CHAPTER III

RESEARCH METHOD

In this chapter discusses about the research method, it consist of research

design, population and sample, research instrument, validity and reliability

testing, normality and homogeneity testing, data collecting method and data

analysis.

A. Research Design

This research, the researcher found that experimental research is classified

into: pre-experimental design, true experimental design, and quasi experimental

design. Pre experimental designs do not have random assignment of subjects to

groups or other strategies to control extraneous variables. True experimental

designs (also called randomized design) use randomization and provide maximum

control of extraneous variables. Quasi experimental design lacks randomization

but employs other strategies to provide some control over extraneous variables.

This research used pre-experimental research design by using pre-test and

post-test with quantitative approach, because the researcher want to established

possible cause and effect between dependent and independent variable. The

researcher is intended to describe the effectiveness of crossword puzzle game

toward students’ vocabulary achievement for the first grade students of SMPN 2

Sumbergempol by comparing between the students’ score before being taught by

36
 37

using crossword puzzle game and after being taught by using crossword puzzle

game. This research was classified as pre experimental design because it had not a

control variable. In this research, the researcher just put one group and used pre-

test and post-test to see the results of the test.

According to Mark Balnaves (2001) a research design is the guidance of

how the research was constructed and carried out. Based on Creswell (2012: 293)

research design can be used to collect, analyze, and interpret data. Based on the

theory above, the researcher gets valid data and finally the researcher come to find

the answer of the research problems.

Gay (1992:298) defines that the experimental method is the only method

of the research that can truly test hypotheses concerning cause and effect

relationships. Creswell (2012:326) explains that experimental researchers test and

idea (or practice or procedure) to determine its effect on an outcome. There are

three designs included in pre-experimental. They are one-shot case study, one-

group pretest-posttest design and static group. The researcher used one-group

pretest-posttest design. The one-group pretest-posttest design usually involved

three steps as follow:

1. Administering a pretest measuring the dependent variable

2. Giving the experimental treatment to the subjects

3. Administering a posttest measuring the dependent variable

Differences attributed to application of the experimental treatment are

evaluated by comparing the pretest and posttest scores.

 38

Table 3.1 The Test Illustration of One Group Pre-test and Post-test Design

Pre-test Independent Variable Post-test

(Treatment)
Y1 X Y2

The procedures of pre-experimental design used one group pre-test and

post-test design applied in this research are, they are:

1. Administering a pre-test before applying game with a purpose measuring

the students’ vocabulary achievement in the first grade students at SMPN 2
Sumbergempol.

2. Applying treatment in teaching vocabulary by using Crossword Puzzle

Game to the subject in the first grade students at SMPN 2 Sumbergempol.

3. Administering a post-test after applying game with a purpose measuring the

students’ vocabulary achievement in the first grade students at SMPN 2
Sumbergempol.

4. Comparing the scores of pre-test and post-test.

It means that the researcher used only one class in this research. The

researcher had two test, those are before being taught crossword puzzle game and

after being taught crossword puzzle game. Then both of students’ score are

compared to know the significant difference. The reason why the researcher chose

one group pre-test and post-test is because the researcher wanted to focus

conducted research on one class.

This research intended to investigate the effectiveness of crossword puzzle

game toward students’ vocabulary at first grade of students in SMPN 2

 39

Sumbergempol in academic years 2015/2016. By applying the treatment was to

know whether the scores are increasing or not. Pre-test and post-test were given to

measure if there were significant difference scores before and after the students

being taught by using crossword puzzle game. So, the researcher know about the

effectiveness when the students’ get scores.

B. Population and Sample

1. Population

Population is subjects that have some qualities and characteristics

chosen to be learned and to be concluded by the researcher. According to

Gay (1992:140) population is the group to which a researcher would like the

result of a study to be generalizable. Moreover, Arikunto (Encyclopedia of

Educational Evaluation, 2010:173) states that a population is a set (or

collection) of all elements processing one or more attributes of interest.

Based on that statement above, the population of this research is all

the students at first grade of SMPN 2 Sumbergempol that consist of 209

students. The first grade of SMPN 2 Sumbergempol consist of seven

classes. The quantity of students in each class of the population is as follow:

 40

Table 3.2 Population of the Research

Class X (Total of Students)

VII A 26

VII B 26

VII C 26

VII D 26

VII E 27

VII F 26

VII G 26

VII H 26

∑X = 209

2. Sample

Gay (1992:123) states that sample is the individual selected

comprise. It means that selecting of a sample is very important step in

conducting a research study. It can be concluded that a sample is a part of

the population which have a certain characteristic from the population. The

researcher has chosen first grade class as one experimental.

