Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
psy400ch14p333
Analyzing Your Data II: Specific Approaches
| Term | Definition |
|---|---|
| computerized adaptive testing, or CAT, adjusts the level of questions in response to | the estimated ability of the person taking the test; saves time and maintains measurement precision. |
| Make sure you get the first bunch of questions correct if | you're taking an adaptive test |
| NHST | Null Hypothesis Significance Testing |
| Analysis of variance (ANOVA): A statistical technique to test | for differences among means |
| Parametric statistical test: requires data to he interval or ratio level and have a mean and standard deviation | makes strong assumptions about the distribution of measurements in the population (t test or ANOVA) |
| Nonparametric statistical tests: make few assumptions about the distribution of measurements in the population and | does not require data to be interval or ratio level |
| t test, one sample | compares the mean of a single sample to a specified value |
| Wilcoxon signed-rank test | A nonparametric alternative to the one-sample or matched-pairs t tests |
| Nonparametric alternative one sample to t test | one sample Wilcoxon signed rank test |
| Degrees of freedom (df) | The number of values that are free to vary in the computation of a statistic |
| For a one-sample t test, there are | n — 1 degrees of freedom |
| t test, independent samples | for comparing the means of two independent samples |
| t test, independent samples Assumptions: | Interval- or ratio-level data. Random sampling and independence of observations/cases. The two populations are normally distributed and have equal variances. |
| Welch's t test | an independent-samplest t test that takes into account unequal variances between the two groups |
| Mann-Whitney U test or Wilcoxon rank-sum test | A nonparametric alternative to the independent-samples t test. |
| t test, matched pairs | compares the means of two matched samples (two measurements from the same participants or participants matched on some criteria (e.g., academic achievement) |
| Matched-Pairs t Test Assumptions: | Interval- or ratio-level data. Random sampling, Independent observations (between cases, not within). Difference scores are normally distributed. |
| Matched-Pairs t Test Nonparametric alternative | Wilcoxon signed-rank test |
| One-way analysis of variance (ANOVA) | tests for differences of means on a single factor. |
| If we wish to compare the means for three or more samples on a single factor, then | we employ one-way analysis of variance (ANOVA) |
| Independent-Groups One-Way ANOVA (Between Subjects) Assumptions: | Interval- or ratio-level data; Random sampling and independence of observations. populations normally distributed, homogeneity of variance |
| Kruskal-Wallis test | A nonparametric alternative to one-way analysis of variance. |
| ANOVA table | organizes and displays the results of analysis of variance |
| Sums of squares | measures the amount of variability in data, including between-subjects, within-subjects, and total sums of squares |
| The between-subjects sum of squares shows the extent to which | the group means deviate from the overall mean |
| The within-subjects sum of squares indicates the extent to which | each data point deviates from its group mean |
| Each mean square value is computed by dividing | the corresponding sum of squares by its associated degrees of freedom |
| Each mean square value | is an estimate of the population variance |
| If the between-subjects mean square is considerably larger than the within-subjects mean square, | this is evidence that the population means differ from one another |
Created by:
james22222222