anova 2 (within groups)
TRANSCRIPT
![Page 1: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/1.jpg)
Repeated-measures designs (GLM 4)
Thanks to Andy Fieldhttps://
www.youtube.com/watch?v=wkMwW_2_TzY&feature=youtu.be
![Page 2: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/2.jpg)
Aims• Rationale of Repeated Measures ANOVA
– One- and two-way– Benefits
• Partitioning Variance• Statistical Problems with Repeated
Measures Designs– Sphericity– Overcoming these problems
• Interpretation
Slide 2
![Page 3: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/3.jpg)
Experimental rationale• Cause and effect.• Manipulate variables in a systematic
way to infer things about causality. • Previously different groups.• Now same group repeatedly.• Same patient, 2 different machines.
![Page 4: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/4.jpg)
Benefits of Repeated Measures Designs
• Sensitivity–Unsystematic variance is reduced.–More sensitive to experimental
effects.• Economy
–Less participants are needed.–But, be careful of fatigue.
Slide 4
![Page 5: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/5.jpg)
Counterbalancing Divide the participants into groups and have each group perform a slightly different task, so that any imbalance in the task is canceled out.
![Page 6: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/6.jpg)
An Example• Are certain Bushtucker foods more
revolting than others?• Four Foods tasted by 8 celebrities:
– Stick Insect– Kangaroo Testicle– Fish Eyeball– Witchetty Grub
• Outcome:– Time to retch(seconds).
Slide 6
![Page 7: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/7.jpg)
The Data
![Page 8: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/8.jpg)
Theory of one-way repeated-measures
ANOVA
![Page 9: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/9.jpg)
Problems with Analyzing Repeated Measures Designs• Same participants in all
conditions.– Scores across conditions correlate.– Violates assumption of
independence.• Assumption of Sphericity.
– Crudely put: the correlation across conditions should be the same.
– Adjust Degrees of Freedom.Slide 9
![Page 10: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/10.jpg)
The Assumption of Sphericity
• Basically means that the correlation between treatment levels is the same.
• Actually, it assumes that variances in the differences between conditions is equal.
• Measured using Mauchly’s test.– P < .05, Sphericity is Violated. (boo)– P > .05, Sphericity is met. (Yay!)
Slide 10
![Page 11: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/11.jpg)
What is Sphericity?
Slide 11
![Page 12: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/12.jpg)
Estimates of Sphericity
• Three measures:– Greenhouse-Geisser Estimate– Huynh-Feldt Estimate– Lower-bound Estimate
• Multiply df by these estimates to correct for the effect of Sphericity.
• G-G is conservative, and H-F liberal.
Slide 12
~
![Page 13: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/13.jpg)
Correcting for Sphericity
Mauchly's Test of Sphericity
Measure: MEASURE_1
.136 11.406 5 .047 .533 .666 .333Within Subjects EffectAnimal
Mauchly's WApprox.
Chi-Square df Sig.Greenhouse
-Geisser Huynh-Feldt Lower-bound
Epsilon
Tests the null hypothesis that the error covariance matrix of the orthonormalized transformed dependent variables isproportional to an identity matrix.
Slide 13
df = 3, 21
![Page 14: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/14.jpg)
Slide 14
OutputTests of Within-Subjects Effects
Measure: MEASURE_1
83.125 3 27.708 3.794 .02683.125 1.599 52.001 3.794 .06383.125 1.997 41.619 3.794 .04883.125 1.000 83.125 3.794 .092
153.375 21 7.304153.375 11.190 13.707153.375 13.981 10.970153.375 7.000 21.911
Sphericity AssumedGreenhouse-GeisserHuynh-FeldtLower-boundSphericity AssumedGreenhouse-GeisserHuynh-FeldtLower-bound
SourceAnimal
Error(Animal)
Type III Sumof Squares df Mean Square F Sig.
![Page 15: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/15.jpg)
Interpretation: Main Effect
Slide 15
Bushtucker Trials
Animal
Stick Insect Kangaroo Testicle Fish Eye Witchetty Grub
Tim
e to
Ret
ch (
s)
0
1
2
3
4
5
6
7
8
9
10
![Page 16: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/16.jpg)
Post Hoc Tests• Compare each mean against all
others (t-tests).• In general terms they use a stricter
criterion to accept an effect as significant.– Hence, control the familywise error rate.– Simplest example is the Bonferroni
method:
Slide 16
TestsofNumber Bonferroni
![Page 17: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/17.jpg)
TWO WAY ANOVA
19/03/16
![Page 18: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/18.jpg)
What is Two-Way Repeated Measures
ANOVA?• Two Independent Variables
– Two-way = 2 IVs– Three-Way = 3 IVs
• The same participants in all conditions.– Repeated Measures = ‘same
participants’– A.k.a. ‘within-subjects’
Slide 18
![Page 19: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/19.jpg)
An Example• Field (2013): Effects of
advertising on evaluations of different drink types.– IV 1 (Drink): Beer, Wine, Water– IV 2 (Imagery): Positive, negative,
neutral– Dependent Variable (DV):
Evaluation of product from -100 dislike very much to +100 like very much)
Slide 19
![Page 20: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/20.jpg)
Slide 20
SST
Variance between all participants
SSMWithin-Particpant Variance Variance explained by the
experimental manipulations
SSRBetween-
Participant Variance
SSAEffect of
Drink
SSBEffect of Imagery
SSA BEffect of
Interaction
SSRAError for
Drink
SSRBError for Imagery
SSRA BError for
Interaction
![Page 21: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/21.jpg)
Running the Analysis: Naming factors
Slide 21
![Page 22: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/22.jpg)
Defining Variables
Slide 22
![Page 23: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/23.jpg)
Defining Variables
Slide 23
![Page 24: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/24.jpg)
Contrasts
Slide 24
![Page 25: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/25.jpg)
Plots
Slide 25
![Page 26: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/26.jpg)
Getting Means
Slide 26
![Page 27: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/27.jpg)
Output: Sphericity
Slide 27
![Page 28: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/28.jpg)
Output: Main ANOVA
Slide 28
![Page 29: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/29.jpg)
Main Effect of Drink
Slide 29
F(1.15, 21.93) = 5.11, p = .01
![Page 30: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/30.jpg)
Main Effect of Imagery
Slide 30
F(1.50, 28.40) = 122.57, p < .001
![Page 31: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/31.jpg)
Drink by Dose Interaction p581 text
Slide 31
F(4, 76) = 17.16, p < .001
![Page 32: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/32.jpg)
Contrasts
![Page 33: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/33.jpg)
Summary• Repeated measures designs are very similar
to other ANOVAs– Interpret F ration for each effect
• Watch out for Sphericity– Mauchley’s test
• P <.05 sphericity can’t be assumed– Greehouse-Geisser correction– Huynh-Feldt correction
• Follow up tests– In SPSS can do built in contrasts only– Limited post-hoc tests (bonferroni)
![Page 34: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/34.jpg)
http://www.phdcomics.com/comics/archive.php?comicid=905
![Page 35: ANOVA 2 (within groups)](https://reader033.vdocuments.site/reader033/viewer/2022042619/587859481a28ab18098b4abf/html5/thumbnails/35.jpg)