Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
65 Cards in this Set
- Front
- Back
|
nominal scale
|
labels observations so that they fall into different categories; no rank or order
|
|
|
ordinal scale
|
the categories have separate names and are also ranked in terms of magnitude; rank and order apply
|
|
|
interval scale
|
consists of an ordered set of categories with equal intervals between points on the scale; addition and subtraction is possible, but multiplication and division are not
|
|
|
ratio scale
|
an interval scale with the additional feature of an absolute zero; addition, subtraction, multiplication, and division
|
|
|
error variance
|
variance not due to the IV
|
|
|
independent events
|
occurrence is not correlated with the occurrence of another event
|
|
|
central limit theorem
|
as the size of samples from the population approach infinity, the distribution of the means of those samples gets to be more and more normal
|
|
|
family-wise type I error rate
|
when there are multiple comparisons, the probability of making at least one type I error
|
|
|
per-comparison error rate
|
probability of error for each indivudal analysis
|
|
|
within group variance
|
sampling error
|
|
|
between group variance
|
chance + IV
|
|
|
omega squared
|
ω-squared; estimate of effect size in population
|
|
|
analysis of main effects
|
looking at whether or not the IV is significant
|
|
|
analysis of main comparisons
|
looking at levels of IV for an analysis; Tukey
|
|
|
analysis of simple effects
|
computed to determine a significant interaction; manipulating one variable and holding all others constant; Tukey
|
|
|
analysis of simple comparisons
|
comparing every combination of the IVs with every other cominations of IVs; Tukey
|
|
|
orthogonal
|
planned contrast; uncorrelated
|
|
|
post hoc test
|
posttests that are unplanned and occur after the analysis
|
|
|
a posteriori comparisons
|
unplanned; performed after omnibus f test is completed
|
|
|
a priori comparisons
|
comparisons chosen before analyzing the data
|
|
|
k
|
used to identify the number of treatment conditions
|
|
|
quadratic trend
|
one change of direction
|
|
|
cubic trend
|
two changes of direction
|
|
|
interaction
|
the effect of IVA on the DV depends on the level of IVB
|
|
|
confounded comparisons
|
comparison in which groups vary on more than one level of the IV
|
|
|
assumptions of t-tests and ANOVAS
|
DV is an interval or ratio scale
Normally distributed Homogeneity of variance |
|
|
between groups research designs
|
each subject is tested under only one level of the IV
|
|
|
f-ratio
|
test statistic for ANOVA; between variance / within variance
|
|
|
critical value
|
the value from a sampling distribution against which a computed statistic is compared to determine whether the null may be rejected
|
|
|
R-squared
|
estimate of eta-squared; calculation of effect size; formula: SSbetween/ SStotal
|
|
|
analysis of simple comparisons
|
comparing every one of the IVs with every other combination of the IVs; Tukey
|
|
|
orthogonal
|
planned contrast; uncorrelated
|
|
|
post hoc test
|
posttests that are unplanned and occur after the analysis
|
|
|
a posteriori comparisons
|
unplanned; performed after omnibus f test is completed
|
|
|
a priori comparisons
|
comparisons chosen before analyzing the data
|
|
|
k
|
used to identify the number of treatment conditions
|
|
|
quadratic trend
|
one change of direction; slope other than zero, three groups
|
|
|
cubic trend
|
two changes of direction
|
|
|
interaction
|
the effect of IVA on the DV depends on the level of IVB
|
|
|
confounded comparisons
|
comparison in which groups vary on more than one level of the IV
|
|
|
assumptions of t-tests and ANOVAS
|
DV is an interval or ratio scale
Normally distributed Homogeneity of variance |
|
|
between groups research designs
|
each subject is tested under only one level of the IV
|
|
|
f-ratio
|
test statistic for ANOVA; between variance / within variance
|
|
|
critical value
|
the value from a sampling distribution against which a computed statistic is compared to determine whether the null may be rejected
|
|
|
R-squared
|
estimate of eta-squared; calculation of effect size; formula: SSbetween/ SStotal
|
|
|
df Total
|
N-1
|
|
|
df Within
|
N-k
|
|
|
df Between
|
k-1
|
|
|
# of comparisons for an analysis of simple comparisons
|
k(k-1)/2
|
|
|
Levels of IV in a trend analysis
|
Orthogonal (evenly-spaced)
Same n IV & DV must be quantitative |
|
|
omnibus test
|
used for an analysis of two or more groups and controls for family-wise error
|
|
|
cell effect
|
each cell is a distinct and independent group of subjects
|
|
|
main effect
|
the effect of the IV
|
|
|
interaction effect
|
cell effect- effect of IVA- effect of IVB
|
|
|
eta-squared
|
the proportion of variance in combined populations that can be accounted for by the IV; R-squared is an estimate of eta-squared
|
|
|
df Total
|
N-1
|
|
|
df Within
|
N-k
|
|
|
df Between
|
k-1
|
|
|
# of comparisons for an analysis of simple comparisons
|
k(k-1)/2
|
|
|
Levels of IV in a trend analysis
|
Orthogonal (evenly-spaced)
Same n IV & DV must be quantitative |
|
|
omnibus test
|
used for an analysis of two or more groups and controls for family-wise error
|
|
|
cell effect
|
each cell is a distinct and independent group of subjects
|
|
|
main effect
|
the effect of the IV
|
|
|
interaction effect
|
cell effect- effect of IVA- effect of IVB
|
|
|
eta-squared
|
the proportion of variance in combined populations that can be accounted for by the IV; R-squared is an estimate of eta-squared
|
