where: DP
= discrimating power JB
A
= the sum deviation of each students in upper group JB
b
= the sum deviation of each students in lower group The criteria of discriminating power of the test in the try out are;
Interval Criteria
DP 0.00 Very Poor
0.00 DP 0.20 Poor
0.20 DP 0.40 Satisfactory
0.40 DP 0.70 Good
0.70 DP 1.00 Excellent
3.8.2 Pre-Test
The pre test is administered before the treatment season. The purpose of the test is to check the students‟ mastery of simple past tense before the treatments
are given. First, I come to the class and explained what the students had to do. The students are asked to do the pre-test. The test is about identifying the irregular and
irregular verbs of simple past tense in form multiple choice items. Multiple-choice tests tend to have superior reliability and validity. Moreover, scoring can be done
quickly and involved no judgment and opinions as to degree of correctness; therefore, the tests tend to be objective. This is done two groups, experimental and
B B
A A
JS JB
JS JB
DP
control group. The purpose of pre- test is to measure the student‟ initial
understanding and achievement before the treatments are given.
3.8.3 Post Test
Brown 2004:3 states that a test is a method of measuring a person‟s ability, knowledge, or performance in a given domain. After the treatments are
done and finished, the post test will be used to measure the students. will be given to the students. After I analyze the try-out of post-test, the post-test itself could be
used to be tested because the test items have been selected. The aim of conducting post-
test is to know the result of the students‟ simple past tense mastery after the treatments. Then the data of pre-test and post-test are analyzed to see whether
there is improvement and significant difference of students‟ simple past tense mastery between those who are taught using Course Review Horay technique and
those who are taught without Course Review Horay technique or not This is also done in the control and experiment group. For this post-test, multiple-choice test
is used.
3.9 Technique of Data Analysis
3.9.1 T-test Analysis
According to Arikunto 2006: 311, t-test is a statistical test that involves means of normal populations with unknown standard deviations. The small samples are
used based on a variable t equal to the difference between the mean of the sample, and the mean of population divided by a result obtained by dividing the standard
deviation of the sample by the square root of the number of individual in the sample.