Professional Documents
Culture Documents
JABATAN SAINS
Tel:609 7717 758 (Off)
012 9298705
Email: keri3058@yahoo.com
1
What is research?
Another process of “tool” or sense making
The world is a complex place
Dynamic, ever-changing
Driven by entropy, chaos
Built-in rot, decay, obsolescence
Need to be always in control
From Science: devices and remedies
From Soc. Science: mental tools/strategies
2
PENYELIDIKAN PENDIDIKAN
(EDUCATIONAL RESEARCH)
3
EDUCATIONAL RESEARCH
RESEARCH BERMULA DENGAN ADANYA
PERASAAN TIDAK PUASHATI TERHADAP
SUASANA KERJA,CORAK PENGURUSAN P&p
DAN PRESTASI DIRI
PENYELIDIKAN –PROSEDUR YANG TERATUR
UNTUK UNTUK MEMPEROLEHI
PENGETAHUAN DAN KEMAHIRAN BARU
HASILNYA DINAMAKAN SEBAGAI NISBA
ATAU VARIABLE BARU
4
PP
Proses penyelidikan libatkan kenalpasti
masalah,mengumpul ,menganalisis dan
mentafsir bukti untuk membuat
keputusan
PP ditafsirkan sebagai prosedur teratur
untuk memperolehi pengetahuan dan
kemahiran baru dalam kurikulum
pendidikan.
5
Pendekatan Kuantitatif dan
Pendekatan Kualitatif
• Quantitative approaches is a deductive
process which attempting to provide evidence
for or against a pre-specified objectives
focused on testing preconceived outcomes.
6
Kajian Kualitatif
Definisi: Satu usaha untuk memahami
sesuatu situasi itu dalam keadaannya yang
tersendiri. Bagaimana individu itu bertindak,
berinteraksi, menjalani kehidupan harian
secara neutral, menunjukkan reaksi dalam
menghadapi liku-liku kehidupan yang
ditempuhi, Input akhirnya ialah satu hasil
kajian yang memberi kefahaman yang
mendalam mengenai kehidupan sebenar
responden yang dikaji (Pattom, 1985).
7
Ciri Penyelidikan kualitatif
•Penyelidik adalah instrumen data dan
analisis yang akan dibuat
•Penyelidikan kualitatif melibatkan kerja
lapangan
•Penyelidikan kualitatif bersifat deskriptif
tentang peristiwa, manusia dan proses
•Penyelidikan kualitatif bersifat induktif
8
The differences
Qualitative research
Introduce new theories
Suggest causes
Descriptive, bottom-up
Uses inductive thinking
Quantitative research
Sharpen old/existing tools
Suggest a cure
Prescriptive, top-down
Uses deductive thinking
9
What is research?
Another process of “tool” or sense making
The world is a complex place
Dynamic, ever-changing
Driven by entropy, chaos
Built-in rot, decay, obsolescence
Need to be always in control
From Science: devices and remedies
From Soc. Science: mental tools/strategies
10
Quantitative Research
Sharpen / replace existing practices / tools
Prescribe, top-down intervention
Paradigms, theories & models play Critical
Roles
Justification: “….no study has yet explored
the use of this P / T / M in this context…..”,
Title: “The effects of an IV on a DV among
an MV…..”
11
Quantitative Research
Problem or Need
Identify an alternative
Structure to guide
research: Create a structure
Theoretical Framework to guide research:
Conceptual
Framework
Grand theory
Midrange theory
Micro-range theory
Conceptual Definitions
of Study Variables,
Research Questions, Operational Definitions to Instruments
Hypotheses measure the study variables
12
What is obtained?
A new cure / remedy
A more dynamic & productive paradigm
13
Acute Anomalies
Malaysia:- 5 As + Sc + IS + BSc = killers
PhD + Datukship + CEO = CBT
Car + Motorcycle + License = accidents
Schooling + F in all subjects = millionaire
The US:- Best of everything + Best of
everything + best of everything
= killers
World: Islam + marginalization = terrorists
How to study / solve these problems?
14
Qualitative Research
Reassess known paradigms, theories & models
in specific contexts
Non-invasive data collection
Justification: “….no adequate P / T / M currently
explains this phenomenon…..”,
Title: “Violence in the Malaysian Premier
Schools-A case study”
Or “Social construction of technology in the
Malaysian Smart School-A case study…..”