Before researcher determines sample of this research, researcher

used purposive sampling because she already know the characteristics of the

class which would be used as sample based on observation. Purposive

sampling can be very useful for situations where you need to reach a

targeted sample quickly. In this research, the researcher had taken the first
 41

grade as a sample. The sample in this research is the students’ of VII-F in

SMPN 2 Sumbergempol. In this class, there were consists of 9 female and

17 male students’.

C. Research Instrument

Instrument has important function in this research. To collect data, the

researcher used instruments. According to Creswell (2012:157) an instrument is to

measure the variables in the study may not be available in the literature or

commercially. Creswell explains that developing an instrument consist of several

steps such as identifying the purpose of the instrument, reviewing the literature,

writing the questions and testing the questions with individuals similar to those

plan to study.

According to Sugiyono (2009) research instrument is a tool or instrument

used to measure nature and social phenomena observed. In this research, the

researcher collected the data through administering test. Test is an instrument or

procedure designed to measure the student’s ability.

In this research, the instrument used by the researcher was test. According

to Isnawati (2014) test is to obtain information. The information that we hope to

obtain will of course vary from situation to situation. In this research, the

instrument is used to know the students score of vocabulary achievement. The

tests were constructed by the researcher by using some score. Before her real test

was administered, the researcher conducted a try out test to the same students with
 42

the same test. In this test, there are pre-test and post-test. Both pre-test and post-

test have a same topic. The materials of the test are taken from English book

which are related to their subject and based on Junior High School Curriculum.

Pre-test is given to measure their ability before giving the treatment; meanwhile

post-test is given after giving the treatment. The numbers of the test given were 30

questions. This test is to know the aims of the students to improve the vocabulary

achievement.

D. Validity and Reliability Testing

1. Validity

The first criterion of good test is validity. According to Gay

(1992:154) validity is totally indispensable; there is no quality or virtue of a

test that can compensate for inadequate validity. Other definition, Gay

(1992) explains validity is the degree to which a test measures, what it is

supposed to measure. It means that, the used of valid instrument is very

essential to determine the validity of data. According to Isnawati there are

four types of validity: 1) Content validity, 2) Criterion- Related Validity and

3) construct validity 4) Face Validity. To measure whether the test has a

good validity, the researcher analyzed the test from content validity.

In this research, content validity is the degree to which a test

measures an intended content area and the test must appropriate with the

grade. The researcher made a test based on the objectives of syllabus so that
 43

it was not out of contents. Moreover, the try out test of this research had

content validity because the items were taken from sources for first grade

students in SMPN 2 Sumbergempol.

2. Reliability

In this research, reliability is a necessary characteristic of any good

test for it to be valid at all and a test must be reliable as measuring

instruments. According to Gay (1992:161) Reliability is the degree to which

a test consistently measures whatever it measures. Moreover, reliability is

expressed numerically, usually as a coefficient; a high coefficient indicates

high reliability. In this research, there is significant difference between the

score of pre-test and the score post-test.

To measure the reliability of the test, the researcher administered

tryout to see if the result of the test was reliable or not. Tryout was done to

make sure that the instrument was clear and the test was not either too easy

or too difficult. The formula used was Pearson-Product Moment formula.

 44

Table 3.3 The Result of Try Out Test Reliability

Correlations
VAR00001 VAR00002
VAR00001 Pearson Correlation 1 .663**
Sig. (2-tailed) .000
N 26 26
VAR00002 Pearson Correlation .663** 1
Sig. (2-tailed) .000
N 26 26

**. Correlation is significant at the 0.01 level (2-tailed).

The result of the calculation showed the reliability coefficient was

0.663. The computation of the Person Product Moment in tryout test the

score is 0.663, it is bigger than r table that is 0.388. So the researcher

concluded that the test is reliable.

E. Normality and Homogeneity Testing

1. Normality

Normality is the vital requirement in parametric analysis. The

purpose of normality testing is to know whether the data is normal

distribution or not. Normality of the data is important because if the data

were in normal distribution, the data are considered to be the representative

of the population. In this research, the researcher used one of the methods of

normality testing was done towards both try out of pre-test and post-test

score. The data were presented on the table below:

 45

Table 3.4 Normality Try out Pre-test of the students’

One-Sample Kolmogorov-Smirnov Test

VAR00001
N 26
Normal Parametersa Mean 72.8462
Std. Deviation 5.40882
Most Extreme Absolute .239
Differences Positive .239
Negative -.107
Kolmogorov-Smirnov Z 1.219
Asymp. Sig. (2-tailed) .102
a. Test distribution is Normal.

