nota kursus-asas-spss-28-29-april-2014-plpp

28-29 April 2014

© Muhammad Amirul Abdullah 2014 1

Muhammad Amirul bin Abdullah

E-mel: [email protected]

Blog: cikguamirul.wordpress.com

1

TARIKH

/ MASA8.30 - 10.30 pagi

10.30 -

11.00 pagi11.00 pg - 1.00 tgh

1.00 tgh - 2.30

ptg2.30 - 4.30 ptg

4.30 -

5.00

ptg

28 April

(Isnin)

1.0 Asas Penyelidikan

2.0 Mengenali SPSS

2.1 Membuka perisian

2.2 Menyediakan

template

2.3 Memasukkan data

MINUM PAGI

3.0 Modifying the Data

File

4.0 Screening & Cleaning

Data

5.0 Manipulating the

Data REHAT &

MAKAN

TENGAHARI

6.0 Descriptive

Statistics

7.0 Realibility

MINUM

PETANG

29 April

(Selasa)

8.0 T-Tests

9.0 One-Way ANOVA

10.0 Two-Way ANOVA

11.0 Correlation

12.0 Multiple

Regression

13.0 Kesimpulan

2

28-29 April 2014


“SUKA PENYELIDIKAN SUKA STATISTIK”

Statistical Package for the Social Sciences

Predictive Analytics SoftWare (2009) – ver.18

IBM SPSS (2010) – ver.21

3

• Kenapa STATISTIK?

Alat untuk membuat keputusan:

i. Objektif kajian

ii. Hipotesis Kajian

Make informed decisions

Collect Analyze Present Interpret

4

28-29 April 2014


PERUBAHAN

AMALAN

ANALISIS STATISTIK

Tu

juan

Perisia

n

Jen

isd

ata

Kem

ah

iran

Reko

d

Maklu

man

Pem

an

tau

an

Kajian

5

Melibatkan pengumpulan maklumat (data), menganalisisnya,

dan membuat keputusan yang bermakna.

Sains membuat kesimpulan dari data.

Koleksi prosedur mengumpul data bagi membuat

keputusan

Bidang pengajian yang melibatkan proses

pengumpulan, analisis, persembahan, dan tafsir

untuk membuat keputusan.

Satu cabang matematik yang menganalisis nombor untuk

membuat keputusan.

MAKSUD

STATISTIK

6

28-29 April 2014


Secara umumnya statistik ialah satu teknik matematik

untuk memproses, menyusun, menganalisis dan

menyimpulkan data yang berbentuk kuantitatif. Data-

data yang diperolehi dari individu disatukan untuk

membuat sesuatu kesimpulan seberapa umum yang

boleh.

7

KegunaanStatistik

Menerangkandata

MeringkaskanData

Memberimakna

kepada data

8

28-29 April 2014


Statistik deskriptif digunakan

untuk mengumpul data,

menyusunnya dan

mempersembahkan data itu

supaya data yang banyak dapat

disimpulkan dengan

menggunakan indeks seperti

kekerapan, peratusan, min,

mod, median, varians dan

sisihan piawai.

Statistik inferensi digunakan

untuk membuat sesuatu

anggaran tentang indeks

populasi dengan

menggunakan satu indeks

statistik daripada sampel

yang representatif. Dengan

menggunakan indeks statistik

daripada sampel kita boleh

membuat satu kesimpulan

tentang sifat sesuatu

populasi. Statistik yang

digunakan bergantung kepada

paras ukuran data. Contoh;

Ujian-t, ANOVA, Korelasi,

Regresi dan lain-lain.

STATISTIK DALAM PENYELIDIKAN SAINS SOSIAL

STATISTIK DESKRIPTIF STATISTIK INFERENSI

9

Meringkas dan mempersembah data dengan menggunakan

nombor.

Data berasal daripada (sama ada) pemboleh ubah kuantitatif

(ketinggian, kecerdasan, berat) atau dari pemboleh ubah

kategori (jantina, judul buku, jenis sekolah)

Data yang dikumpul diproses dan disusun dalam bentuk yang

mudah dibaca dengan menggunakan pelbagai cara seperti

graf, jadual, dan carta.

10

28-29 April 2014


Markah ujian yang dikumpul

Bagaimana hendak memudahkan bacaan dan

memberi makna kepada markah yang dikumpul?

11

12

28-29 April 2014


Membuat inferens mengenai sesuatu populasi

dengan berdasarkan data yang dikumpul dari

satu kumpulan yang lebih kecil (sampel)

Sampel yang dipilih mempunyai ciri-ciri yang

sama dengan populasi (representative)

Menggunakan kaedah statistik yang

mengambil kira faktor ralat dan perbezaan

sampel dengan populasi

13

STATISTIK INFERENSI

Populasi Sampel

Dapatan

14

28-29 April 2014


Markah ujian yang dikumpul

Apakah interpretasi yang boleh dibuat

berdasarkan kepada markah ujian sampel?

Pelajar Lelaki lebih cemerlang?

Tiada Perbezaan kecemerlangan berdasarkan jantina?

Apakah ujian statistik yang perlu digunakan?

15

5 JENIS:

Independent Variable

Dependent Variable

Mediated Variable

16

28-29 April 2014


Moderator Variable

Extraneous Variable

17

Demografi:

i. Jantina

ii. SES

iii. Lokasi

Kaedah Mengajar:

i. X

ii. Y

PENCAPAIAN PELAJAR

Kualiti Kelengkapan

Bengkel/Makmal

Independent Variables (IV) Dependent Variable (DV)18

28-29 April 2014


Demografi:

i. Jantina

ii. SES

iii. Lokasi

Kaedah Mengajar:

i. X

ii. Y

MOTIVASI

Kualiti Kelengkapan

Bengkel/Makmal

Independent Variables

(IV)

Dependent Variable

(DV)

PENCAPAIAN PELAJAR

INTERVENING VARIABLE

19

Nisbah

(Ratio)

Sela (Interval)

Ordinal

Nominal• Aras paling rendah

• Angka tiada magnitud. Bertujuan untuk

pengkelasan, pengenalan

• Jantina, nombor KP, jenis sekolah, kod buku

• Pengkelasan mengikut pemeringkatan (tinggi rendah)

• Nombor menunjukkan kuantiti; jarak/selang tidak sekata

• Kedudukan dalam kelas, penarafan, kemahiran bertutur,

ranking, SES, Pendapat (Setuju, Tak Pasti, Tidak Setuju)

• Nombor menunjukkan kuantiti/ magnitud

• Jarak sekata antara nombor.

