Term
|
Definition
| Hypothesis that 2 or more groups differ with respect to measures on a variable |
|
|
Term
| Choosing the right statistic depends on: |
|
Definition
- Type of measurement
- Nature of comparison
- # of groups to be compared |
|
|
Term
| Cross-tabulation tables: x2 test for goodness-of-fit |
|
Definition
x2 test tests the statistical significance of a contingency table
- Compares observed frequencies with expected frequencies
- Goodness-of-fit of observed distribution with expected distribution |
|
|
Term
|
Definition
- Used for nominal, ordinal, and transformed interval variables
- Difficult to interpret when a variable has 5+ categories |
|
|
Term
|
Definition
One variable
- ex) Papa John's restaurants are more likely to be located in stand-alone location or in a shopping center |
|
|
Term
|
Definition
2 variables
- ex) stand-alone locations are more likely to be profitable than shopping center locations |
|
|
Term
| 2 steps to testing the hypothesis |
|
Definition
1) examine the statistical significance of the observed contingency table
2) examine whether the differences between the observed and expected values are consistent with the hypothesized prediction |
|
|
Term
| Independent samples t-test |
|
Definition
- tests difference between means taken from 2 independent samples
- tests if the differences between the two means is 0 |
|
|
Term
| Standard error of a t-test |
|
Definition
| Estimate of the standard error for a t-test of independent means that assumes the variances of both groups are equal |
|
|
Term
|
Definition
- Use for samples < 30
- t-test and z-test yield similar results as sample size increases |
|
|
Term
|
Definition
- Compares scores of 2 interval variables from related populations
- Used when means need to be compared that are not from independent samples |
|
|
Term
| z-test for comparing 2 proportions |
|
Definition
- Tests the hypothesis that proportions are significantly different for 2 independent samples
- Must use sample size > 30 |
|
|
Term
| One-way analysis of variance (ANOVA) |
|
Definition
- One way = one independent variable
- Analysis that investigates the effects of 1 treatment variable on an interval-scaled dependent variable |
|
|
Term
| ANOVA hypothesis tested is: |
|
Definition
| - At least one group mean is not equal to another group mean |
|
|
Term
| Dividing variance in ANOVA |
|
Definition
Total variability
- Grand mean: mean of a variable over all observations
- ASK CAILEY |
|
|
Term
| Dividing variance in ANOVA |
|
Definition
Total variability
- Grand mean: mean of a variable over all observations
- ASK CAILEY |
|
|
Term
|
Definition
| - Sum of differences between the group mean and the grand mean summed over all groups for a given set of observations |
|
|
Term
| Within-group error or variance |
|
Definition
- Sum of differences between observed values and the group mean for a given set of observations
- AKA total error variance |
|
|
Term
|
Definition
- Test statistic for ANOVA
- Used to determine whether there is more variability in the scores of one sample than in the scores of another sample
- Variance components are used to compute F-ratios |
|
|
Term
|
Definition
| - Way of modeling how different IVs cause fluctuations in DV |
|
|
Term
|
Definition
- Type of general linear model
- Best fit line |
|
|
Term
|
Definition
|
|
Term
| How to interpret a multiple regression model |
|
Definition
1) examine f-test for significance
2) examine individual statistical tests for each IV for significance
3) examine the model's R^2
4) diagnose multicollinearity |
|
|
Term
|
Definition
A case of multiple regression in which the predictor variables are themselves highly correlated.
- AKA extent to which IVs are correlated
- Variance inflation factors between 1 and 2 are okay |
|
|
