Presentation is loading. Please wait.

Presentation is loading. Please wait.

Statistics for the Social Sciences

Similar presentations


Presentation on theme: "Statistics for the Social Sciences"— Presentation transcript:

1 Statistics for the Social Sciences
Psychology 340 Spring 2010 Factorial ANOVA

2 Outline Basics of factorial ANOVA Interpretations Computations
Main effects Interactions Computations Assumptions, effect sizes, and power Other Factorial Designs More than two factors Within factorial ANOVAs Mixed factorial ANOVAs

3 Statistical analysis follows design
The factorial (between groups) ANOVA: More than two groups Independent groups More than one Independent variable

4 Factorial experiments
B1 B2 B3 A1 A2 Two or more factors Factors - independent variables Levels - the levels of your independent variables 2 x 3 design means two independent variables, one with 2 levels and one with 3 levels “condition” or “groups” is calculated by multiplying the levels, so a 2x3 design has 6 different conditions

5 Factorial experiments
Two or more factors (cont.) Main effects - the effects of your independent variables ignoring (collapsed across) the other independent variables Interaction effects - how your independent variables affect each other Example: 2x2 design, factors A and B Interaction: At A1, B1 is bigger than B2 At A2, B1 and B2 don’t differ

6 Results So there are lots of different potential outcomes:
A = main effect of factor A B = main effect of factor B AB = interaction of A and B With 2 factors there are 8 basic possible patterns of results: 1) No effects at all 2) A only 3) B only 4) AB only 5) A & B 6) A & AB 7) B & AB 8) A & B & AB

7 2 x 2 factorial design Interaction of AB A1 A2 B2 B1 Marginal means
What’s the effect of A at B1? What’s the effect of A at B2? Condition mean A1B1 Condition mean A2B1 Marginal means B1 mean B2 mean A1 mean A2 mean Main effect of B Condition mean A1B2 Condition mean A2B2 Main effect of A

8 Examples of outcomes Main effect of A √ Main effect of B
Dependent Variable B1 B2 30 60 45 60 45 30 30 60 Main Effect of A Main effect of A Main effect of B X Interaction of A x B X

9 Examples of outcomes Main effect of A Main effect of B √
Dependent Variable B1 B2 60 60 60 30 30 30 45 45 Main Effect of A Main effect of A X Main effect of B Interaction of A x B X

10 Examples of outcomes Main effect of A Main effect of B
Dependent Variable B1 B2 60 30 45 60 45 30 45 45 Main Effect of A Main effect of A X Main effect of B X Interaction of A x B

11 Examples of outcomes Main effect of A √ Main effect of B √
Dependent Variable B1 B2 30 60 45 30 30 30 30 45 Main Effect of A Main effect of A Main effect of B Interaction of A x B

12 Factorial Designs Benefits of factorial ANOVA (over doing separate 1-way ANOVA experiments) Interaction effects One should always consider the interaction effects before trying to interpret the main effects Adding factors decreases the variability Because you’re controlling more of the variables that influence the dependent variable This increases the statistical Power of the statistical tests

13 Basic Logic of the Two-Way ANOVA
Same basic math as we used before, but now there are additional ways to partition the variance The three F ratios Main effect of Factor A (rows) Main effect of Factor B (columns) Interaction effect of Factors A and B

14 Partitioning the variance
Total variance Stage 1 Between groups variance Within groups variance Stage 2 Factor A variance Factor B variance Interaction variance

15 Figuring a Two-Way ANOVA
Sums of squares

16 Figuring a Two-Way ANOVA
Degrees of freedom Number of levels of B Number of levels of A

17 Figuring a Two-Way ANOVA
Means squares (estimated variances)

18 Figuring a Two-Way ANOVA
F-ratios

19 Factor B: Arousal Level
Low B1 Medium B2 High B3 FactorA: Task Difficulty A1 Easy 3 1 6 4 2 5 9 7 11 10 8 A2 Difficult Example

20 Factor B: Arousal Level
Low B1 Medium B2 High B3 FactorA: Task Difficulty A1 Easy 3 1 6 4 2 5 9 7 11 10 8 A2 Difficult Example