• Suhu, markah ujian, IQ

• Nilai sifar arbitrari (tiada sifar mutlak)

• Nombor menunjukkan kuantiti

• Jarak sekata antara nombor.

• Berat, tinggi, pendapatan

• Nilai sifar menunjukkan tiada

SKALA…No Oil In River

20

28-29 April 2014


Jenis UjianStatistik

Sela & Nisbah

Parametrik

BukanParametrik

Nominal &

OrdinalBukan

Parametrik

PEMILIHAN UJIAN STATISTIK

21

TUJUAN

JENIS DATA

Parametrik Bukan Parametrik

Menerangkan satu kumpulan Mean, SDMedian, interquartile

range

Perbandingan satu kumpulan

menggunakan satu nilai

One-sample

T- testWilcoxon test

Membandingkan dua kumpulan

berbeza

Independent

T- testMann-Whitney test

Membanding dua kumpulan

berpasanganPaired T-test Wilcoxon test

22

28-29 April 2014


TUJUAN

JENIS DATA

Parametrik Bukan Parametrik

Membandingkan tiga atau

lebih kumpulan berbezaOne-way ANOVA Kruskal-Wallis test

Korelasi dua variabel Pearson correlationSpearman

correlation

Meramal nilai dari variabel

lain yang diukur (Predict value

from another measured

variable)

Simple linear regression

or

Nonlinear regression

Nonparametric

regression**

Meramal nilai dari beberapa

variabel lain yang diukur

(Predict value from several

measured or binomial variables)

Multiple linear regression* or

Multiple nonlinear regression**

23

IV

-Data diskret

(Nominal / Ordinal)

DV

-Data continuous

(Interval / ratio)

Jenis Ujian

1

(cth. Lelaki/perempuan)

1

(cth. Pencapaian)

Ujian-t

1

(cth. Melayu/Cina/India)

1 Anova Satu

Hala

2

(cth. Bangsa & Jantina)

1 ANOVA Dua

Hala

1 @ > 2 @ > MANOVA

24

28-29 April 2014


• Apa yang ingin dikaji?

• Kumpulan mana?

• Berapa pembolehubah?

• Deskriptif? Inferensi?

• Pernyataan persoalan kajian:

“Adakah terdapat perbezaan yang signikan skor

gaya pembelajaran pelajar di kolej A berdasarkan

jantina?”

25

• Hipotesis = andaian kajian yg akan diuji

• Jenis Hipotesis = HA & Ho

• Ho

• = Min Sampel Tidak Berbeza Dari Min Populasi

• Pengiraan dan perbandingan t obtain dan t kritikal

• T obtain > t kritikal (alfa=0.05), maka wujud perbezaan yg signifikan kedua-dua min skor sampel dan min populasi

• Why Null?

“It is difficult to prove something to be TRUE, but is much easier to prove something to be NOT TRUE.”

26

28-29 April 2014


SOALAN KAJIAN PERLU/TIDAK PENGUJIAN HIPOTESIS

27

1• Nyatakan Ho & Ha

2• Setkan darjah keyakinan/alfa (kajian sains

sosial=.05)

3• Laporkan ujian statistik & kesignifikanan

4• Membuat keputusan (terima / gagal)

5• Kesimpulan

Ho BETUL Ho SALAH

TOLAK Ho RALAT JENIS I KEPUTUSAN TEPAT

GAGAL TOLAK Ho KEPUTUSAN TEPAT RALAT JENIS II

28

Tolak Ho = Terdapat perbezaan/hubungan yg

signifikan

Gagal tolak Ho = Tidak terdapat perbezaan/hubungan

yg signifikan

Ralat Jenis 1 (alfa) = Tolak Ho yg betul

Ralat Jenis 2 (beta) = Terima Ho yg salah

28-29 April 2014


Ho: Tidak terdapat perbezaan yg signifikan antara

penggunaan koswer Sains dengan kaedah

konvensional terhadap pemahaman konsep sains

pelajar sekolah rendah.

29

Jika memang sebenarnya tiada kesan yang

signifikan antara penggunaan koswer berbanding

kaedah konvensional (Ho memang betul) tetapi

anda TOLAK kerana kajian anda menunjukkan ada

perbezaan maka implikasinya melibatkan

pelaburan jutaan ringgit bagi membangunkan

koswer dan membeli peralatan ICT sedang

aplikasinya tidak berkesan. Kerugian kepada

kewangan negara!.

30

28-29 April 2014


Jika memang sebenarnya ada kesan yang

signifikan antara penggunaan koswer berbanding

kaedah konvensional (Ho perlu ditolak) tetapi anda

TERIMA kerana kajian anda menunjukkan tiada

perbezaan maka implikasinya tiada polisi

dijalankan bagi membangunkan koswer dan

membeli peralatan ICT sedang ianya berkesan

kepada pelajar. Kerugian ini lebih serius (secara

relatif) dan berterusan kerana melibatkan satu

pendekatan berkesan yang dapat membantu pelajar

dalam pembelajaran tetapi tidak dilaksanakan.31

• Type 1 Error (T1E): Tolak Ho yang BETUL (patutnya tolak

yang salah ler...)

• Type 2 Error (T2E): Terima Ho yang SALAH (patutnya terima

yang betul...)

