Data Gathering Technique Data Analysis Technique
looked at the two aspects, which were the central tendency and the dispersion. According to Hatch and Farhady 1982, central tendency is used to talk about the
central point in the distribution of the scores in the data. There are three indicators to look at the central tendency. They are the mode which means the most frequently
obtained score in the data, the median which means the score at the center of the distribution, and the mean which means the average or the arithmetic average. Hatch
and Farhady 1982 claims that the mean is the most commonly used measure of central tendency because it takes all scores into account. The formula is as follows:
Where: μ
: the mean of the scores ∑N
: the total sum of the scores N
: the total number of cases
To be able to get the data more accurately, the researcher measured the degree of variability of the data from central tendency. The common way in measuring the
variability is the standard deviation. As Hatch and Farhady 1982 state, the most frequently used measure of variability is the standard deviation. “It is “standard” in
the sense that it looks at the average variability of all the scores around the mean; all scores are taken into account” Hatch and Farhady, 1982:57. The formula is as
follows:
Where: σ : the standard deviation of a set of scores
∑N
2
: the sum of the squares of each score ∑N
2
: the sum of the scores squares N
: the total number of cases
In order to gain the detailed statistic description of the data results, the researcher presents the descriptive statistic table.
Table 3.3 The Descriptive Statistic Table
No Variable Sources
Pretest Posttest
1 Mean 2 Mode
3 Median 4 Standard
Deviation 5 Maximum
6 Minimum
The researcher classified the pretest and the posttest scores into five categories Masidjo, 1995. The classifications are listed below.
Table 3.4 The Classification of The Scores.
Category Scores
1 Very good
9-10
Category Scores
2 Good
8 – 8.9 3
Sufficient 6.5 – 7.9
4 Bad
5.5 – 6.4 5
Very bad …. 5.5
The next step was the hypothesis testing. To do this, the researcher used t-test for non independent sample formula. According to Fraenkel and Wallen 1993, t-test
for non independent samples is used to compare the mean scores of the same group. The formula is as follows:
Table 3.5The table of the raw data of the scores Subject
Number X Y D D
2
1. 2.
N= ∑X=
∑Y= ∑ D
=
∑ D
2=
Where: ∑N :
the number of cases ∑X :
the total scores of the pretest ∑Y :
the total scores of the posttest D
: the score difference between the pretest and the posttest
D
2
: the squared score difference ∑D :
the total of the score difference ∑ D
2
: the total of the squared score difference
t
=
Where: t
: the t-value for non independent sample D
: the difference between paired scores D
: the mean of the difference ∑ D
2
: the sum of the squared difference scores N
: the number of pairs
Related to the statistical hypothesis as described in Chapter II, H was rejected if the
t-value was greater than the t-table in the .05 level of significance.