4 Good to average
capitalization, paragraphing, but meaning
not obscured
Scoring Elements
Scale Quality
Description
3 Fair to poor
Frequent errors of spelling, punctuation,
capitalization, paragraphing
– poor handwriting
– meaning confused or obscured
2 Very poor
No mastery conventions –
dominant by errors of spelling, punctuation,
capitalization, paragraphing
– handwriting illegible
– or not enough to evaluate
The range of score is 100 – 50 that can be explained as follows:
100 – 80 : Excellent to very good
79 – 70
: Good to average 69
– 60 : Fair to poor
59 – 50
: Very poor 50
: No qualified to be followed in the calculation
F. The Technique of Data Analysis
1. Normality Test
Before the writer decided parametric or nonparametric statistics to calculate the data to answer the hypothesis of the research, the writer had to analyze the
normality and homogeneity of the data. The examination of normality was needed to know whether the data has been normally distributed. The writer used Lilliefors
test using SPSS 22. This test is used to determine whether the distribution of the data from the sample is normal. If the normality is more than the level of
significance α 0.05, scores will be normally distributed. If the significant value
of the normality test is greater than 0.05, the data is normal. On the other hand, if it is below 0.05, the data significantly far from a normal distribution.
The criterion of hypothesis is: - Ho: Significant Score 0.05 means the data is normally
distributed. - H
1
: Significant Score 0.05 means the data is not normally distributed.
2. Homogeneity Test
After conducting the normality test, the writer tested the homogeneity of data. The objective of conducting homogeneity test was to see whether the data or
samples in both classes were homogenous or heterogeneous. It is to determine whether the data from the two groups have the same variant in order the
hypotheses can be tested using t-test. In calculating homogeneity test, the
researcher used Levene Statistic Test from SPSS 22. The steps are:
1 Click Analyze Compare means 2 Choosing One Way Anova
3 Fill variable Score on dependent list and fill Class variable on factor box 4 Click option and Checklist Homogeneity of variance test
5 OK If the result of homogeneity test shows the significance of the data was higher
than the significance degree α = 0.05 it means the data is homogeneous but if
the significance of the data was lower than the significance degree α = 0.05
it means the data is heterogeneous.
3. Hypothesis Test
After analyzing the normality and homogeneity of the data, the writer calculated the data to test the hypothesis that whether there is significant
difference betw een students’ writing of descriptive text in experimental class and
students’ writing of descriptive text in control class. The writer has calculated the data by using t-test formula because the data obtained was normal and
homogeneous. T-test is used to know whether Dictogloss technique is effective on students’ writing of descriptive text. To do hypothesis test, the researcher used t-
test formulaadapted from Anas Sudijono.
4
a. Determining mean of experimental class:
M
x
=
∑
Mx = Mean of gained score of experimental
∑ = Sum of gained score of experimental group N1 = The total students in experimental class
b. Determining mean of controlled class
My =
∑
My = Mean of gained score of controlled ∑ = Sum of gained score of experimental group
N2 = The total students in controlled class c. Determining standard deviation of experimental class X
SD
x
=
∑
SDx = Standard deviation score of experimental group ∑
= Sum of squared deviation of score of experimental group N1 = Number of students of experimental group
d. Determining Standard Deviation of Controlled Class Y
SD
y
=
∑
SD
y
= Standard deviation score of controlled group Σy
2
= Sum of squared deviation of score controlled group
4
Anas Sudijono, Pengantar Statistik Pendidikan, Jakarta : Raja Grafindo Persada, 2003, pp. 306-307.
N2 = Number of students of controlled group
e. Determining of standard error mean of variable X SEM
x
=
√
SE
M
x
= Standard error mean of experimental group SD
x
= Standard deviation score of experimental group N1 = Number of students of experimental group
f. Determining of standard error mean of variable Y
SEM
y
=
√
SE
M
y
= Standard error mean of controlled group SD
y
= Standard deviation score of controlled group N2 = Number of students of controlled group
g. Determining standard error of different mean of variable X and mean of variable Y, with formula:
SE
M
x
‒
M
y
=
√
h. Determining T T observation with formula:
T =
i. Determining t
– table t
t
in significant level 5 and 1 with degree of freedom df, with formula:
= d
= Degree of freedom N
1
= The total students in the experimental class N
2
= The total students in the controlled class