• Mana lebih serius - jika ada orang minat kat anak dara kita,

katakan nama dia Ho...dan kita tak kenal orang tu…

• Maka tolak Ho walaupun dia BETUL tak apa (boleh cari lain..)

dari kita terima Ho yang SALAH…naya anak dara kita…

32

28-29 April 2014


1. Starting SPSS [From Start Button/Short Cut Desktop]

2. Opening an Existing Data File

File: survey5ED.sav

33

34

28-29 April 2014


3. Starting a New Data File

FileNewData

4. Defining the Variables

35

5. Procedure for Defining Your Variables (Name; Type;

Width; Decimals; Label; Value; Missing; Align; Measure)

36

28-29 April 2014


1. To enter data, you need to have the Data View active. Click on

the Data View tab at the bottom left-hand side of the screen of

the Data Editor window. A spreadsheet should appear with your

newly defined variable names listed across the top.

2. Click on the first cell of the data set (first column, first row).

3. Type in the number (if this variable is ID, this should be 1).

4. Press the right arrow key on your keyboard; this will move the

cursor into the second cell, ready to enter your second piece of

information for case number 1.

37

5. Move across the row, entering all the information for case 1,

making sure that the values are entered in the correct columns.

6. To move back to the start, press the Home key on your

keyboard (on some computers you may need to hold the Ctrl key

or the Fn key down and then press the Home key). Press the down

arrow to move to the second row, and enter the data for case 2.

7. If you make a mistake and wish to change a value, click in the

cell that contains the error. Type in the correct value and then

press the right arrow key.

38

28-29 April 2014


i. Memulakan SPSS

ii. Menyediakan Template Data

iii. Memasukkan Data

39

1. To delete a case

2. To insert a case between existing cases

3. To delete a variable

4. To insert a variable between existing variables

5. To move an existing variable

6. To split the data file

40

28-29 April 2014


Checking for error

Finding the error in the data file

Correcting the error in

the data file

41

File: error5ED.sav

1. From the main menu at the top of the screen, click on Analyze,

then click on Descriptive Statistics, then Frequencies.

2. Choose the variables that you wish to check (e.g. sex, marital,

educ.).

3. Click on the arrow button to move these into the Variable box.

4. Click on the Statistics button. Tick Minimum and Maximum in

the Dispersion section.

5. Click on Continue and then on OK

42

28-29 April 2014


1. From the menu at the top of the screen, click on Analyze, then

click on Descriptive statistics, then Descriptives.

2. Click on the variables that you wish to check. Click on the arrow

button to move them into the Variables box (e.g. age).

3. Click on the Options button. You can ask for a range of

statistics. The main ones at this stage are mean, standard

deviation, minimum and maximum. Click on the statistics you wish

to generate.

4. Click on Continue, and then on OK

43

Method 1

1. Click on the Data menu and choose Sort Cases.

2. In the dialogue box that pops up, click on the variable that you

know has an error (e.g. sex) and then on the arrow to move it into

the Sort By box. Click on either ascending or descending

(depending on whether you want the higher values at the top or

the bottom). For sex, we want to find the person with the value of

3, so we would choose descending.

3. Click on OK.

44

28-29 April 2014


Method 2

1. Make sure that the Data Editor window is open and on the screen with

the data showing.

2. Click on the variable name in which the error has occurred (e.g. sex).

3. Click once to highlight the column.

4. Click on Edit from the menu across the top of the screen. Click on Find.

5. In the Find box, type in the incorrect value that you are looking for (e.g. 3).

6. Click on Find Next. SPSS will scan through the file and will stop at the first

occurrence of the value that you specified. Take note of the ID number of

this case (from the first column). You will need this to check your records

or questionnaires to find out what the value should be.

7. Click on Find Next again if you need to continue searching for other

cases with the same incorrect value. In this example, we know from the

Frequencies output that there is only one incorrect value of 3.

8. Click on Close when you have finished searching.

45

Rujuk ID soal selidik Semak Semula Borang

Soal Selidik Buat Pembetulan

46

28-29 April 2014


• Descriptive statistics

• Using graphs to describe and explore the data

1. Frekuensi

2. Deskriptif

3. Crosstab

4. Graf/Carta/Histogram

47

• Menyediakan jadual, graf, carta, dan crosstab.

• Selamat MENCUBA….

• Jangan lupa paste Output pada MS Word…

48

28-29 April 2014


Procedure for assessing normality using Explore

1. From the menu at the top of the screen click on Analyze, then select Descriptive Statistics, then Explore.

2. Click on the variable(s) you are interested in (e.g. Total perceived stress: tpstress). Click on the arrow button to move them into the Dependent List box.

3. In the Label Cases by: box, put your ID variable.

4. In the Display section, make sure that Both is selected.

5. Click on the Statistics button and click on Descriptives and Outliers. Click on Continue.

6. Click on the Plots button. Under Descriptive, click on Histogram. Click on Normality plots with tests. Click on Continue.

7. Click on the Options button. In the Missing Values section, click on Exclude cases pairwise. Click on Continue and then OK

Skewness & kurtosis

Test of NormalityKolmogorov-Smirnov…non-sig.=normal

Big samples=Central Limit Theorem

File: survey5ED.sav

49

Data file: staffsurvey5ED.sav.

1. Follow the procedures covered in this chapter to generate appropriate descriptive

statistics to answer the following questions.

(a) What percentage of the staff in this organisation are permanent

employees? (Use the variable employstatus.)

(b) What is the average length of service for staff in the organisation?

(Use the variable service.)

(c) What percentage of respondents would recommend the organisation to

others as a good place to work? (Use the variable recommend.)

2. Assess the distribution of scores on the Total Staff Satisfaction Scale (totsatis) for

employees who are permanent versus casual (employstatus).

(a) Are there any outliers on this scale that you would be concerned about?

(b) Are scores normally distributed for each group?

50

28-29 April 2014


HISTOGRAM

Procedure for creating a histogram

1. From the menu click on Graphs, then select Legacy Dialogs. ChooseHistogram.

2. Click on your variable of interest and move it into the Variable box.This should be a continuous variable (e.g. Total perceived stress:tpstress).

3. If you would like to generate separate histograms for differentgroups (e.g. male/female), you could put an additional variable (e.g.sex) in the Panel by: section. Choose Rows if you would like the twographs on top of one another, or Column if you want them side by side.In this example, I will put the sex variable in the Column box.

