Written by:

Fitria Rahmawati, S.Pd., M.Hum.

Atika Salma, S.Pd.

for Internal Use of

Lecturer: Fitria Rahmawati, S.Pd., M.Hum.

English Education Department

Language Education Faculty
Universitas Muhammadiyah Yogyakarta
 SPSS is a Windows based program that can be used to perform data entry and
analysis and to create tables and graphs. People usually use this program to their
questionnaire report for their research.

A. DATA ENTRY
Before you analyze your data in SPSS, the first step that you should do is to entry
your data into SPSS. Perform the following steps for data entry:
Fill up variable view. In variable view, we can input name, nim, gender, major,
semester and other demographic information. However, one thing you should remember in
reporting your research data, the participants’ real identity should remain anonymous. Your
data view will be seen like the following image;

After that, fill in the variables with the data that you have got by going to the ‘data
view’, as seen in the following picture:
B. DATA SCREENING
Data screening is the process of ensuring your data is clean and ready to go before you
conduct further statistical analyses. Data must be screened in order to ensure the data is
useable, reliable, and valid for testing causal theory.

1. Descriptive Statistics (Frequency)

Below are some steps to find out the frequency of your data in SPSS, including:
• First, click Analyze à Descriptive Statistics à Frequencies

• After that, input all of questionnaire items that you have into the variable(s) column.
• Then, click Statistic
• in central tendency make check list in the mean, median, mode and sum.
• in Dispersion check list range, minimum, and maximum
• in Distribution check list in Skewness and Kurtosis
• click continue.

• After finish with Statistics then move on the Chart

• Click “Chart”
• You can choose chart type that you want (ex: choose histograms and check list show
normal curve on histogram if you want to see the curve on your histogram).

• Then, move on to Format and check list Ascending values and Compare variables
Click continue
 • Last, check list display frequency tables and click OK.

After finishing all the steps above, the Frequency data analysis result will show up like the
table below.
Statistics
Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 Q11 Q12
Valid 35 35 35 35 35 35 35 35 35 35 35 35
N
Missing 0 0 0 0 0 0 0 0 0 0 0 0
Mean 3.37 3.11 3.00 3.54 2.17 2.97 4.00 3.80 3.17 3.60 3.69 4.17
Median 4.00 3.00 3.00 4.00 2.00 3.00 4.00 4.00 3.00 4.00 4.00 4.00
Mode 4 2 2 4 2 2 4 4 3 4 4 4a
- - - - - -
Skewness .369 .119 .830 .383 -.959 .014
.569 .484 1.230 .386 .621 .674
Std. Error of
.398 .398 .398 .398 .398 .398 .398 .398 .398 .398 .398 .398
Skewness
- - - - - - - - -
Kurtosis 1.284 1.787 1.340
.748 .975 1.252 .852 1.162 .846 .796 .533 .198
Std. Error of
.778 .778 .778 .778 .778 .778 .778 .778 .778 .778 .778 .778
Kurtosis
Range 4 4 4 4 4 4 4 4 4 4 4 3
Minimum 1 1 1 1 1 1 1 1 1 1 1 2
Maximum 5 5 5 5 5 5 5 5 5 5 5 5
Sum 118 109 105 124 76 104 140 133 111 126 129 146

In order to check the missing data, refer to the N Valid Missing and the Range.
Missing data is a case in which the respondent(s) who missed to respond to one or more
items/statements in the questionnaire.
There is no missing data if the N Valid Missing score from all the questionnaire items
is 0 (zero), meaning that all items had been responded.
From those data, we can see that there is no missing data because all off the respondents fill
or respond all the questionnaire items, since the score of N Valid Missing on the sample table
is 0.
Besides, the missing data can also be observed from the Range Score. Range Score is
the response scale you have in your questionnaire (e.g. 1. Strongly disagree, 2. Disagree, 3.
Neutral, 4. Agree, 5. Strongly agree). In the sample, the scale used is 1 to 5, there is no
missing data if the range score resulted from the SPSS analysis is NOT more than 5 and NOT
less than 1.

Frequency. Frequency is used to identify how many respondents answer/response to each

questionnaire item. Below is the result of frequency analysis for 12 items.
To make you easier in reading the result, replace the clue questionnaire that was
originally stated as Q1 into the questionnaire statement. To replace the clue into the
questionnaire statement, you can follow these following steps:
1. Go to variable view
2. Open your questionnaire and copy your questionnaire statement on excel
 3. After your questionnaire statements are already copied in excel, now copy your
questionnaire statements in ‘label’ column in the ‘variable view’.

