Exam 3 Flashcards
When to use ANOVA
- Comparing >2 groups
- Seeing if group means differ from one another
ANOVA Assumptions
- Data are normally distributed
- Data are independent
- Groups have constant variance
What is a Simple/One Way Analysis of Variance?
- Two variables: One categorical, one quantitative
- The variable has MORE THAN TWO LEVELS
What is Categorical Data?
Types of data which can be divided into fixed groups (eg. age groups, educational level, etc.)
What is Quantitative Data?
Data expressed in a quantity/amount/range (eg, meters, years, etc.)
ANOVA/F-Statistic Equation
F = Between Group Variation/Within Group Variation
What is Factorial Design ANOVA?
ANOVA with more than one independent variable
What does a larger obtained F score mean for the test?
Larger F = evidenfce against Ho (Because there is more difference between groups than within groups)
How to find the Degrees of Freedom for ANOVA
Numerator: Number of groups - 1 (k-1)
Denominator: Total number of observations - Number of GROUPS (N-k)
How to report F statistic
F (numerator, denominator)
What is the purpose of Post Hoc comparisons?
To indicate WHICH groups were significantly different from each other
What is the APA format for an ANOVA?
“A one way between subjects ANOVA was conducted to compare the effect of [INDEPENDENT VARIABLE] on [DEPENDENT VARIABLE] in [X], [Y], and [Z] conditions
What is the Effect Size?
The proportion of variance (of the dependent variable) that can be explained by the grouping/independent variable.
Small effect size?
About 0.01
Medium effect size?
About 0.06
Large effect size?
0.14 or greater
What is a Main Effect?
A difference between the levels of any factor in an ANOVA
What is an Interaction Effect?
The effect of one factor is differentiated across another factor. (Eg. gender AND exercise intensity affecting weight loss)
Main Effects on a Graph
Do not cross
Interaction effects on a graph
DO cross
When to use a post hoc test
- If the interaction is significant
- If the independent variable has MORE than two levels
What are correlations?
Correlations examine the associative relationship between two variables on a scale from -1 to 1
APA Style Correlation Table
Lists the correlation between every variable and every other variable
What is the Coefficient of Determination?
The % of variance in one variable that is accounted for in the other variable (Higher correlation = more variance explained)
What is the symbol of the Coefficient of Determination?
r^2
What information does the coefficient of determination give us?
Whether significant findings are meaningful.
What is a partial correlation?
It explores the relationship between two variables (with the impact of a third variable removed)
What is Regression?
A statistical technique for finding the best-fitting straight line for a set of data
What is Regression most often used for?
To make predictions about future events
What is the independent variable in a regression equation called?
The predictor variable(s)
How can we compute the significance of a regression equation?
By computing an f-ratio
What is the regression line formula?
Y’ = bX + a,
(Y’ = predicted
b = slope
X = predictor
a, = intercept)