4. Click on OK

51

File: survey5ED.sav

BAR GRAPH:

Procedure for creating a bar graph

1. From the menu at the top of the screen, click on Graphs, then select LegacyDialogs. Choose Bar. Click on Clustered.

2. In the Data in chart are section, click on Summaries for groups of cases.Click on Define.

3. In the Bars represent box, click on Other statistic (e.g. mean).

4. Click on the continuous variable you are interested in (e.g. Total perceived

stress: tpstress). This should appear in the box listed as Mean (Total perceivedstress). This indicates that the mean on the Perceived Stress Scale for thedifferent groups will be displayed.

5. Click on your first categorical variable (e.g. agegp3). Click on the arrowbutton to move it into the Category axis box. This variable will appear acrossthe bottom of your bar graph (X axis).

6. Click on another categorical variable (e.g. sex) and move it into the DefineClusters by: box. This variable will be represented in the legend.

7. If you would like to display error bars on your graph, click on the Optionsbutton and click on Display error bars. Choose what you want the bars torepresent (e.g. confidence intervals).

8. Click on Continue and then OK

52

28-29 April 2014


LINE GRAPH:

Procedure for creating a line graph

1. From the menu at the top of the screen, select Graphs, then Legacy Dialogs,then Line.

2. Click on Multiple. In the Data in Chart Are section, click on Summaries forgroups of cases. Click on Define.

3. In the Lines represent box, click on Other statistic. Click on the continuousvariable you are interested in (e.g. Total perceived stress: tpstress). Click on thearrow button. The variable should appear in the box listed as Mean (Totalperceived stress). This indicates that the mean on the Perceived Stress Scale forthe different groups will be displayed.

4. Click on your first categorical variable (e.g. agegp3). Click on the arrowbutton to move it into the Category Axis box. This variable will appear acrossthe bottom of your line graph (X axis).

5. Click on another categorical variable (e.g. sex) and move it into the DefineLines by: box. This variable will be represented in the legend.

6. If you would like to add error bars to your graph, you can click on theOptions button. Click on the Display error bars box and choose what youwould like the error bars to represent (e.g. confi dence intervals).

7. Click on OK

53

Procedure for creating a boxplot

1. From the menu at the top of the screen, click on Graphs, then

select Legacy Dialogs and then Boxplot.

2. Click on Simple. In the Data in Chart Are section, click on

Summaries for groups of cases. Click on the Define button.

3. Click on your continuous variable (e.g. Total Positive Affect:

tposaff). Click on the arrow button to move it into the Variable

box.

4. Click on your categorical variable (e.g. sex). Click on the arrow

button to move it into the Category axis box.

5. Click on ID and move it into the Label cases box. This will allow

you to identify the ID numbers of any cases with extreme values.

6. Click on OK

54

28-29 April 2014


File: staffsurvey5ED.sav.

1. Generate a histogram to explore the distribution of scores on the

Staff Satisfaction Scale (totsatis).

2. Generate a bar graph to assess the staff satisfaction levels for

permanent versus casual staff employed for less than or equal to 2

years, 3 to 5 years and 6 or more years. The variables you will need

are totsatis, employstatus and servicegp3.

3. Generate a boxplot to explore the distribution of scores on the Staff

Satisfaction Scale (totsatis) for the different age groups (age).

4. Generate a line graph to compare staff satisfaction for the different

age groups (use the agerecode variable) for permanent and casual

staff.

55

CALCULATING TOTAL SCALE SCORE

COLLAPSING A CONTINUOUS VARIABLE INTO GROUP

56

28-29 April 2014


File: survey5ED.sav.

1. From the menu at the top of the screen, click on Transform, then click on

Recode Into Different Variables.

2. Select the items you want to reverse (op2, op4, op6). Move these into the

Input Variable - Output Variable box.

3. Click on the first variable (op2) and type a new name in the Output

Variable section on the right-hand side of the screen and then click the Change

button. I have used Rop2 in the existing data file. If you wish to create your own

(rather than overwrite the ones already in the data file), use another name (e.g.

revop2). Repeat for each of the other variables you wish to reverse (op4 and

op6).

4. Click on the Old and new values button.

In the Old value section, type 1 in the Value box.

In the New value section, type 5 in the Value box (this will change all

scores that were originally scored as 1 to a 5).

57

5. Click on Add. This will place the instruction (1 → 5) in the boxlabelled Old > New.

6. Repeat the same procedure for the remaining scores. For example:

Old value—type in 2 New value—type in 4 Add




Always double-check the item numbers that you specify for recodingand the old and new values that you enter. Not all scales use a five-point scale; some have four possible responses, some six and someseven. Check that you have reversed all the possible values for yourparticular scale.


58

28-29 April 2014


Procedure for calculating total scale scores

1. From the menu at the top of the screen, click on Transform, then click

on Compute Variable.

2. In the Target Variable box, type in the new name you wish to give to

the total scale scores. (It is useful to use a T prefix to indicate total

scores, as this makes them easier to find in the list of variables when you

are doing your analyses.)

Important: make sure you do not accidentally use a variable name that

has already been used in the data set. If you do, you will lose all the

original data—potential disaster—so check your codebook.

3. Click on the Type and Label button. Click in the Label box and type

in a description of the scale (e.g. total optimism). Click on Continue.

59

4. From the list of variables on the left-hand side, click on the first itemin the scale (op1).

5. Click on the arrow button to move it into the Numeric Expressionbox.

6. Click on + on the calculator.

7. Repeat the process until all scale items appear in the box. In thisexample we would select the unreversed items first (op3, op5) and thenthe reversed items (obtained in the previous procedure), which arelocated at the bottom of the list of variables (Rop2, Rop4, Rop6).

8. The complete numeric expression should read as follows:

op1+op3+op5+Rop2+Rop4+Rop6.

9. Double-check that all items are correct and that there are + signs inthe right places. Click OK

60

28-29 April 2014


Procedure for collapsing a continuous variable into groups

1. From the menu at the top of the screen, click on Transform and chooseVisual Binning.

2. Select the continuous variable that you want to use (e.g. age). Transfer it intothe Variables to Bin box. Click on the Continue button.