4. After that, repeat the frequency process in above to see the difference.
5. Finally, you will get the result as seen in the table below.
Statistics
1. Saya 2. Saya 3. Saya 4. Saya 5. 6. Saya 7. Saya 8. 9. Saya 10. Saya 11. Saya 12.
suka memba memba- suka Saya lebih lebih Biasanya dapat suka suka Kebiasa
membac ca ca memba lebih suka suka saya mengert membaca memba- an
a buku buku dengan ca suka mem- memba menggun i isi dengan ca keras memba-
dengan dengan keras ulang mem- baca ca buku akan baca dan keras karena ca keras
keras keras hanya dengan baca keras yang body mengek karena memban saya
baik minim ketika keras keras suatu terdapat language presikan dapat tu saya dapat
buku al 1 mendap bacaan mela- komik gambar dan perasaan menambah didalam melatih
cerita jam atkan untuk lui E- atau- didalam ekpressi saya Kosa kata meng- “pronou
atupun perhari tugas memah book pun nya. muka melalui dan ingat nciation
buku . dari ami isi dari novel ketika memba- pengeta- kosa ” saya
pelajara kampus dan pada dari sedang ca keras. huan baru. kata untuk
n. . makna buku pada membaca baru. lebih
dari cetak. buku keras baik.
bacaan pembel untuk
tersebut ajaran. meningka
tkan
pemaha-
man saya.
Valid 35 35 35 35 35 35 35 35 35 35 35 35
N Missin
0 0 0 0 0 0 0 0 0 0 0 0
g
Mean 3.37 3.11 3.00 3.54 2.17 2.97 4.00 3.80 3.17 3.60 3.69 4.17
Median 4.00 3.00 3.00 4.00 2.00 3.00 4.00 4.00 3.00 4.00 4.00 4.00
Skewness -.569 .369 .119 -.484 .830 .383 -1.230 -.959 .014 -.386 -.621 -.674
Std. Error
of .398 .398 .398 .398 .398 .398 .398 .398 .398 .398 .398 .398
Skewness
Kurtosis -.748 -.975 -1.252 -.852 1.284 -1.162 1.787 1.340 -.846 -.796 -.533 -.198
Std. Error
of .778 .778 .778 .778 .778 .778 .778 .778 .778 .778 .778 .778
Kurtosis
Range 4 4 4 4 4 4 4 4 4 4 4 3
Minimu
1 1 1 1 1 1 1 1 1 1 1 2
m
Maximu
5 5 5 5 5 5 5 5 5 5 5 5
m
Sum 118 109 105 124 76 104 140 133 111 126 129 146

Then after you label your questionnaire items, the frequency table will be seen as below:
1. Saya suka membaca buku dengan keras baik buku cerita atupun buku pelajaran.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 3 8.6 8.6 8.6
Tidak setuju 7 20.0 20.0 28.6
Netral 4 11.4 11.4 40.0
Valid
Setuju 16 45.7 45.7 85.7
sangat setuju 5 14.3 14.3 100.0
Total 35 100.0 100.0
2. Saya membaca buku dengan keras minimal 1 jam perhari.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 1 2.9 2.9 2.9
Tidak setuju 12 34.3 34.3 37.1
Netral 10 28.6 28.6 65.7
Valid
Setuju 6 17.1 17.1 82.9
sangat setuju 6 17.1 17.1 100.0
Total 35 100.0 100.0
3. Saya membaca dengan keras hanya ketika mendapatkan tugas dari kampus.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 2 5.7 5.7 5.7
Tidak setuju 14 40.0 40.0 45.7
netral 4 11.4 11.4 57.1
Valid
Setuju 12 34.3 34.3 91.4
sangat setuju 3 8.6 8.6 100.0
Total 35 100.0 100.0
4. Saya suka membaca ulang dengan keras bacaan untuk memahami isi dan makna dari bacaan
tersebut
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 1 2.9 2.9 2.9
Tidak setuju 8 22.9 22.9 25.7
Netral 4 11.4 11.4 37.1
Valid
Setuju 15 42.9 42.9 80.0
sangat setuju 7 20.0 20.0 100.0
Total 35 100.0 100.0
5. Saya lebih suka membaca keras melalui E-book daripada buku cetak.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 8 22.9 22.9 22.9
Tidak setuju 16 45.7 45.7 68.6
Netral 9 25.7 25.7 94.3
Valid
Setuju 1 2.9 2.9 97.1
sangat setuju 1 2.9 2.9 100.0
Total 35 100.0 100.0
 6. Saya lebih suka membaca keras suatu komik ataupun novel daripada buku pembelajaran.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 3 8.6 8.6 8.6
Tidak setuju 14 40.0 40.0 48.6
Netral 6 17.1 17.1 65.7
Valid
Setuju 5 14.3 14.3 80.0
sangat setuju 7 20.0 20.0 100.0
Total 35 100.0 100.0
7. Saya lebih suka membaca buku yang terdapat gambar didalamnya.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 1 2.9 2.9 2.9
Tidak setuju 2 5.7 5.7 8.6
Netral 4 11.4 11.4 20.0
Valid
Setuju 17 48.6 48.6 68.6
sangat setuju 11 31.4 31.4 100.0
Total 35 100.0 100.0
8. Biasanya saya menggunakan body language dan ekpressi muka ketika sedang membaca keras
untuk meningkatkan pemahaman saya.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 1 2.9 2.9 2.9
Tidak setuju 2 5.7 5.7 8.6
Netral 7 20.0 20.0 28.6
Valid
Setuju 18 51.4 51.4 80.0
sangat setuju 7 20.0 20.0 100.0
Total 35 100.0 100.0

