From An UNKNOWN Population Mean Is... | a one-sample t-test |
| The Test We Use When We Want To Determine Whether The Mean Of A Single Sample Is Significantly Different From An KNOWN Population Mean Is... | a one-sample z-test |
| In A Factorial ANOVA, Each Of The Independent Variables Is Called... | a factor |
| Interaction In An ANOVA | when the effect of a variable on the DV depends on the other variable (lines on a graph will not be parallel) |
| Main Effect In ANOVAs | the overall effect of a single independent variable (factor) on a dependent variable, averaged across all levels of any other independent variables |
| The Number Of Independent Variables Is The Same As The Number Of Main Effects | *** |
| The Test We Use When All Participants Are Tested In Both Experimental Conditions Is... | the paired samples t-test |
| The Test We Use The Estimated Standard Deviation Of The Difference For Is... | the paired samples t-test |
| The Degrees Of Freedom For The Paired Samples T-Test Is... | N-1 (we lose 1 degree of freedom) |
| Assumptions Of The Paired Samples T-Test | normality, independence of pairs |
| Independence Assumption In The Paired Samples T-Test | observations in condition 1 are not independent from observations in condition 2, because they are provided by the same participant (less strict) |
| A Very Small P-Value Can Be Written As | p < 0.001 |
| Count The Pairs Formula | G(G-1) / 2 |
| Family Wise Error Rate | the chance of making at least one type 1 error |
| Needs For One-Way ANOVA | one categorical IV with 3+ levels, different people in each group, a continuous DV |
| Between-Group Variance | how far the group means are from each other (from the grand mean) |
| Within-Group Variance | how much scores vary inside each group (noise) |
| Mean Square | an sum of squares divided by its degrees of freedom, which makes it a variance |
| F-Ratio | mean squares between / mean squares within |
| Grand Mean For Equal Group Sizes | it's the average of the group means |
| "k" Variable | current group we are calculating |
| "Nk" Variable | number of observations for CURRENT group |
| "G" Variable | total number of groups |
| F Distribution | the sampling distribution of F when the null is true // its shape depends of two degrees of freedom (between & within) // it is never negative & it's right skewed |
| Omnibus Test | an overall test of whether ANY difference exists among the groups, without saying where (ex: ANOVA F) |
| Post Hoc Test Definition | a follow-up test, run after a significant F, that compares pairs of groups while controlling the familywise error rate |
| Tukey's HSD Definition | the standard post hoc test for comparing every pair of means |
| Eta-Squared Definition | a statistical measure of effect size that tells you the proportion of total variance in a dependent variable that is explained by an independent variable (ranges from 0 to 1) |
| Effect Size Values For Eta-Squared | small = 0.01, medium = 0.06, large = 0.14 |
| How To Report Results | 1) state test // 2) give each group's mean & sd // 3) provide F with both degrees of freedom // 4) give p & eta-squared // 5) state post hoc results // 5) give a plain-language conclusion |
| Needs For Factorial ANOVA | two or more categorical IVs, one continuous DV |
| How To Label A Design | number of factors = number of numbers // that factor's levels = each number |
| How To Find The Number Of Groups/Cells | multiply each number (a 2 x 2 design will have 4 groups) |