3. In the Visual Binning screen, a histogram showing the distribution of agescores should appear.

4. In the section at the top labelled Binned Variable, type the name for thenew categorical variable that you will create (e.g. Agegp3). You can alsochange the suggested label that is shown (e.g. age in 3 groups).

5. Click on the button labelled Make Cutpoints. In the dialogue box thatappears, click on the option Equal Percentiles Based on Scanned Cases. In thebox Number of Cutpoints, specify a number one less than the number ofgroups that you want (e.g. if you want three groups, type in 2 for cutpoints). Inthe Width (%) section below, you will then see 33.33 appear. This means thatSPSS will try to put 33.3 per cent of the sample in each group. Click on theApply button.

6. Click on the Make Labels button back in the main dialogue box. This willautomatically generate value labels for each of the new groups created.

7. Click on OK

61

Procedure for recoding a categorical variable

1. From the menu at the top of the screen, click on Transform, then on Recodeinto Different Variables. (Make sure you select ‘different variables’, as thisretains the original variable for other analyses.)

2. Select the variable you wish to recode (e.g. educ). In the Name box, type aname for the new variable that will be created (e.g. educrec). Type in anextended label if you wish in the Label section. Click on the button labelledChange.

3. Click on the button labelled Old and New Values.

4. In the section Old Value, you will see a box labelled Value. Type in the firstcode or value of your current variable (e.g. 1). In the New Value section, typein the new value that will be used (or, if the same one is to be used, type thatin). In this case I will recode to the same value, so I will type 1 in both the OldValue and New Value sections. Click on the Add button.

5. For the second value, I would type 2 in the Old Value but in the New Value Iwould type 1. This will recode all the values of both 1 and 2 from the originalcoding into one group in the new variable to be created with a value of 1.

6. For the third value of the original variable, I would type 3 in the Old Valueand 2 in the New Value. This is just to keep the values in the new variable insequence. Click on Add. Repeat for all the remaining values of the originalvalues. In the table Old > New, you should see the following codes for thisexample: 1→1; 2→1; 3→2; 4→3; 5→4; 6→5.

7. Click on Continue and then on OK62

28-29 April 2014


63

• Merujuk kpd sejauhmana sst.alat ukur dpt. Memberikan ukuran

terhadap apa yg patut diukur (Tuckman, 1978; Mohd Majid,

1990; Anastasi&Urbina 1997).

• Darjah ketepatan ujian/alat ukur tersebut mengukur perkara

atau kualiti yg diukur oleh ujian tersebut (Anastasi, 1990 dlm

Mohamad Sahari, 2008).

• Cth.: Alat penimbang sah untuk mengukur berat badan, TETAPI

kurang sah untuk mengukur darjah kesihatan seseorang.

• Sesuatu alat yg berupaya mengukur dengan tepat sst

pembolehubah yg ditetapkan adalah dianggap SAH sbg alat

pengukur bg pembolehubah tersebut.

64

28-29 April 2014


• Kesahan Muka (Face validity) – bahasa, ejaan,

kejelasan, kurang saintifik & boleh disemak oleh org

bukan pakar bidang

• Kesahan Kandungan (Content validity) – sejauh mana

alat ukur itu mewakili bidang/kandungan yg diukur.

MESTI disahkan oleh pakar bidang.

• Kesahan Kriteria (Criterion validity)

• Terbahagi kpd 2:

i. Kesahan serentak (concurrent);

ii. Kesahan Jangkaan (Predictive)65

• K.serentak- kesetaraan…skor instrumen yg dibina setara/hampir

setara dgn instrumen org lain. Cth.,Soalan Matematik pada tahun

2007 (Lembaga Pep.) dgn soalan Matematik yg dibina pada 2012

(menguji topik yg sama) – menunjukkan keputusan yg tidak jauh

berbeza apabila diuji utk tempoh masa yg dekat.

• K.Jangkaan – dpt.menjangka keputusan akan datang (3-6 bulan).

Lazim utk ujian penyaringan. Cth. IMSAK di IPG).

• “the ability of a survey instrument to forecast future events,

behaviours, attitudes, or outcome.” (Litwin 1995)

• Kesahan Gagasan (Construct validity)

• Item yg menguji konstruk yang sama, skor ujian adalah ‘correlated’;

tetapi jika mengukur konstruk yang berlainan akan mencatatkan

korelasi yg rendah

• Ringkasnya, item yg mewakili sesuatu konstruk perlu mempunyai ciri

sepunya!

66

28-29 April 2014


kestabilan & ketekalan/konsistensi sst alat/instrumen

mengukur sst konsep, pd bila2 masa, dlm apa jua

keadaan.

Memberi skor yg sama walau diukur berulang kali

“…reliability doesn't ensure validity…” (Hair et al.,

1995)

67

• Inter-Rater or Inter-Observer Reliability

Used to assess the degree to which different raters/observers

give consistent estimates of the same phenomenon.

• Test-Retest Reliability

Used to assess the consistency of a measure from one time to

another.

• Parallel-Forms Reliability

Used to assess the consistency of the results of two tests

constructed in the same way from the same content domain.

• Internal Consistency Reliability

Used to assess the consistency of results across items within a

test.

68

28-29 April 2014


• Cronbach (1946):

•<0.6 : rendah

•0.6 – 0.8 : diterima

•>0.8 : baik

•DeVellis (2003), >0.7

69

1. From the menu at the top of the screen, click on Analyze, select Scale,

then Reliability Analysis.

2. Click on all of the individual items that make up the scale (e.g. item1,

item2, item3, item4, item5). Move these into the box marked Items.

3. In the Model section, make sure Alpha is selected.

4. In the Scale label box, type in the name of the scale or subscale (Life

Satisfaction).

5. Click on the Statistics button. In the Descriptives for section, select Item,

Scale, and Scale if item deleted. In the Inter-Item section, click on

Correlations. In the Summaries section, click on Correlations.