15
What is obtained?
A new mind set / problem situation
A hidden/grounded theory
16
Qualitative Research
Problem in a
given context
17
Summary
Survey of issues, paradigms, theories, models, frameworks
Suggest
Cured?
a cure Choose
Identify a Collect the
Problem/ P/T/M/F.
Data &
need Develop the
Analyse
Identify instruments
Grounded
hidden
Theory?
Lit. review causes
18
Empat kaedah utama pengumpulan data
kualitatif
• Pemerhatian
• Temubual
• Dokumen
• Imej
19
Dalam beberapa situasi penyelidik
• Mengumpul maklumat melalui pemerhatian
sebagai peserta
• Mengumpul maklumat melalui pemerhatian
sebagai pemerhati
• Melakukan temubual tak berstruktur atau
terbuka dan mencatatkan temubual
• Melakukan temubual tak berstruktur atau
terbuka, merekodkan temubual dan
dalam bentuk audio melakukan transkripsi
temubual
20
Steps in Educational Research
(Contd.)
5) define the variables involved in operational terms
[e.g. Academic achievement are grades assigned by
teachers; or Intelligence is the score obtained in
Cattle’s Culture Fair Intelligence Test]
6) Design instruments to measure the variables
involved
7) Pilot test the instruments to ascertain (I) whether
it is suitable for the sample under study (2) Internal
Reliabilities (Item Analyses), Test Reliablities and
Test Validities.
8)Administer the instruments and score based on a
predetermined score sheet.
21
Steps in Educational Research
(Contd.)
9) Analyse the data using SPSS
10) Interprete the analyses and answer the research
question or reject/accept the hypotheses
11) State any assumptions or limitations in the
study.
22
Types of Educational Research
23
Descriptive Research
Survey Research
Case studies
Correlational Research
24
Types of Research Designs
(a) X Y (Experimental)
25
Types of Research Designs
(contd)
Preexperimental Designs: 2) One-
Group Pretest-Posttest Design
Design 2: One Group, Before - After
(a) Yb X Ya (Experimental)
26
Types of Research Designs
(contd)
Preexperimental Designs: The Static-
Group Comparison
Design 3: Two-Groups
(a) X Y
---------------- (Experimental)
(~ X) Y
(b) X Y
----------------- (Ex Post Facto)
(~X) ~Y 27
Types of Research Designs
(contd)
True Experimental Designs: 1) The
Pretest-Postest Control-Group Design
Design 4:
R Yb X Ya
----------------------------
R Yb Ya
28
Types of Research Designs
(contd)
Quasi Experimental Design (Ex Post
Facto Design) - No random assignment
of treatment
Design 5:
Yb X Ya
----------------------------
Yb Ya
29
a good design is measured by its validity - its
capability to answer questions it addresses.
2 types of validity: Internal Validity & External
Validity
30
Internal Validity
32
Validity
Content Validity - if the instrument tests
only those aspects that should be tested
Construct Validity - if the test measures
what it is supposed to measure
Criterion-related Validity/ concurrent
validity - if the test scores are closely related
to another test which measures similar
construct
Predictive Validity - if the instrument can
predict correctly a particular outcome
33
METHODS OF ESTIMATING RELIABILITY
Type of
Reliability Measure Procedure
Test-retest method Measure of stability Give the same twice to the same
group with any time interval
between tests from several
minutes to several years
Test-retest with Measure of stability Give two forms of the test to the
equivalence forms and equivalence same group with increased time
interval between forms
Split-half method Measure of internal Give test once. Score two equivalent
consistency halves test (e.g. odd items and even time)
Kuder-Richardson Measure of internal Give test once. Score total test and
method consistency apply Kuder-Richardson formula
34
DESIGNING INSTRUMENTS
35
Outline of SPSS Part 1
Types of Data
How to enter data and examine data
How to explore data for normality
What analyses / statistics to use
How to run these analyses
How to COMPUTE and RECODE
36
Outline
37
Exercise 1
Start your SPSS for Windows now. You will get the
Data Editor Window. Study the menu bar and the
options available in each menu.
