Study your flashcards anywhere!

Download the official Cram app for free >

  • Shuffle
    Toggle On
    Toggle Off
  • Alphabetize
    Toggle On
    Toggle Off
  • Front First
    Toggle On
    Toggle Off
  • Both Sides
    Toggle On
    Toggle Off
  • Read
    Toggle On
    Toggle Off
Reading...
Front

How to study your flashcards.

Right/Left arrow keys: Navigate between flashcards.right arrow keyleft arrow key

Up/Down arrow keys: Flip the card between the front and back.down keyup key

H key: Show hint (3rd side).h key

A key: Read text to speech.a key

image

Play button

image

Play button

image

Progress

1/40

Click to flip

40 Cards in this Set

  • Front
  • Back
Dependent means/groups
Association or link in the research design between the sets of scores. Usually occurs in one of three conditions - repeated measures, linked selection, or matching.
Repeated Measures
Repeated measures designs collect data on subjects using the same measure on at least two occasions. This often occurs before and after a treatment or when the same research subjects are exposed to two different experimental conditions.
Linked Selection
When selection is with the intent to analyze the data together (e.g. parent-child, partners)
Subject matching
When you want to control for something (e.g. socioeconomic differences in research subjects). You match on the variable and the scores on the dependent variables are then treated as a pair in the statistical test.
Statistics for dependent means
McNemar Test (two samples or times of measurement), Wilcoxon t Test (two samples), Dependent Means t Test (two samples), Friedman ANOVA for Ranks (three or more samples), Simple Repeated Measures ANOVA (three or more samples), and Mixed Factorial ANOVA (at least one factor is linked/correlated).
Independent means/groups
No subject overlap across group (can the person be in both groups? e.g. gender)
Statistics for Independent Means
chi-square test of independence (two or more groups), Mann-Whitney U Test (two groups), Independent Means t test (two groups), One-Way Between-Groups ANOVA (three or more groups), and Factorial ANOVA (two or more independent variables).
Nominal Data
McNemar – two sample/dependent
Chi-Squares – all others
Nominal – one sample
Dependent variable
Chi goodness of fit
Nominal –one sample
DV & IV
Chi test of independence
Nominal – two samples
Independent Groups
Chi test of independence
Nominal – two samples
Dependent Groups
McNemar
Ordinal data- one sample
DV & IV
Spearman’s r’s
Ordinal Data – multiple samples
Independent Samples
Two samples
Mann-Whitney U
Ordinal Data – multiple samples
Independent Samples
3+ samples
Kruskal Wallis H
Ordinal Data – multiple samples
Dependent samples
Two samples
Wilcoxon T
Ordinal Data – multiple samples
Dependent samples
3+ samples
Friedman Anova by Ranks
Scale Data
Includes approximate interval, interval and ratio
-group differences or associations between independent and dependent variables
Scale data – one sample
Dependent variable
Known population sd
Z test
Scale data – one sample
Dependent variable
Known population mean
One-sample t-test
Scale data – one sample
(1) IV & DV
Pearsons r
Bivariate regression
Scale data – one sample
Mulitple IVs & DVs
Multiple Regression
Scale Data Multiple Samples
Independent Samples
Two Samples
Independent t-test
Scale Data Multiple Samples
Independent Samples
Three Samples
One-way ANOVA
Factorial ANOVA
Scale Data Multiple Samples
Dependent Samples
Two Samples
Dependent t-test
Scale Data Multiple Samples
Dependent Samples
Three Samples
Repeated Measures ANOVA
Mixed Factorial ANOVA
Parametric Assumptions
Kolmogorov-Smirnov Test
used to determine how likely it is that a sample came from a population that is normally distributed.
Parametric Assumptions
Levene test
used to test the assumption of equal variances
Parametric Assumptions
A) Interval, ration, approximate interval scale
B) random sampling from a defined population
C) Characteristic is normally distributed in the population
D) Population variance is equal (if two or more groups/variables)
Violated parametric test assumptions
A) transform data
B) Use non-parametric statistic
Parameter
A value, usually numeric, characteristic of a population
Mu – mean
Sigma – standard deviation
Sigma square – variance
Parametric tests assume:
A) populations from which samples are drawn have specific characteristics
B) samples are drawn under certain conditions.
Nonparametric tests assume:
A) sampling (random)
B) independence or dependence of samples (varies by test) but make no assumptions about the population.
one-sample tests
Z test; t test; Pearson and Spearman correlations; chi-square goodness-of-fit
Two- sample tests
("samples" for any statistic that examines differences between groups t test for dependent means)
t test for independent means; one-way ANOVA; Friedman ANOVA; chi-square test of independence
Type I Error
Rejecting the null when it is true
Alpha
Usually with one-tailed test
Type II Error
Rejecting the alternative hypothesis (fails to reject the null hypothesis) when the alternative hypothesis is true.
Beta
Power of test
1 minus beta
Opposite of type 2 error
increased by increase sample size, alpha, effect magnitude, decreasing random error, use parametric and one-tailed tests.
1-B (inverse of Beta)
Increasing Power
A) Increasing alpha, decreases beta and increases power
B) sample size
C) effect size
D) directional –one tailed are more powerful
Effect size
The degree of distance between the null hypothesis and alternative hypothesis distributions. The larger the effect size, the easier it is to detect a true difference between the two population means. The effect size is the only factor that influences power that is not under the investigator's control. We estimate the effect size (anticipated difference between our null hypothesis and alternative hypothesis) from the literature.