Download Exam 4 | PSY-K 300 - STATISTICAL TECHNIQUES and more Quizzes Psychology in PDF only on Docsity!
Analysis of Variance
an inferential tool that we use to test for statistically significant differences among the means of 3+ populations TERM 2
Single-factor ANOVA
DEFINITION 2 the statistical analysis appropriate when we are analyizing the results of an experiment in which we have one factor and are looking for difference in the response variable among 3+ groups, each of which is receiving different "levels" or amounts of the factor. TERM 3
Between-Groups Variance
DEFINITION 3 indicates the size of the difference between sample means and the grand mean (mean of all scores/mean of all sample means). TERM 4
Within-Groups Variance
DEFINITION 4 shows how much individual scores vary within the sample collected. TERM 5
Non-directional Hypothesis
DEFINITION 5 all ANOVA alternative hypotheses ask whether there is a difference between 2 or more groups. We can't specify directional hypotheses for 2 or more groups, so all ANOVA hypotheses are non-directional.
Critical Value (of
F)
tells us how many times greater the BG variance must be compared to the WG variance before we conclude that the samples are drawn from different populations. TERM 7
Alpha
DEFINITION 7 tells us how unlikely (rare) the ratio of BG variance/WG variance must be before we will reject the null hypothesis. TERM 8
Calculated Value (of
F)
DEFINITION 8 Fcalc tells us how many times greater BG variance is compared to WG variance for the data in our current study. TERM 9
F-distribution
DEFINITION 9 shows the values of Fcalc you get if you repeatedly draw many samples from one particular population and calculate Fcalc ofr those samples. So, these are the values of Fcalc we would expect if the null hypothesis was true. TERM 10
Grand Mean
DEFINITION 10 mean of all scores.
Factor
the variable hypothesized to 'cause' something to happen. TERM 17
Response Variable
DEFINITION 17 what we are measuring to see if there is a difference between groups; it's the variable we believe will be affected (changed) by the factor(s). TERM 18
Main Effect
DEFINITION 18 the effect of a single factor on the response variable. TERM 19
Interaction
DEFINITION 19 when the effect of one factor depends on the other factor. TERM 20
Level
DEFINITION 20 refers to the categories of a factor represented in our experiment.
Experimental Design
Notation
reflects "levels of factor A" x "levels of factor B" TERM 22
Row Means
DEFINITION 22 the mean across the row. TERM 23
Column Means
DEFINITION 23 the means down each column. TERM 24
Cell means
DEFINITION 24 the individual scores. TERM 25
Parametric Inferential Statistical Tests
DEFINITION 25 inferential tests about the values of a parameter (such as ) conducted using information from a sample (we use sample mean to make an inference about populations). It includes all types of t-tests and ANOVA. It has assumptions about other parameters: such as variance must be similar across groups, data must be distributed normally.
Observed Frequencies
the actual response found in the data. TERM 32
Degree (strength) of correlation
coefficient
DEFINITION 32 The value of r (ignoring the sign) indicates the strength of relationship: strong, weak, absent. (-1.00 to 1.00) TERM 33
Causation vs. Correlation
DEFINITION 33 Causation is a relationship for which we have established that X causes Y. Correlation is a relationship in which we have established that X and Y are related... if we know one we can predict the other, but we cannot conclude that one variable causes the other. TERM 34
Mysterious 3rd variable
DEFINITION 34 when a variable (z) might affect 2 variables of interest (x and y) in a way that causes x and y to appear to be genuinely related when the association is merely artificial. TERM 35
Coefficient of determination
DEFINITION 35 r2 is a measure of the contribution of X predicting Y. It is an indicator of the strength of the relationship between X and Y values.
Mann-Whitney U
Use for nonparametric tests: single sample compared to test value two-independent samples TERM 37
Wilcoxon
DEFINITION 37 Non-parametric test for: two-dependent samples TERM 38
Kruskal-Wallis
DEFINITION 38 Non-parametric test for: single factor ANOVA multiple factor ANOVA TERM 39
Correlation Coefficient
DEFINITION 39 (r) describes the direction & strength of relationship between 2 variables. TERM 40
Positive Correlation
DEFINITION 40 if 2 variables are positively related if x is high, y is high vice versa
