1.
The Significant Difference between Control and Experimental Group
In this study the result of the pre-test and the post-test of control group
and experimental group were analyzed by using t-test to know whether there
was a significant difference between control group and experimental group.
The analysis was calculated by using SPSS 16 program. The analysis
consists of: (1) The significant difference between students’ pre-test and
post-test scores in experimental group. (2) The significant difference
between students’ pre-test and post-test scores in control group. (3) The
significant difference between students’ pre-test scores in control and
experimental group. (4) The significant difference between students’ post-
test scores in control and experimental group.
a. Statistical Analysis in the Experimental Group
Table 4.11
Paired Samples Statistics
Mean N Std. Deviation Std. Error Mean
Pair 1 posttest_exp 77.43 30 5.532 1.010
pretest_exp 35.73 30 9.373 1.711
Based on table 4.11 paired sample statistic showed that, the mean
of pre-test was 35.73, the standard deviation was 9.373, the standard
error mean was 1.711, while the mean of post-test was 77.43, the
standard deviation was 5.532 and the standard error mean was 1.010
Table 4.12
Paired Samples Correlations
N Correlation Sig.
Pair 1 posttest_exp & pretest_exp 30 .111 .560
Paired sample table 4.12 correlation showed that the correlation between
pre-test and post-test of the experimental group was 0.111 with probability score
was 0.560.
Table 4.13
Paired Samples Test
Paired Differences
95% Confidence Interval
Std.
of the Difference
Deviati Std. Error Sig. (2-
Mean on Mean Lower Upper t df tailed)
Pair 1 posttest_exp -
41.700 10.343 1.888 37.838 45.562 22.083 29 .000
pretest_exp
The result of paired sample differences showed the mean between
pre-test and post-test in experimental group was 41.700, standard
deviation was 10.343, standard error mean was 1.888 and t-obtained was
22.083. At the significant level of p<0.05 for two tailed test and degree
of freedom 29, t-table was 2.06. Since the values of t-obtained was higher
that t-table, it could be stated that there was a significant difference in
students writing skill before and after the treatment in experimental
group.
b. Statistical Analysis in the Control Group
Table 4.14
Paired Samples Statistics
Mean N Std. Deviation Std. Error Mean
Pair 1 posttest_cont 67.68 34 8.868 1.521
pretest_cont 37.15 34 8.725 1.496
Based on the table 4.14 result from paired sample statistics of the
control group above, the mean of pre-test was 37.15, the standard
deviation was 8.725, and the standard error mean was 1.496, while the
mean of post-test was 67.68, the standard deviation was 8.868 and the
standard error mean was 1.521.
Table 4.15
Paired Samples Correlations
N Correlation Sig.
Pair 1 posttest_cont & pretest_cont 34 .100 .574
Based on the table 4.15 paired sample correlation showed that the
correlation between pre-test and post-test of the control group was 0.100
with probability score was lower than 0.05.
Table 4.16
Paired Samples Test
Paired Differences
95% Confidence
Interval of the
Std.
Difference
Deviati Std. Error Sig. (2-
Mean on Mean Lower Upper t df tailed)
Pair 1 posttest_cont -
30.529 13.048 2.238 25.977 35.082 13.643 33 .000
pretest_cont
The result of paired sample differences showed the mean between
pre-test and post-test in control group was 30.529, standard deviation was
3.545, standard error mean was 13.048 and t-obtained was 13.643. At the
significant level of p<0.05 for two tailed test and degree of freedom 33, t-
table was 2.04. Since the value of t-obtained was higher than t-table, it
could be stated that there was a significant difference in students writing
skill before and after the treatment in control group.
c. Statistical of Students’ Pre-test between Experimental and Control Group
Table 4.17
Group Statistics
Categories N Mean Std. Deviation Std. Error Mean
score pretest_exp 30 35.73 9.373 1.711
pretest_cont 34 37.15 8.725 1.496
Derived from the group statistics above, the mean of pre-test in
experimental group was 35.73, the standard deviation of pre-test
experimental group was 9.373, the standard error of pre-test experimental
group was 1.711. Then, the mean of control group was 37.15, the
standard deviation in control group was 8.725, and the standard error in
control group was 1.496.
Table 4.18
Independent Samples Test
Levene's
Test for
Equality of
Variances t-test for Equality of Means
95% Confidence
Std.
Interval of the
Mean Error
Difference
Sig. (2- Differenc Differe
F Sig. T df tailed) e nce Lower Upper
score Equal
variances .002 .969 -.625 62 .534 -1.414 2.263 -5.937 3.110
assumed
Equal
variances
-.622 59.653 .536 -1.414 2.273 -5.961 3.134
not
assumed
In the result of independent samples test table above, the
independent differences showed that the mean pre-test of the
experimental and the control group in equal variances assumed and equal
variances not assumed were -1.414, standart error differences in equal
variances assumed was 2.263 and standart error difference in equal
variances not assumed was 2.273. the t-obtained in equal variances
assumed was -0.625 and the significant (2-tailed) was .534. since the t-
obtained was lower than t-table (-0.625<2.05) and the significant (2-
tailed) was higher than computation with level significant (0.534>0.05),
it could be conclude that there was no significant difference between
pretest in the experimental group and the control group.
d. Statistical of Students’ Post-test between Experimental and Control
Group
Table 4.19
Group Statistics
Categories N Mean Std. Deviation Std. Error Mean
score posttest_exp 30 77.43 5.532 1.010
posttest_cont 34 67.68 8.868 1.521
Derived from the table 4.19 group statistics above, the mean of
post-test in experimental group was 77.43, the standard deviation of post-
test experimental group was 5.532, and the standard error of post-test
experimental group was 1.010. Then, the mean of control group was
67.68, the standard deviation in control group was 8.868, and the
standard error in control group was 1.521.
Table 4.20
Independent Samples Test
Levene's
Test for
Equality of
Variances t-test for Equality of Means
95% Confidence Interval
Std. Error
of the Difference
Sig. (2- Mean Differenc
F Sig. t df tailed) Difference e Lower Upper
score Equal
variances 2.008 .162 5.197 62 .000 9.757 1.877 6.004 13.510
assumed
Equal
variances
5.344 56.105 .000 9.757 1.826 6.100 13.414
not
assumed
In the result of independent samples test table above, the
independent differences showed that the mean pre-test of the
experimental and the control group in equal variances assumed and equal
variances not assumed were 9.757, standart error differences in equal
variances assumed was 1.877 and standart error difference in equal
variances not assumed was 1.826. the t-obtained in equal variances
assumed was 5.197 and the significant (2-tailed) was .000. since the t-
obtained was higher than t-table (5.197>2.06) and the significant (2-
tailed) was lower than computation with level significant (0.00<0.05), it
could be conclude that there was significant difference between post-test
in the experimental group and the control group.