Table 3.5 Normality Try out Post-test of the students’

One-Sample Kolmogorov-Smirnov Test

VAR00002
N 26
Normal Parametersa Mean 77.5769
Std. Deviation 5.87315
Most Extreme Absolute .167
Differences Positive .167
Negative -.128
Kolmogorov-Smirnov Z .850
Asymp. Sig. (2-tailed) .465
a. Test distribution is Normal.

This output of the result normality testing by using One Sample

Kolmogrov Smirnov Test. If the significant value was less than 0.05, it

means that the data was not in normal distribution, meanwhile if the

significant value was more than 0.05. It means that the data was in normal
 46

distribution. Test above showed that the subject is 26 students. The

significance value from tryout of pre-test is 0.102. The significant value

from the pre-test it is bigger than 0.05 (0.102 > 0.05). It means H0 is

accepted and H1 is rejected and the data is in normal distribution.

Meanwhile, the significant value tryout of post-test was 0.465. The

significant value from the tryout of post-test it is bigger than 0.05 (0.465 >

0.05). It also means that H0 was accepted and H1 was rejected and the data

was in normal distribution. So, it could be interpreted that both of the data

tryout (pre-test and post-test) are in normal distribution.

2. Homogeneity

Homogeneity test is intended to know whether the variant of data is

homogeneous or not. Procedure used to test variant of homogeneity was by

determining F-max value. In homogeneity test F empiric should be lower

than F theoretic (table).

Table 3.6 Students’ score of Homogeneity

ANOVA
VAR00001
Sum of
Squares df Mean Square F Sig.
Between Groups 376.235 7 53.748 2.724 .041
Within Groups 355.150 18 19.731
Total 731.385 25
 47

Based on the table above, the test is homogeneity because the

significant is 0.041. It means that the significant is more than 0.05

(0.041>0.05).

F. Variable

A variable is everything that would become that object of research or the

influencing factors that would be studied. According to Mark Balnaves (2001) a

variable is a general class of objects, events, situations, characteristics and

attributes that are of interest to the researcher. Creswell (2012:112) stated that a

variable is a characteristic or attribute of an individual or an organization that (a)

researchers can measure or observe and (b) varies among individuals or

organization studied. The variables of this research are two variable, they are

independent variable and dependent variable.

1. Independent variable (X)

According to Mark Balnaves (2001) Independent variable has an

impact on the dependent variable. In other definition, Creswell (2012: 116)

stated that an independent variable in an attribute or characteristic that

influences or affects an outcome or dependent variable. In these research

independent variables is crossword puzzle game in teaching vocabulary.

2. Dependent variable (Y)

According to Creswell (2012:115) a dependent variable is an

attribute or characteristic that is dependent on or influenced by the

 48

independent variable. Dependent variable is the consequence or dependent

variable upon antecedent variables. The dependent variable in this research

is the student’s in vocabulary achievement.

G. Tryout Test

The researcher conducted try out this test to another subject of sample

would be used in this research. The purpose of conducting tryout of the instrument

is to achieve the validity and reliability of the instrument. Tryout would be

implemented to one class of students of the first grade students at SMPN 2

Sumbergempol. Researcher chose this subject based on characteristics of students

ability that near same with the sample was used in this research. Tryout was being

conducted in home of students because this day is day off and doing in 45

minutes. All of student’s doing by his or her tryout of test. Tryout sample was the

students in different class namely VII-A class. The researcher was chosen because

they have almost same level as the experimental group. The researcher conducted

a try out test to the other students with the same test on Wednesday, 24 February

2016.