Then,
1. Open the data file call ‘PRACTICE’.
2. Run some simple frequency analyses on the
following variables:
a) sex
b) race
c) region
d) happy
3. From the results in your Output Navigator
describe the respondents in this study
38
Types of Measurement Scales and their
Statistical Analyses
Measurement Statistical
Characteristics Type of Data
Scale Tests
Simple Classification in Non-
Nominal Chi-square
Categories without any order parametric
e.g Boy / Girl
Happy / Not Happy
Muslim / Buddhist / Hindu
39
Types of Measurement Scales and their
Statistical Analyses
Measurement Statistical
Characteristics Type of Data
Scale Tests
Do not have true 0 points. Has Parametric COMPARISON:
Interval order as well as equal distance t-tests
or interval between ANOVA
judgements (Social Sciences)
e.g. IQ score of 95 is better RELATIONSHIP:
than IQ 85 by 10 IQ points Pearson r
Ratio Have true 0 points. Has high Parametric
order, equal distance between COMPARISON:
judgements, a true zero value t-tests
(Physical Sciences) e.g.age, no. ANOVA
of children, 9 ohm is 3 times 3 RELATIONSHIP:
ohm and 6 ohm is 3 times 2 Pearson r
ohm But IQ 120 is more
comparable to IQ 100 than to IQ
144, although ratio
IQ 120 /100 = 144 /120 = 1.2 40
Types of Measurement Scales and their
Statistical Analyses
41
Refer to the handout provided.
Exercise 1
42
Data Collection
44
Refer to the handout provided.
Exercise 2:
45
Exploring Data Graphically
46
Histogram
Histogram Statistics
14
12
CHILD REARING
PRACTICES
10
Std.
Error
8
Mean 18.05
6 Median 17.00
Std. Deviation
4 3.89
Frequency
If Ratio is negative
If Mean < Median
22
Boxplot 20
18
Negatively skewed 16
14
12
10
8
CRA
35
6
N= 13 22
MALE FEMALE
SEX
49
Median
Mean
Positivity Skewed
If Ratio is positive
If Mean > Median
50
Checking Normality - Kurtosis
Kurtosis measures the spread of the
data
KurtosisStandard Error
= Statistic
Normal Graf
52
Kurtosis
Negative value of Kurtosis indicates
shorter tails (Box like distribution)
Normal Graf
53
Values more than 3 box-lengths from 75th
percentile
Boxplot
Values more than 1.5
box-lengths from 75th
30 percentile (outliers)
Largest observed value that isn’t
outlier
20
75th Percentile
Median
25th Percentile
10 Smallest observed value that isn’t
outlier
Slightly positively
skewed
0
N= 41 54
CHIL D REARING PRACTI
Stem-and-Leaf Plot
CHILD REARING PRACTICES Stem-and-Leaf Plot
1.00 1 . 0
2.00 1 . 23
8.00 1 . 44444455
11.00 1 . 66666777777
3.00 1 . 889
8.00 2 . 00000111
4.00 2 . 2233
3.00 2 . 555
1.00 2 . 6
Stem width: 10
Each leaf: 1 case(s)
55
Testing Normality of data
collected
All data must be tested for normality before analyzing
them statistically.
Normality - if the data samples the population
representatively, it will be normally distributed - where
the mean and median are approximately equal
Type of analysis depends on the normality of data and the
level of measurement of data
- Normally distributed data - use Parametric Tests like t-
tests, ANOVA, Pearson r.
- Non-normally distributed data - use Non-parametric
Tests like Chi-square, Spearman’s rho, Mann-Whitney,
Wilcoxon
56
To show Normality of Data
Descriptives
Median 16.00
CRA
Variance 16.410 SEX
Std. Deviation
4.05
MALE FEMALE
Huber's
Minimum 7
a 15.14 14.30
M-Estimator
Maximum 21
Tukey's b
Range 14 15.25 14.32
Biweight
Interquartile Range
6.00 Hampel's c
15.20 14.37
Skewness -.279 .616 M-Estimator
Kurtosis -.065 1.191 Andrews'
d 15.25 14.32
FEMALE Mean 14.36 .77 Wave
95% Confidence Lower
12.75 a. The weighting constant is
Interval for Mean Bound
Upper 1.339.
15.97
Bound b. The weighting constant is
5% Trimmed Mean 4.685.
14.39
c. The weighting constants
Median 14.00 are 1.700, 3.400, and 8.500
Variance 13.195 d. The weighting constant is
Std. Deviation
3.63 1.340*pi.
