Multifactor Anova Hypothesis Testing

commit to user 65 c 2 = 2.303 { B - S logS i x n-1 } = 2.303 84.49 - 81.0348 = 3.4552 Based on the result of the calculation above. it can be seen that the c 2 3.4552 is lower than c t at the level of significance a= 0.05 = 7.81. Because c 2 c t 3.49 7.81, the data are homogenous,.

C. Hypothesis Testing

Hypothesis test can be done after the results of normality and homogeneity test are fulfilled. The data analysis is done by using multifactor analysis of variance 2 x 2. H is rejected if F Ft. it means that there is a significant difference and an interaction. If H is rejected the analysis is continued to know which group is better using Tukey test. The multifactor analysis of variance 2 x 2 and Tukey test are described as below: a. Summary of a 2 x 2 Multifactor Analysis of Variance

1. Multifactor Anova

Data Intelligence There Phase Technique Conventional method Sum High A 1 CELL 1 60 68 72 76 80 80 80 84 88 88 92 Data = 11 CELL 2 56 56 60 60 64 64 68 68 68 76 76 Data = 11 Data = 22 SX = 1584 X = 72 commit to user 66 SX = 868 = 78.9 SX = 716 X = 65.09 Low A 2 CELL 3 56 60 60 60 64 64 64 64 64 68 76 Data = 11 SX = 700 X = 63.63 CELL 4 60 60 64 64 64 68 68 68 72 76 76 Data = 11 SX = 740 X = 67.27 Data = 22 SX = 1440 X = 65.45 Total Data = 22 SX = 1568 X= 71.27 Data = 22 SX = 1456 X= 66.18 Data = 44 SX = 3024 X= 68.545 F. Anova F. Ms. Groups = 3 1594 = 531.39 F column = 164 . 49 09 . 285 = 5.798 Ms. Within groups = 40 56 . 1966 = 49.164 F row = 164 . 49 275 . 471 = 9.585 Ms. Column = 1 09 . 285 = 285.09 F ic = 164 . 49 805 . 837 = 17.002 Ms. row = 1 275 . 471 = 471.275 Ms. interaction = 1 805 . 837 = 837.805 X commit to user 67 Table 9: Summary Multifactor Analysis of Variance Source of variance SS dF Ms F o F t 0.5 Between columns Between rows Columns by rows Between groups Within Groups 285.09 471.275 837.805 1594.17 1966.56 1 1 1 3 40 285.09 471.275 837.805 531.39 49.164 5.798 9.585 17.002 - - 4.08 4.08 4.08 - - 3560.73 43 - - - Based on the table above, it can be concluded that: 1 Because F between columns 5.79 is higher than F t at the level of significance a = 0.05 4.08, the difference between columns is significant. It can be concluded that the technique of teaching reading differ significantly from one another in their effect on the performance of the subject in the experiment. The mean score of students using Three –Phase Technique 71.27 is higher than using Conventional Method 66.18. It means that teaching reading using Three- Phase Technique is more effective than using Conventional Method. 2 Because F row between row 9.58 is higher than F t at the level of significance a = 0.05 4.08. The difference between rows is significant. It can be concluded that the students having high and those having low IQ are significantly different. The mean score of students having high IQ 78.9 is higher than low IQ 63.63. It means that the students reading achievement having high IQ and low IQ is significant. 3. Because F interaction between group 17.002 is bigger than F t at the level of significance a= 0.05 4.08. There is interaction effect between the two variables, teaching method and intelligence, It means the effect of teaching method depend on the degree of intelligence. Three-phase technique is more commit to user 68 suitable technique for the students with high intelligence, while conventional method is suitable technique for students with low intelligence in teaching reading comprehension. Tukey Test Data Intelligence There Phase Technique Conventional method Sum High A 1 Group 1 Data = 11 Sx = 868 x = 78.9 Group 2 Data = 11 Sx = 716 x = 65.09 Data = 22 Sx = 1584 x = 72 Low A 2 Group 3 Data = 11 Sx = 700 x = 63.63 Group 4 Data = 11 Sx = 740 x = 67.27 Data = 22 Sx = 1440 x = 65.45 Total Data = 22 Sx = 1568 x = 71.27 Data = 22 Sx = 1456 x = 66,18 Data = 44 Sx = 3024 x = 68.72 1. Three Phase Technique compared with Conventional Method q = n | 2 1 Variance Error X X c c - = 22 | 167 . 49 18 . 66 27 . 71 - = 494 . 1 09 . 15 = 3.406 q o between columns 3.406 is higher than q t at the level of significance a = 0.05 2.95. The difference between columns is significant 2. Three Phase Technique compared with Conventional Technique for the students having high intelligence q = n | 1 2 1 1 Variance Error X X r c r c - = 11 | 164 . 49 63 . 63 9 . 78 - = 6019 . 2 27 . 15 = 5.868 Because q o between columns high intelligence 5.868 is higher than q t at the commit to user 69 level of significance a = 0.05 is 3.11 and q t at the level of significance a = 0.01 is 4.39, teaching technique using Three Phase differs significantly from Conventional method for students who have high intelligence. Because mean A 1 B 1 78.9 is higher than A 1 B 2 63.63, it can be concluded that Three Phase Technique is more effective than Conventional method to teach reading for students having high intelligence. 3. Three Phase Technique compared with Conventional Technique for the students having low intelligence q = n | 2 2 2 1 Variance Error X X r c r c - = 11 | 164 . 49 90 . 62 27 . 67 - = 6019 . 2 37 . 4 = 1.6795 q o between cells A 1 B 2 and A 2 B 2 1.6795 is lower than q t at the level of significance a = 0,05 3,11. b. Summary of Tukey Test The finding of q is found by dividing the difference between the means by the square root of the ratio of the within group variation and the sample size. Between group q o q t 0.05 A 1 – A 2 3.406 2.95 A 1 B 1 – A 1 B 2 5.868 3.11 A 1 B 2 – A 2 B 2 1.6795 3.11 From the summary of Tuckey test, it can be concluded that: 1. Because q between columns 3.406 is higher than qt 2.95, the difference between columns is significant. It can be concluded that teaching reading commit to user 70 using three-phase technique to the seventh grade students at SMPN 5Nganjuk significantly differs from teaching reading using conventional method. 2. Because q between columns 5.868 is higher than qt 3.11, the difference between the students having high intelligence and those having low intelligence is significant. It can be concluded that the students having high intelligence is significantly different from those having low intelligence. 3. Because qo between columns 1.6795 is lower than qt 3.11, the difference between using three-phase technique and conventional method for teaching reading to the students having low intelligence is not significant.

D. Discussion