Search
Create
Log in
Sign up
Log in
Sign up
STats part 3
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Terms in this set (23)
Correlation
measures/describes a relationship between two variables-- not causation
What three characteristics of a relationship does the correlation describe?
Direction (positive vs negative, linear), Form (nonlinear/shape), Strength/consistency
Correlation coefficient
statistic that expresses the direction and strength between two variables (ranges from r= -1.00 to 1.00)
Pearson r
parametric, measures the degree and direction of linear relationship
covariability/covariance
variance between two variables
coefficient of determination
proportion of variability in one variable that can be determined form the relationship with the other variable (similar to omega-- variance explained)
Spearman r
nonparametric, for nonlinear relationships, measures the correlation of the ranks
Regression
standardized method for determining the equation for the line of best fit-- equation of the correlation, y=bX +a
total squared error
squared average of the deviation from each point to the line
standard error of estimate
measure of the standard distance between the regression line and actual data points
What can lead to misleading correlations?
nonlinear relationship, truncated range, small n size, outliers, multiple populations
nonparametric tests
used when parameter assumptions are violated or when DV variables are nominal/ordinal, have less power
Parameter assumptions
scalar data (interval/ratio), independent observations, drawn from normal populations, homogeneity of variance
Mann-U
2 sample independent measures test, used instead of an independent measures t test
Wilcoxon
1 sample repeated measures test, used instead of a repeated measures t test
-find differences in scores--> ranked
Kruskal-Wallis
single factor independent measures test, used instead of one-way ANOVA.
if significant--> follow up Mann-U
chi-square statistic
evaluates sample frequencies and proportions for nominal data
χ² test for goodness of fit
tests how well sample distributions/proportions fit a population model, used instead of 1-way independent measures ANOVA (ex. difference in preferences). sum of (observed-expected)^2 divided by expected
The larger the χ² value... ?
the more likely it is to be significant
observed frequencies
number of individuals from a sample who are classified in a particular category
expected frequencies
define the hypothetical sample distribution that would be obtained if the sample proportions were in perfect agreement with those specified in H0
Assumptions about χ² goodness of fit
mutually exclusive groups, independence of observations, more than 5 subjects
χ² test for independence
compares two or more observed proportions, instead of 2-way independent measures ANOVA
YOU MIGHT ALSO LIKE...
Essentials of Business Research | Silver, Stevens, Kernek, Wrenn, Loudon
AcademicMediaPremium
$9.99
STUDY GUIDE
Statistics Terms
75 Terms
magreen
Combo with "Chp 11" and 1 other
85 Terms
jbecca
Psych 302 Final
188 Terms
melflores18
OTHER SETS BY THIS CREATOR
palabras de amnistia
59 Terms
ilyxoxemily
Español
364 Terms
ilyxoxemily
Psych Dara Final
126 Terms
ilyxoxemily
stats midterm 2 (kill me)
35 Terms
ilyxoxemily
;