File: survey5ED.sav

70

28-29 April 2014


File: staffsurvey5ED.sav

Check the reliability of the Staff Satisfaction Survey, which is

made up of the agreement items in the data fi le: Q1a to Q10a.

None of the items of this scale needs to be reversed.

71

• Ujian-T

• ANOVA SEHALA

• ANOVA 2 HALA

72

28-29 April 2014


Untuk menguji perbezaan Min antara DUA kategori/kumpulanpembolehubah tak bersandar/bebas.

Model yang digunakan bergantung sama ada sampel yang terlibat itubersandar atau tidak.

Jika sampel tidak bersandar, kita perlu terlebih dahulu menentukansama ada varians kedua-dua sampel itu homogenus atau tidak(heterogenus). Ujian yang boleh digunakan ialah Ujian-F (Levene'sTest).

Sekiranya Ujian-F menunjukkan bahawa varians sampel adalahhomogenus, kita perlu menggunakan formula Ujian-t untuk variansyang disatukan (Pooled Varians estimate/Equal varians assumed)

Sekiranya Ujian-F menunjukkan bahawa varians sampel adalahheterogenus, kita perlu menggunakan formula Ujian-t untuk variansyang berasingan (Separate Varians estimate/Equal varians notassumed)

Jika sampel-sampel yang terlibat itu bersandar maka kita perlumenggunakan formula Ujian-t untuk sampel yang bersandar.

UJIAN-t

73

UJIAN-t

SAMPEL TAK BERSANDAR (Independent Sample t-Test)

SAMPEL BERSANDAR (Paired Sample t-Test)

UJIAN-F (Leven’s Test) Bagi menguji

Kemohogenan Varians

VARIANS HOMOGENUS

VARIANS HETEROGENUS

MENGGUNAKAN UJIAN-t VARIANS YANG DISATUKAN (Pooled Varians Estimate/Equal

Varians Assumed)

MENGGUNAKAN UJNIAN-t VARIANS YANG BERASINGAN (Separate Varians Estimate/Equal

Varians Not Assumed

MENGGUNAKAN UJIAN-t SAMPEL

YANG BERSANDAR

74

28-29 April 2014


Example of research question: Is there a significant difference in

the mean self-esteem scores for males and females?

What you need: Two variables:

• one categorical, independent variable (e.g. males/females)

• one continuous, dependent variable (e.g. self-esteem scores).

What it does: An independent-samples t-test will tell you whether

there is a statistically significant difference in the mean scores for

the two groups (i.e. whether males and females differ significantly

in terms of their self-esteem levels). In statistical terms, you are

testing the probability that the two sets of scores (for males and

females) came from the same population.

75

Procedure for independent-samples t-test

1. From the menu at the top of the screen, click on Analyze, then

select Compare means, then Independent Samples T test.

2. Move the dependent (continuous) variable (e.g. total self-

esteem: tslfest) into the Test variable box.

3. Move the independent variable (categorical) variable (e.g. sex)

into the section labelled Grouping variable.

4. Click on Define groups and type in the numbers used in the

data set to code each group. In the current data fi le, 1=males,

2=females; therefore, in the Group 1 box, type 1, and in the

Group 2 box, type 2. If you cannot remember the codes used,

right click on the variable name and then choose Variable

Information from the pop-up box that appears. This will list the

codes and labels.


File: survey5ED.sav

76

28-29 April 2014


Procedure for paired-samples t-test

1. From the menu at the top of the screen, click on

Analyze, then select Compare Means, then Paired

Samples T test.

2. Click on the two variables that you are interested in

comparing for each subject (e.g. fost1: fear of stats

time1, fost2: fear of stats time2) and move them into the

box labelled Paired Variables by clicking on the arrow

button. Click on OK

77


Follow the procedures in the section on independent-

samples t-tests to compare the mean staff satisfaction

scores (totsatis) for permanent and casual staff

(employstatus).

Is there a significant difference in mean satisfaction

scores?

78

28-29 April 2014


Tujuan: Mengenal pasti sama ada terdapat perbezaan skor min

yang signifikan pada 1 DV (berskala interval) yang melibatkan 3

atau lebih kumpulan.

• ANOVA Satu Hala akan menunjukkan sama ada terdapat

perbezaan yang signifikan dalam skor min pembolehubah

bersandar (dependent variable) merentasi 3 kumpulan

responden yang dikaji. Ujian Post-hoc pula digunakan untuk

mengenalpasti kumpulan manakah yang berbeza.

Andaian: sama seperti t-test

79

UJIAN ANALISIS VARIANS SATU-HALA (ANOVA SATU-HALA)

Untuk menguji perbezaan Min antara DUA atau lebihkategori/kumpulan pembolehubah tak bersandar/ bebas.

Terdapat dua punca variasi dalam ujian ini iaitu variasi dalamkumpulan yang bebas dari kesan rawatan yang dianggap sebagaivarians ralat dan variasi antara kumpulan yang berlaku keranakesan rawatan yang dianggap sebagai varians daripada kesanrawatan.

Ujian-F digunakan untuk menentukan sama ada min kumpulan-kumpulan itu berbeza secara signifikan atau tidak.

Sekiranya Ujian-F menunjukkan perbezaan yang signifikan antarakumpulan-kumpulan tersebut maka ujian perbandingan berganda(multiple comparison) perlu dilakukan bagi menentukanperbezaan min antara pasangan-pasangan min. Ujianperbandingan berganda yang selalu digunakan ialah Ujian Tukeyatau Ujian Scheffe.

Ujian ini perlu dijalankan kerana Ujian ANOVA tidak menjelaskansecara khusus perbezaan min yang sebenar bagi setiap pasangan,ia hanya menyatakan secara keseluruhan min-min kumpulanadalah tidak sama atau berbeza secara signifikan. 80

28-29 April 2014


• Contoh Soalan Kajian: Adakah terdapat perbezaan yang

signifikan tahap kualiti peribadi pengetua kanan berdasarkan

persepsi guru berdasarkan pengalaman mengajar guru?