9. Saya dapat mengerti isi baca dan mengekpresikan perasaan saya melalui membaca keras.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 2 5.7 5.7 5.7
Tidak setuju 9 25.7 25.7 31.4
Netral 10 28.6 28.6 60.0
Valid
Setuju 9 25.7 25.7 85.7
sangat setuju 5 14.3 14.3 100.0
Total 35 100.0 100.0
10. Saya suka membaca dengan keras karena dapat menambah Kosa kata dan pengetahuan baru.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 1 2.9 2.9 2.9
Tidak setuju 6 17.1 17.1 20.0
Netral 8 22.9 22.9 42.9
Valid
Setuju 11 31.4 31.4 74.3
sangat setuju 9 25.7 25.7 100.0
Total 35 100.0 100.0
11. Saya suka membaca keras karena membantu saya didalam mengingat kosa kata baru.
Frequency Percent Valid Percent Cumulative Percent
sangat tidak setuju 1 2.9 2.9 2.9
Tidak setuju 6 17.1 17.1 20.0
Netral 5 14.3 14.3 34.3
Valid
Setuju 14 40.0 40.0 74.3
sangat setuju 9 25.7 25.7 100.0
Total 35 100.0 100.0
 12. Kebiasaan membaca keras saya dapat melatih “pronounciation” saya untuk lebih baik.
Frequency Percent Valid Percent Cumulative Percent
Tidak setuju 1 2.9 2.9 2.9
Netral 6 17.1 17.1 20.0
Valid Setuju 14 40.0 40.0 60.0
sangat setuju 14 40.0 40.0 100.0
Total 35 100.0 100.0

Therefore, the histogram will be like this:

2. Missing Data
After you analyzing the missing data, then, how is there is a missing data from the
questionnaire? If in your data there is missing data, you should follow these steps to replace
your missing data.
a. Click Transform à choose Replace Missing Values

b. After that, input all of questionnaire items that you have into New Variables and click
OK
Then, data will be shown like the table below;

Result Variables
Result N of Case Number of Non- N of Valid Creating
Variable Replaced Missing Values Cases Function
Missing First Last
Values
1 Q1_1 0 1 35 35 SMEAN(Q1)
2 Q2_1 0 1 35 35 SMEAN(Q2)
3 Q3_1 0 1 35 35 SMEAN(Q3)
4 Q4_1 0 1 35 35 SMEAN(Q4)
5 Q5_1 0 1 35 35 SMEAN(Q5)
6 Q6_1 0 1 35 35 SMEAN(Q6)
7 Q7_1 0 1 35 35 SMEAN(Q7)
8 Q8_1 0 1 35 35 SMEAN(Q8)
9 Q9_1 0 1 35 35 SMEAN(Q9)
SMEAN(Q1
10 Q10_1 0 1 35 35
0)
SMEAN(Q1
11 Q11_1 0 1 35 35
1)
SMEAN(Q1
12 Q12_1 0 1 35 35
2)
From data above we can see there is no replaced missing data since the score is ‘0’.
The reason why the score is 0 is because all the respondents answered all the questions
provided in the questionnaire.
3. Data Outlier
Data outlier is when your data 'lie outside' (much smaller or larger than) most of the
other values in a set of data. The followings are the steps to investigate whether or not your
data consist of outlier.
a. First click Analyze à choose Descriptive Statistics à Explore

b. Input all of questionnare items that you have in the Dependent List and choose what you
want to analyse (Name, NIM, Gender, Major or Semester), e.g. gender.
c. Then, click Statistics
d. In the dialogue box, check list Descriptives (confidence interval 95%) and Outlier.
e. Click continue.

f. After that, move on to Plots and choose Factor levels together in Boxplots
g. click Stem-and-Leaf in Descriptive
h. click None in Spread vs Level With Levene Test and click continue

