3.4 Method of Collecting the Data
Collecting data is the most important step in conducting a research study since it will influence much on the result of the research. A good research cannot be
obtained unless a proper data is available. Heaton 1979:109 states that
―before we assess the students‘ results, we should identify the features which we want to measure first. For example, in
writing test we may identify the point of fluency, grammar, vocabulary, content, and mechanics.
‖ As such, the writer considered the five aspects as the items to mark and each aspect had 5 point. The total score of the students was gotten from
the total point which was gotten then multiplied by 4.
3.5 Statistical Design
According to Isaac and William 1971:134 ―the t-test to determine a significant
difference between two sample means‖. The writer used t-test to see whether there is a significant difference between using a study tour method and using pictures in
teaching descriptive writing. Before t-test formula was applied, the first step to identify the significant difference between the experimental and the control
groups were found by comparing the means of both groups. After the computation of the two means was done, the t-test formula was
applied to determine whether the difference between the two means was statistically significant. In order to apply the t-test formula, the deviation should
be computed first.
The formula is as follows:
t =
1 −
2 �12+ �22
1+ 2− 2 1+ 2
1 2
In which; t
: significance M1
: means of the experimental group M2
: means of the control group d1
: deviation of the experimental group d2
: deviation of the control group N1
: numbers of sample in the experimental group N2
: numbers of sample in the control group Isaac and William, 1971:134
To interpret the t obtained, it should be consulted with the critical value of the t-table to check whether the difference is significant or not. In education
research, the 5 0.05 level of significance is used. If the t-value is higher than t- table, it means that there is significant difference between the two means.
Contrary, if the t-value is lower than t-table, it means that there is no significant difference between two means.
3.6 Scoring System