H. Data Collecting Method

Data collecting method is the method to obtain data. Data of this research

are collected by administering test. Test is tool or procedure used to know or

measured something in a condition, ways and the rules are determined (Arikunto,
 49

2010: 266). The researcher as teacher in this research teaches the students. In

order to get high quality of data, the instruments used must meet requirements as

good instruments. Instrument is used to collect data in research and it is one of the

significant steps in conducting the research. The instrument is to get the students

score of vocabulary achievement. Therefore, the researcher must choose some

instruments in data collecting process. There were three steps of tests used in this

research they were:

1. Pre-test

Before teaching the new material by using crossword puzzle game,

the researcher gave a test to the students. This test was given to know the

basic competence for the student and to measuring knowledge skills of

individual students. Pre-test was given to the students before being taught

by using crossword puzzle game. The test respondent was asked to do set of

vocabulary. The score obtained were analyzed in determine between pre-test

and post-test. The tests of pre-test consist of 30 questions. Time allocation

of test was 45 minutes. The researcher had taken the pre-test from the first

grade students in SMPN 2 Sumbergempol on Monday, 29 of February 2016.

2. Post-test

To get a data, a post-test was given to the students. In this test was

given to know the scores of the students after being taught by using

crossword puzzle game. The test respondent was asked to do set of

vocabulary. The tests of post-test consist of 30 questions. Time allocation of

 50

test was 45 minutes. The researcher had taken of pre-test and post-test from

the same place. The post-test have been conducted on Saturday, 12 of March

2016.

I. The Description of Treatment

After administering the pre-test, the researcher gave the treatment to

the students. The researcher applied the treatment of English by using

crossword puzzle game on 29th February 2016 until 7th March 2016. The

treatment in this research is crossword puzzle game. The researcher taught

vocabulary by crossword puzzle game of teaching. The material animals are

used to teach vocabulary, in order to increase their vocabulary achievement.

Crossword puzzle games help the students easier to memorize vocabulary.

The students can answer with instruction for teacher. It makes the students

were enthusiasm, enjoyable and interested in learning English. When teaching

and learning process by crossword puzzle is done, the students were very

happy and they got new spirit to learn English.

J. Data Analysis

This research used a quantitative data analysis. The quantitative data of

this research is numeric data and can be formulated by using statistical method. In

the experimental design, the data analyses are experimental one groups, used pre-

test and post-test. The data analysis in this research is using t-test.
 51

Gay (1992:436) states that t-test is used to determine whether two means

are significantly different at a selected probability level. The method used to find

the significant difference on the teaching vocabulary related with the first value of

pre-test and the last value of post-test by using crossword puzzle game.

The researcher in this research used the formula of t-test to analyze the

data, because to find out which one is more effective between before the students’

being taught using crossword puzzle game and after the students being taught

using crossword puzzle game in teaching vocabulary achievement to the first

grade students of SMPN 2 Sumbergempol in academic year 2015/2016.

In this research, the data obtained from pre-test and post-test were

analyzed by using T-test by using SPSS 16.0. It means that the researcher did not

used manual computation. All the data collected were accounted by using SPSS

16.0 program in this case was paired sample T-test. Because the researcher hope

to find out the effect of crossword puzzles game in teaching vocabulary

achievement. Firstly, the researcher conducted of pre-test. Then after of pre-test,

the researcher gives a treatment. The researcher was taught by using crossword

puzzles game in teaching vocabulary. After the treatment, the students were tested

again. Finally, the means of the two tests are compared to find out there is

significant difference.

The researcher used of T-test as follows:

1. The researcher finds out the mean of pre-test (x) and mean of post-test (y),
the formula is:

x=
 52

y=

Where:
: Total score of pre-test
: Total score of post-test
N : total number of students
2. Then, the researcher finds out the mean of differentiate pre-test and post-
test, the formula used is follow:

Md =

Where:
Md : the mean of differential pre-test and post test
: sum of different between post-test and pre-test
N : total number of students
3. Next, the researcher finds out the data percentage, the researcher used
formula:

P=

Where:
P : percentage of data
f : frequency of the counted value
n : number of students
4. After that, the researcher finds out the standard deviation, the formula used
is:

S =

S =

Where:
 53

S : standard deviation
2
∑X : sum of pre-test quadrate score
∑x : sum of pre-test score
∑Y2 : sum of post-test quadrate score
∑y : sum of post-test score
N : number of students

5. Then, the researcher finds out the total number of quadrate deviation (∑ X2
d), the formula is:

∑ X2 d = ∑ d2 -

Where:
∑ X2 d : total number of quadrate deviation
∑d : sum of different between post-test and pre-test
N : number of students

6. Next, the researcher finds out the t-test by using formula:

tcount =

Where:
Md : mean different of pre-test and post-test
∑x2 d : total of quadrate deviation
N : number of students
7. Finally the researcher looks for t-table distribution with significant 5%
df = N-1
Where:
df : degree of freedom
N : number of students