Analyzing a Factorial ANOVA: Non-significant interaction Rick - - PowerPoint PPT Presentation

▶
analyzing a factorial anova non significant interaction
SMART_READER_LITE
LIVE PREVIEW

Analyzing a Factorial ANOVA: Non-significant interaction Rick - - PowerPoint PPT Presentation

Dec 29, 2022 315 likes •449 views

Analyzing a Factorial ANOVA: Non-significant interaction Rick Balkin, Ph.D., LPC-S, NCC Department of Counseling Texas A&M University-Commerce Rick_balkin@tamu-commerce.edu Balkin, R. S. (2008) 1 Analyzing a Factorial ANOVA:

slide-1
SLIDE 1

Balkin, R. S. (2008) 1

Analyzing a Factorial ANOVA: Non-significant interaction

Rick Balkin, Ph.D., LPC-S, NCC Department of Counseling Texas A&M University-Commerce Rick_balkin@tamu-commerce.edu

slide-2
SLIDE 2

Balkin, R. S. (2008) 2

Analyzing a Factorial ANOVA: Non-significant interaction

1.Analyze model assumptions 2.Determine interaction effect

3. Report main effects for each IV 4. Compute Cohen’s f for each IV 5. Perform post hoc and Cohen’s d if necessary. 3. Plot the interaction 4. Analyze simple effects 5. Compute Cohen’s f for each simple effect 6. Perform post hoc and Cohen’s d if necessary.

Non-significant interaction Significant interaction

slide-3
SLIDE 3

Balkin, R. S. (2008) 3

Analyzing a Factorial ANOVA: Non-significant interaction

  Analyze model assumptions   Determine interaction effect   Report main effects for each IV   Compute Cohen’s f for each IV  Perform post hoc and Cohen’s d if necessary

slide-4
SLIDE 4

Balkin, R. S. (2008) 4

Analyze model assumptions

Kolmogorov -Smirnov(a) Shapiro-Wilk Gender Statistic df Sig. Statistic df Sig. Men .117 30 .200(*) .972 30 .603 Change in GPA Women .156 30 .060 .924 30 .033

Kolmogorov -Smirnov(a) Shapiro -Wilk Note -Taking methods Statistic df Sig. Statistic df Sig. Method 1 .126 20 .200(*) .916 20 .081 Method 2 .154 20 .200(*) .971 20 .766 Change in GPA Control .144 20 .200(*) .952 20 .392

slide-5
SLIDE 5

Balkin, R. S. (2008) 5

Analyze model assumptions

Levene's Test of Equality of Error Variances(a) Dependent Variable: Change in GPA F df1 df2 Sig. .575 5 54 .719 Tests the null hypothesis that the error variance of the dependent variable is equal across groups. a Design: Intercept+gender+method +gender * method

slide-6
SLIDE 6

Balkin, R. S. (2008) 6

Determine interaction effect

Tests of Between -Subjects Effects Dependent Variable: Change in GPA Source Type III Sum

  • f Squares

df Mean Square F Sig. Partial Eta Squared Corrected Model 1.889(a) 5 .378 11.463 .000 .515 Intercept 4.931 1 4.931 149.582 .000 .735 gender .523 1 .523 15.856 .000 .227 method 1.174 2 .587 17.809 .000 .397 gender * method .193 2 .096 2.921 .062 .098 Error 1.780 54 .033 Total 8.600 60 Corrected Total 3.669 59 a R Squared = .515 (Adjusted R Squared = .470)

slide-7
SLIDE 7

Balkin, R. S. (2008) 7

Determine interaction effect

slide-8
SLIDE 8

Balkin, R. S. (2008) 8

Report main effects for each IV

Tests of Between -Subjects Effects Dependent Variable: Change in GPA Source Type III Sum

  • f Squares

df Mean Square F Sig. Partial Eta Squared Corrected Model 1.889(a) 5 .378 11.463 .000 .515 Intercept 4.931 1 4.931 149.582 .000 .735 gender .523 1 .523 15.856 .000 .227 method 1.174 2 .587 17.809 .000 .397 gender * method .193 2 .096 2.921 .062 .098 Error 1.780 54 .033 Total 8.600 60 Corrected Total 3.669 59 a R Squared = .515 (Adjusted R Squared = .470)

slide-9
SLIDE 9

Balkin, R. S. (2008) 9

Compute Cohen’s f/d for each IV

Descriptive Statistics Dependent Variable: Change in GPA Gender Note -Taking methods Mean

  • Std. Deviation

N Method 1 .3350 .22858 10 Method 2 .6400 .17764 10 Control .1650 .14916 10 Men Total .3800 .26993 30 Method 1 .1700 .18288 10 Method 2 .3050 .19214 10 Control .1050 .14615 10 Women Total .1933 .18880 30 Method 1 .2525 .21853 20 Method 2 .4725 .24893 20 Control .1350 .14699 20 Total Total .2867 .24938 60

slide-10
SLIDE 10

Balkin, R. S. (2008) 10

Compute Cohen’s f/d for each IV

Descriptive Statistics Dependent Variable: Change in GPA Gender Note -Taking methods Mean

  • Std. Deviation

N Method 1 .3350 .22858 10 Method 2 .6400 .17764 10 Control .1650 .14916 10 Men Total .3800 .26993 30 Method 1 .1700 .18288 10 Method 2 .3050 .19214 10 Control .1050 .14615 10 Women Total .1933 .18880 30 Method 1 .2525 .21853 20 Method 2 .4725 .24893 20 Control .1350 .14699 20 Total Total .2867 .24938 60

slide-11
SLIDE 11

Balkin, R. S. (2008) 11

Perform post hoc and Cohen’s d if necessary

Note -Taking methods

Multiple Comparisons Dependent Variable: Change in GPA Tukey HSD 95% Confidence Interval king methods (J) Note -Taking methods Mean Diffe rence (I-J)

  • Std. Error

Sig. Lower Bound Upper Bound Method 2

  • .2200(*)

.05741 .001

  • .3584
  • .0816

Control .1175 .05741 .111

  • .0209

.2559 Method 1 .2200(*) .05741 .001 .0816 .3584 Control .3375(*) .05741 .000 .1991 .4759 Method 1

  • .1175

.05741 .111

  • .2559

.0209 Method 2

  • .3375(*)

.05741 .000

  • .4759
  • .1991

Based on observed means. * The mean difference is significant at the .05 level.