Title | Psyc 305 tests - Final Review |
---|---|
Author | Tiny Roland |
Course | Statistics for Experimental Design |
Institution | McGill University |
Pages | 7 |
File Size | 263.6 KB |
File Type | |
Total Downloads | 98 |
Total Views | 143 |
Download Psyc 305 tests - Final Review PDF
Test
Use
Variable used
Assumptions
Statistic/result
Z Test
Comparing a group Binary variable mean to a demonstrating hypothesis group membership
Z score: follows normal distribution. Critical value at 0.05 is abs. value 1.96. If abs. z score is greater than 1.96, reject H0
T test (about 1 mean)
Comparing population mean to sample mean. Similar means = population will have same response to treatment Two unknown population means are different based on their samples.
t-distribution changes with sample size (DF), CV not always 1.96. compare tstatistic to CV. If >CV, reject H0. OR P-val Because assumptions fulfilled, only parameter that can change is group means.
T test (about 2 means)
- Normal distribution of population - σ and µ of population must be known - Sample must be chosen randomly Binary variable - Normal demonstrating distribution of group population membership - Mean of population taken from H0 - Random sample Binary variable - both demonstrating populations group follow ND membership - homogeneity of variance (SD) σ - Random sample
Effect Size Measure
Pearson’s Correlation Coefficient (r)
Pearson’s Correlation Coefficient (r)
Limitations Degrees of OR in SPSS freedom LIM: Knowing df=1 σ and µ is unlikely in large populations Unit dependent (scale invariant) df=1
LIM: ≤ 2 means
df=1
Test
Use
Variable used
One-Way ANOVA (Independent)
≥ 2 means
Analysis of variance: IV = factor. Has many levels or categories. Treatment levels.
One-Way ANOVA (Repeated)
N subjects are measured on a single DV under K conditions or levels of a factor.
Analysis of variance between DVs across treatment levels. Testing for significant differences across subjects.
Assumptions
Statistic/result
- Indep. of observations in each group - All groups have equal variance in pop - groups follow ND
VB: Between groups variance VW: Within groups variance F Statistic= (VB/ VW) If >CV, reject H0. Also look at p-val (...