C 7
17.5 C
14 34.15
D D
6 14.63
E E
From the tables above, it was seen that the post-test percentage of grade A in the experimental group was 50. I used the same formula in percentage computation
for  grade  A  like  what  I  had  done  in  the  previous  pre-test  computation  in  the experimental group. The other items would use the same formula.
Furthermore, I concluded that the students‟ achievements increased in the post- test. The facts proved that there was no students who got E 0-59 in the post-test.
4.3.1 The Score Differences between Two Groups of Post-Test
I  used  independent  sample  t-test  to  know  the  score  differences  between  the experimental and the control groups in the post-test. Before t-test was done to know
the  significant  difference  between  the  control  and  the  experimental  groups,  I measured test of normality and homogeneity of post-test like what I had done before.
4.3.1.1 Post-Test Normality
Table 4.13 Process of Normality Analysis
One-Sample Kolmogorov-Smirnov Test
Post-Test control Post-Test
experimental N
41 40
Normal Parameters
a
Mean 79.73
87.28 Std. Deviation
9.995 8.545
Most Extreme Differences Absolute
.116 .125
Positive .116
.092 Negative
-.103 -.125
Kolmogorov-Smirnov Z .740
.791 Asymp. Sig. 2-tailed
.644 .559
a. Test distribution is Normal. b. Calculated from data.
Output  on  normality  test  by  using  Kolmogorov  test  above  for  post-test  in  the control group showed that Z value was 0.740 and sig value was 0.644. Because sig
0.664  was  higher  than  0.05,  it  was  concluded  that  the  post-test  data  in  the  control group was distributed normally. Furthermore, the experimental group showed that Z
value  was  0.791  and  sig  value  was  0.559.  The  post-test  data  in  the  experimental group were also distributed normally, for it showed that 0.559 was higher than 0.05.
4.3.1.2 Post-Test Homogeneity
Table 4.14 Process of Homogeneity Analysis
Test of Homogeneity of Variance
Pre-Test Levene
Statistic df1
df2 Sig.
1.246 1
79 .268
Based on the homogeneity test of post-test data in the control and experimental groups by using Levene Statistic, it showed that F value was 1.246 and sig value was
0.268.  Because  0.268  was  higher  than  0.05,  it  indicated  that  the  data  were homogeneous.
4.3.1.3 The Results of Post-Test
Based on the table of students‟ achievement in the post-test, it could be seen that the experimental group gained better achievement in the post-test than the control group
did.  The  results  of  the  post-test  were  better  than  the  results  of  the  pre-test  in  the control  group.  It  indicated  that  the  control  group  improved  well.  However,  the
score‟s improvement of the control group  was lower than that of the experimental group. The calculation of the post-test result by using T-test
Table 4.15 T-test
Group Statistics Group
N Mean
Std. Deviation
Std. Error Mean
Post-Test   Control Post-Test
Experimental 41
40 79.73
87.28 9.995
8.545 1.561
1.351
Independent Sample Test
t-test for Equality of Means t
df Sig.
Mean Std. Error
95 Confidence
2-tailed Difference
Difference Interval of the
Difference Lower
Upper Post-Test   Equal variances
Pre-Test assumed
Pre-Test Equal variances
Pre-Test not assumed
- .3.647
- .3.654
79 77.67
3 .000
.000 -7.543
-7.543 2.069
2.065 -
11.661 -
11.654 -3.426
-3.433
Based on t-test calculation above, it showed that t value was 3.647 and sig. 2-tailed was  0.000
.
0.000  was  lower  than  0.05,  so  it  indicated  that  there  was  significant difference  of  both  groups  where  the  average  score  of  the  post-test  was  different
between  the  experimental  and  the  control  groups.  The  statistic  table  above  proved that the experimental group had higher score than the control group did in which the
experimental group gained 87.28 and the control group gained 79.73.
4.4 The Effectiveness of Tea Party Technique