• Hipotesis:

Ho : µ1 = µ2 = µ3

Ho : Tidak terdapat perbezaan yang signifikan skor min tahap

kualiti peribadi pengetua kanan berdasarkan persepsi guru

mengikut pengalaman mengajar guru.

81

• Dalam Post Hoc, nak guna Tukey atau Scheffe? Lazimnya, Scheffe digunakan

bagi N tiga atau lebih kumpulan berbeza, manakala Tukey memerlukan N

bagi setiap kumpulan adalah sama!

• Keputusan Post Hoc wajib dilihat dan dilaporkan hanya sekiranya ujian

Anova didapati terdapat perbezaan yang signifikan (lihat Sig.), Jika nilai

Sig. melebihi had yang ditetapkan oleh pengkaji (cth. p<0.05), maka tidak

perlu melihat keputusan post hoc.

• Untuk melaporkan keputusan ujian Anova, pengkaji perlu mengemukakan

Jadual Deskriptif, Jadual Ujian Anova, dan Jadual Post Hoc (jika Nilai Sig. <

0.05).

• Nilai Eta Squared dalam Anova memerlukan pengkaji melakukan pengiraan

sendiri dengan menggunakan formula di bawah dan seterusnya tentukan

sama ada tinggi/sederhana/rendah berdasarkan saranan Cohen atau yang

lain.

• Eta squared = Sum of squares between groups

Total sum of squares

82

28-29 April 2014


Example of research question: Is there a difference in optimismscores for young, middle-aged and old participants?

What you need: Two variables:

• one categorical independent variable with three or more distinctcategories. This can also be a continuous variable that has beenrecoded to give three equal groups (e.g. age group: participantsdivided into three age categories, 29 and younger, between 30and 44, 45 or above)

• one continuous dependent variable (e.g. optimism scores).

What it does: One-way ANOVA will tell you whether there aresignificant differences in the mean scores on the dependentvariable across the three groups. Post-hoc tests can then be usedto find out where these differences lie.

83

Procedure for one-way between-groups ANOVA with post-hoc tests

1. From the menu at the top of the screen, click on Analyze, then select

Compare Means, then One-way ANOVA.

2. Click on your dependent (continuous) variable (e.g. Total optimism:

toptim). Move this into the box marked Dependent List by clicking on

the arrow button.

3. Click on your independent, categorical variable (e.g. age 3 groups:

agegp3). Move this into the box labelled Factor.

4. Click the Options button and click on Descriptive, Homogeneity of

variance test, Brown-Forsythe, Welch and Means Plot.

5. For Missing values, make sure there is a dot in the option marked

Exclude cases analysis by analysis. Click on Continue.

6. Click on the button marked Post Hoc. Click on Tukey.

7. Click on Continue and then OK84

survey5ED.sav

28-29 April 2014



Conduct a one-way ANOVA with post-hoc tests (if

appropriate) to compare staff satisfaction scores

(totsatis) across each of the length of service categories

(use the servicegp3 variable).

85

• Tujuan: Mengenal pasti sama ada terdapat perbezaan skor min yang

signifikan pada 1 DV (berskala interval) yang melibatkan 2 IV (jantina &

bangsa).

• Andaian: kenormalan, sampel rawak, taburan normal

• Soalan Kajian: Adakah terdapat perbezaan yang signifikan tahap

gangguan emosi berdasarkan jantina dan bangsa?

• Hipotesis:

Ho1: Tidak terdapat perbezaan yang signifikan tahap gangguan emosi

berdasarkan jantina.

Ho2: Tidak terdapat perbezaan yang signifikan tahap gangguan emosi

berdasarkan bangsa.

Ho3: Tidak terdapat kesan interaksi yang signifikan antara jantina dan

bangsa terhadap tahap gangguan emosi.

86

28-29 April 2014


Example of research question: What is the impact of age and genderon optimism? Does gender moderate the relationship between age andoptimism?

What you need: Three variables:

• two categorical independent variables (e.g. sex: males/females; agegroup: young, middle, old)

• one continuous dependent variable (e.g. total optimism).

What it does: Two-way ANOVA allows you to simultaneously test for theeffect of each of your independent variables on the dependentvariable and also identifies any interaction effect. For example, itallows you to test for (a) sex differences in optimism, (b) differences inoptimism for young, middle and old participants, and (c) the interactionof these two variables-is there a difference in the effect of age onoptimism for males and females?

87

CONTOH SOALAN KAJIAN

1. Adakah terdapat perbezaan tahap budaya penyelidikan

berdasarkan lokasi sekolah dan jenis sekolah?

Hipotesis Kajian:

Ho.1. Tidak terdapat perbezaan yang signifikan dari segi tahap

budaya penyelidikan antara guru sekolah bandar dengan

guru sekolah luar bandar.

Ho.2. Tidak terdapat perbezaan yang signifikan tahap budaya

penyelidikan antara guru sekolah menengah dengan guru

sekolah rendah.

Ho.3. Tidak terdapat kesan interaksi yang signifikan antara lokasi

sekolah dan jenis sekolah terhadap tahap budaya

penyelidikan di kalangan guru.

88

28-29 April 2014


JADUAL 1

Perbandingan Skor Min Tahap Budaya Penyelidikan Di Kalangan Guru

Berdasarkan Lokasi Sekolah dan Jenis Sekolah

Lokasi Jenis Sekolah Min

Sisihan

Piawai Bil (n)

Bandar Sek. Menengah

Sek. Rendah

Jumlah

3.479

3.511

3.495

0.453

0.448

0.450

120

130

250

Luar Bandar Sek. Menengah

Sek. Rendah

Jumlah

3.278

3.323

3.300

0.558

0.574

0.565

233

214

337

Jumlah Sek Menengah

Sek. Rendah

Jumlah

3.347

3.394

3.370

0.532

0.537

0.535

353

344

69789

JADUAL 2

Ujian ANOVA Dua-Hala Perbandingan Tahap Budaya Penyelidikan Di

Kalangan Guru Berdasarkan Lokasi Sekolah dan Jenis Sekolah

Kesan Utama Jumlah

Kuasadua

Darjah

Kebebasan

Min

Kuasadua

Nilai-

F

Tahap Sig.