21 Factor B: Arousal Level
Low B1 Medium B2 High B3 FactorA: Task Difficulty A1 Easy 3 1 6 4 2 5 9 7 11 10 8 A2 Difficult Example

22 Factor B: Arousal Level
Low B1 Medium B2 High B3 FactorA: Task Difficulty A1 Easy 3 1 6 4 2 5 9 7 11 10 8 A2 Difficult Example

23 Example: ANOVA table Source SS df MS F Between A B AB 120 60 1 2 30
27.7 6.9 Within Total 104 344 24 4.33

24 Factorial ANOVA in SPSS
What we covered today is a completely between groups Factorial ANOVA Enter your observations in one column, use separate columns to code the levels of each factor Analyze -> General Linear Model -> Univariate Enter your dependent variable (your observations) Enter each of your factors (IVs) Output Ignore the corrected model, intercept, & total (for now) F for each main effect and interaction

25 Assumptions in Two-Way ANOVA
Populations follow a normal curve Populations have equal variances Assumptions apply to the populations that go with each cell

26 Effect Size in Factorial ANOVA (completely between groups)
Note: if you downloaded the lecture Tues. there were two errors

27 Approximate Sample Size Needed in Each Cell for 80% Power (
Approximate Sample Size Needed in Each Cell for 80% Power (.05 significance level)

28 Other ANOVA designs Basics of repeated measures factorial ANOVA
Using SPSS Basics of mixed factorial ANOVA Similar to the between groups factorial ANOVA Main effects and interactions Multiple sources for the error terms (different denominators for each main effect)

29 Example Suppose that you are interested in how sleep deprivation impacts performance. You test 5 people on two tasks (motor and math) over the course of time without sleep (24 hrs, 36 hrs, and 48 hrs). Dependent variable is number of errors in the tasks. Both factors are manipulated as within subject variables Need to conduct a within groups factorial ANOVA

30 Example Factor B: Hours awake Factor A: Task 24 36 48 Motor Math B1 B2
1 4 3 5 6 9 A2 Math 2

31 Within factorial ANOVA in SPSS
Each condition goes in a separate column It is to your benefit to systematically order those columns to reflect the factor structure Make your column labels informative Analyze -> General Linear Model -> Repeated measures Enter your factor 1 & number of levels, then factor 2 & levels, etc. (remember the order of the columns) Tell SPSS which columns correspond to which condition As was the case before, lots of output Focus on the within-subject effects Note: each F has a different error term

32 Example Source SS df MS F p A Error (A) 1.20 13.13 1 4 3.28 0.37 0.58
B Error (B) AB Error (AB) 104.60 6.10 2.60 8.10 2 8 52.30 0.76 1.30 1.01 < 0.01

33 Example It has been suggested that pupil size increases during emotional arousal. A researcher presents people with different types of stimuli (designed to elicit different emotions). The researcher examines whether similar effects are demonstrated by men and women. Type of stimuli was manipulated within subjects Sex is a between subjects variable Need to conduct a mixed factorial ANOVA

34 Example Factor B: Stimulus FactorA: Sex Neutral Pleasant Aversive Men
4 3 2 8 6 5 1 A2 Women 7

35 Mixed factorial ANOVA in SPSS
Each within condition goes in a separate column It is to your benefit to systematically order those columns to reflect the factor structure Make your column labels informative Each between groups factor has a column that specifies group membership Analyze -> General Linear Model -> Repeated measures Enter your within groups factors: factor 1 & number of levels, then factor 2 & levels, etc. (remember the order of the columns) Tell SPSS which columns correspond to which condition Enter your between groups column that specifies group membership As was the case before, lots of output Need to look at the within-subject effects and the between groups effects

36 Example Source SS df MS F p Between Sex (A) Error (A) 0.83 20.00 1 8
2.50 Within Stimulus (B) Sex * Stimulus Error (B) 58.10 0.07 39.20 2 16 29.00 0.03 2.45

37 Partitioning the variance
Stage 1 partition is same as usual Stage 2 combines the other partitioning that we’ve done: The between subjects var is broken into 2 parts The within subjects is broken into different parts. Note: the interaction, because it involves a within groups variable, comes out in the partitioning of the within groups par


Download ppt "Statistics for the Social Sciences"

Similar presentations


Ads by Google