Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
21 Cards in this Set
- Front
- Back
Bonferroni Correction
|
- Corrected level of significance when performing multiple comparisons (simple effects)
- .05/number of tests |
|
3 Decimal Places
|
- P values
- R values - Partial n2 values |
|
Reporting T-test Results
|
- t value, p value, 95% Confidence Interval
- Cohens d (effect size) |
|
Reporting One-Way ANOVA Results
|
- Significance: f value, p value
- Partial n2 (effect size) + variance explained (%) - Post hoc test: p and d values for each comparison |
|
Reporting Two-Way ANOVA Results
|
For both Main Effects and Interaction:
- Significance: f value, p value - Partial n2 (effect size) - Post hoc test: p values |
|
Reporting Correlation Results
|
> Pearsons r + p value
> Strength of relationship (weak/moderate/strong) > Percentage of shared variance* |
|
Reporting Simple Effects
|
- Number and type used
- Bonferroni adjusted criterion - t-test results + cohens d |
|
Reporting Linear Regression
|
- R2 (squared)
- ANOVA Result: F + p - Slope + 95% CI |
|
Reporting Multiple Linear Regression
|
- Variance explained % = (R2*100)
- ANOVA Result: F + p - T statistics for each predictor - Slope + 95% CI - Most influential predictor (based on Beta) |
|
Confounding Variable
|
- Hidden extraneous variable
- Correlates with IV and DV - Can cause us to see a causal relationship where there is none |
|
Quasi-Experiment
|
- Unable to randomly allocate participants to conditions
- e.g. age or gender |
|
Kurtosis
|
- Peakedness of population distribution
- i.e. steep or flat |
|
Skewness
|
- Asymmetry of a probability distribution
- i.e. how far left/right distribution is from centre (mean) - Negative = Right - Positive = Left |
|
Interval Scale
|
- True numerical relationships
- Equal intervals - No true zero point - e.g. Temperature |
|
Nominal Scale
|
- No numerical relationship
- Categorical - e.g. Gender, Ethnicity, Job |
|
Ordinal Scale
|
- Data organised by rank
- True numerical relationships - BUT intervals between values not equal - e.g. Likert Scale |
|
Ratio Scale
|
- True numerical relationships
- Equal intervals - True zero point - e.g. Speed |
|
Type 1 Error
|
- Reject null hypothesis when it is in fact TRUE
- Believing there's a relationship when there isn't |
|
Type 2 Error
|
- Fail to reject null hypothesis when it is in fact FALSE
- Believing there's no relationship when there is |
|
Residual Variance
|
- Variance not explained by regression line
- Distance between each data point and the regression line - SSr |
|
Total Variance
|
- Linear regression
- Variance not explained by the mean - Distance between each data point and the mean (horizontal line: simplest model) - SSt |