(p)

Lokasi

Jenis Sekolah

Interaksi

Lokasi*J. Sek.

Ralat

Jumlah

6.032

0.233

0.006

192.509

198.935

1

1

1

693

696

6.032

0.233

0.006

0.278

5.361

6.574

0.000

0.001*

0.360

0.877

90

28-29 April 2014


Berdasarkan jadual di atas didapati terdapat perbezaan yang signifikan tahapbudaya penyelidikan antara guru sekolah bandar dengan guru sekolah luarbandar (F (1,693) =21.716; p=0.001). Guru sekolah bandar mempunyai budayapenyelidikan yang lebih (min=3.495) berbanding dengan guru sekolah luarbandar (min=3.300)

Dari segi jenis sekolah, didapati tidak terdapat perbezaan yang signifikantahap budaya penyelidikan antara guru sekolah menengah dengan gurusekolah rendah (F=0.840; dk=1.693; p=0.360). Ini bermakna budayapenyelidikan di kalangan guru sekolah menengah dan guru sekolah rendahadalah pada tahap yang sama.

Dari segi kesan interaksi pula, didapati tidak terdapat kesan interaksi yangsignifikan antara lokasi sekolah dengan jenis sekolah terhadap budayapenyelidikan di kalangan guru (F=0.024; dk=1.693; p=0.877). Rajah 1 dibawah menunjukkan graf kesan interaksi antara lokasi sekolah dan jenissekolah terhadap budaya penyelidikan di kalangan guru.

Contoh penjelasan

91

Budaya Penyelidikan Di Kalangan Guru

lokasi

luar bandarbandar

Sko

r M

in

3.6

3.5

3.4

3.3

3.2

jenis sekolah

sek. menengah

sek. rendah

92

28-29 April 2014


Berdasarkan Rajah 1, dapat dirumuskan bahawa budaya penyelidikan dikalangan guru adalah berbeza secara signifikan antara guru sekolahbandar dengan guru sekolah luar bandar. Tahap budaya penyelidikan dikalangan guru sekolah bandar adalah lebih tinggi berbanding dengan gurusekolah luar bandar sama ada bagi sekolah menengah mahupun sekolahrendah.

93


Conduct a two-way ANOVA with post-hoc tests (if

appropriate) to compare staff satisfaction scores

(totsatis) across each of the length of service categories

(use the servicegp3 variable) for permanent versus

casual staff (employstatus).

94

28-29 April 2014


Example of research question: Is there a relationship between

the amount of control people have over their internal states and

their levels of perceived stress? Do people with high levels of

perceived control experience lower levels of perceived stress?

What you need: Two variables: both continuous variables (two

values).

What it does: Correlation describes the relationship between two

continuous variables, in terms of both the strength of the

relationship and the direction.

95

Procedure for requesting Pearson r or Spearman rho


Correlate, then Bivariate.

2. Select your two variables and move them into the box markedVariables (e.g. Total perceived stress: tpstress, Total PCOISS: tpcoiss). Ifyou wish you can list a whole range of variables here, not just two. In theresulting matrix, the correlation between all possible pairs of variableswill be listed. This can be quite large if you list more than just a fewvariables.

3. In the Correlation Coefficients section, the Pearson box is the defaultoption. If you wish to request the Spearman rho (the non-parametricalternative), tick this box instead (or as well).

4. Click on the Options button. For Missing Values, click on the Exclude

cases pairwise box. Under Options, you can also obtain means andstandard deviations if you wish.

5. Click on Continue and then on OK

File: survey5ED.sav

96

28-29 April 2014


small r=.10 to .29

Medium r=.30 to .49

large r=.50 to 1.0

Cohen (1988, pp. 79–81)

97

Data file: sleep5ED.sav.

Check the strength of the correlation between

scores on the Sleepiness and Associated

Sensations Scale (totSAS) and the Epworth

Sleepiness Scale (ess).

98

28-29 April 2014


Example of research questions:

1. How well do the two measures of control (mastery, PCOISS)

predict perceived stress? How much variance in perceived stress

scores can be explained by scores on these two scales?

2. Which is the best predictor of perceived stress: control of

external events (Mastery Scale) or control of internal states

(PCOISS)?

3. If we control for the possible effect of age and socially

desirable responding, is this set of variables still able to predict a

significant amount of the variance in perceived stress?

99

What you need:

• one continuous dependent variable (Total

perceived stress)

• two or more continuous independent variables

(mastery, PCOISS). (You can also use dichotomous

independent variables, e.g. males=1,

females=2.)

100

28-29 April 2014


• What it does: Multiple regression tells you how much

of the variance in your dependent variable can be

explained by your independent variables. It also gives

you an indication of the relative contribution of each

independent variable. Tests allow you to determine the

statistical significance of the results, in terms of both

the model itself and the individual independent

variables.

101


Regression, then Linear.

2. Click on your continuous dependent variable (e.g. Total perceived stress:

tpstress) and move it into the Dependent box.

3. Click on your independent variables (Total Mastery: tmast; Total PCOISS:

tpcoiss) and click on the arrow to move them into the Independent box.

4. For Method, make sure Enter is selected. (This will give you standard multiple

regression.)

5. Click on the Statistics button.

• Select the following: Estimates, Confidence Intervals, Model fit,

Descriptives, Part and partial correlations and Collinearity diagnostics.

• In the Residuals section, select Casewise diagnostics and Outliers outside 3

standard deviations. Click on Continue.

102

survey5ED.sav

28-29 April 2014


6. Click on the Options button. In the Missing Values section, select

Exclude cases pairwise. Click on Continue.

7. Click on the Plots button.

• Click on *ZRESID and the arrow button to move this into the Y box.

• Click on *ZPRED and the arrow button to move this into the X box.

• In the section headed Standardized Residual Plots, tick the Normal

probability plot option. Click on Continue.

8. Click on the Save button.

• In the section labelled Distances, select Mahalanobis box and Cook’s.

• Click on Continue and then OK

103

nota kursus-asas-spss-28-29-april-2014-plpp

Documents