• Then, move on to Options

• click Exlude Cases Listwise in Missing Value
• click continue as seen in the table below
• The last, click OK and the result will be shown as below:
 Based on the data above, you can see that there is no outlier in question items number
1, 2,3,4,5,6,9 and 11. However, in question items number 7,8,10 and 12 there are data
outliers. On the question item number 7, there are 3 respondents who answer different answer
from others, they are respondents 10, 30 and 21 where respondent number 10 answers
strongly disagree, then respondent number 30 and 21 answer disagree. Then, In question
number 8 most of the respondents answer agree and neutral while respondent number 16, 20
and 28 answer strongly agree and respondent number 10 answers disagree. After that, there
is one respondent who becomes outlier in question number 10 that is respondent number 35
where most of respondents answer agree, strongly agree and neutral, while respondent 35
answers strongly disagree. Next, in the question number 12 there is also an outlier where
most of respondents answer agree and strongly agree, however there is just one respondent
(respondent 1) who answers disagree.
4. Validity and reliability
a. Validity
Use the Aiken Test for the validity test (see other separate document to check it)

b. Reliability
Reliability is related to consistency, meaning that how an instrument is consistent in
measuring data. In Quantitative Method, the instrument reliability is determined through
statistical analysis. To see whether your instrument is reliable, follow below procedures:

• Click Analyze à choose Scale à and then Reliability Analysis

• Secondly, input all of the valid questionnaire items that you have to the items
coloumn.
 • Then, click Statistic,
• Choose Scale if item deleted in “Descriptives for”,
• Choose None in “ANOVA table”, then click Continue

• Click Continue and the data will be shown like the followings:

Reliability Statistics
Cronbach's N of
Alpha Items
.914 7

This is the first table resulted from the Reliability test from the SPSS.
To find out the reliability, see the Cronbach’s Alpha score of the total items you have.

From result, the Cronbach’s Alpha score is 0.914 which means that all the 7 items of the
questionnaires are reliable. The score belongs to the High Reliability.

Item-Total Statistics
Scale Mean Scale Corrected Cronbach's
if Item Variance if Item-Total Alpha if Item
Deleted Item Deleted Correlation Deleted
1. Saya suka membaca
buku dengan keras
21.29 28.151 .827 .891
baik buku cerita atupun
buku pelajaran.
2. Saya membaca buku
dengan keras minimal 21.54 29.844 .720 .903
1 jam perhari.
4. Saya suka membaca
ulang dengan keras
bacaan untuk
21.11 28.987 .809 .894
memahami isi dan
makna dari bacaan
tersebut
9. Saya dapat mengerti
isi baca dan
mengekpresikan 21.49 32.198 .519 .925
perasaan saya melalui
membaca keras.
10. Saya suka
membaca dengan keras
karena dapat 21.06 28.820 .828 .892
menambah Kosa kata
dan pengetahuan baru.
11. Saya suka
membaca keras karena
membantu saya 20.97 28.499 .870 .887
didalam mengingat
kosa kata baru.
12. Kebiasaan
membaca keras saya
dapat melatih 20.49 33.669 .623 .913
“pronounciation” saya
untuk lebih baik.

The second table of the Reliability Test shows detail Cronbach’s Alpha score for each
item. From this table, see whether or not there is an item which has higher Cronbach’s Alpha
score compared to the total items. If there is, meaning that, the item is not reliable.
For this case, item no. 9 is higher (0,926 > 0,914), that shows, if questionnaire item no
9 is deleted, the reliability score will be increased to 0.925.
The result is, there are 6 reliable questionnaire items, which are items no 1, 2, 4, 10,
11 and 12.
 Reliability Statistics
Cronbach's N of
Alpha Items
.925 6

Item-Total Statistics
Scale Mean Scale Corrected Cronbach's
if Item Variance if Item-Total Alpha if Item
Deleted Item Deleted Correlation Deleted
1. Saya suka membaca
buku dengan keras
18.11 21.457 .823 .905
baik buku cerita atupun
buku pelajaran.
2. Saya membaca buku
dengan keras minimal 18.37 22.946 .714 .920
1 jam perhari.
4. Saya suka membaca
ulang dengan keras
bacaan untuk
17.94 22.350 .787 .910
memahami isi dan
makna dari bacaan
tersebut
10. Saya suka
membaca dengan keras
karena dapat 17.89 21.928 .838 .903
menambah Kosa kata
dan pengetahuan baru.
11. Saya suka
membaca keras karena
membantu saya 17.80 21.400 .909 .893
didalam mengingat
kosa kata baru.
12. Kebiasaan
membaca keras saya
dapat melatih 17.31 26.104 .645 .928
“pronounciation” saya
untuk lebih baik.