Minimum 7
Maximum 21
Range 14
Interquartile Range
5.00
Tests of Normality
CRA
SEX
MALE FEMALE
Kolmogorov-Smirnova Statistic .129 .151
df 13 22
Sig. .200* .200*
Shapiro-Wilk Statistic .963 .965
df 13 22
Sig. .751 .581
*. This is a lower bound of the true significance.
a. Lilliefors Significance Correction
20
18
16
14
12
10 Slightly Positively
Slightly Negatively Skewed
8 Skewed
CRA
35
6
N= 13 22
MALE FEMALE
SEX
59
Detrended Normal Q-Q Plot
Normal Q-Q Plot of CRA of CRA
Normal Q-Q Plot of CRA Detrended Normal Q-Q Plot of CRA
For SEX= MALE For SEX= MALE
1.5 .4
1.0
.2
.5
-.0
0.0
-.2
-.5
-.4
-1.0
-.6
-1.5
6 8 10 12 14 16 18 20 22
6 8 10 12 14 16 18 20 22
Observed Value
Observed Value
1.5 .1
1.0
0.0
.5
0.0 -.1
Expected Normal
-.5
-.2
-1.0
-.3
-1.5
-2.0 -.4
6 8 10 12 14 16 18 20 22 6 8 10 12 14 16 18 20 22
60
Observed Value Observed Value
Exercise
Open the data file “PRACTICE’ and check the normality of
the ‘Age’ data of the respondents using
a) Histogram
b) Boxplot
c) Stem-and-leaf
d) E-estimators
e) Kolmogorov-Sminov & Shapiro Wilk
f) Normal Q-Q Plot
g) Detrended Normal Q-Q Plot
61
Testing equality of variance
Levernes Test (SPSS-DataEditor-Analize-Explore
-Plots(Leverne)
Levene
Mothers Statistic df1 df2 Sig. Not
CHILD
Fathers
REARING
Sig.
.000 1 39 .991
PRACTICES
63
Compute Data
SPSS data editor - Transform - Compute -
65
Recode (contd)
67
Select cases
69
Parametric Statistical Analyses
(Degree of Association/
Relationship)
Pearson Product-moment Correlation
Correlations
WHAT
KIND OF
SOMETHING PERSON
ABOUT ARE
CRA MYSELF YOU?
Pearson CRA 1.000 .204 .285
Correlation SOMETHING
ABOUT .204 1.000 .375*
MYSELF
WHAT KIND
OF
.285 .375* 1.000
PERSON
ARE YOU?
Sig. CRA . .239 .097
(2-tailed) SOMETHING
ABOUT .239 . .016
MYSELF
WHAT KIND
OF
.097 .016 .
PERSON
ARE YOU?
*. Correlation is significant at the 0.05 level (2-tailed).
70
Presenting Correlation Table
Table 1
Pearson Product Moment Correlations between SAM,
WKOPAY and CRA Scores
71
Reporting Product Moment Correlations
Table 1 presents the inter-correlations among Creative Child Rearing
Practices (CRA), Something About Myself (SAM) and What Kind of
Person Are You? (WKOPAY) scores. The correlation coefficient between
CRA and SAM scores is .20 which is not significant at p < .05. This
indicates that parents who perceive themselves as creative based on
their past creative performances do not engage in creative child rearing
practices.
The correlation coefficent between CRA and WKOPAY scores is also not
significant (r = .29, p > .05). This indicates that parents who perceive
themselves as creative based on their personality characteristics, also
do not engage in creative child rearing practices.
72
Report
There is a significant correlation between
SAM and WKOPAY (r = .375, p < .05). The
correlation is positive, indicating that an
increase in SAM scores will result in an
increase in WKOPAY scores. Results also
show that 14% (r squared) of the variance of
SAM scores is explained by WKOPAY scores.
About 86% of the variance in SAM is
unaccounted for.
73
t - tests
Paired t-tests
Grouped t-tests
74
Assumptions of t-tests
75
Parametric Statistical Analyses
( comparisons - t-tests )
SPSS Data Editor - Compare means - Independent Sample t test
76
Parametric Statistical Analyses
( comparisons - t-tests )
Group Statistics
SD 4.05 3.63
78
Effect Size
__ ___
X 1 X 2
EffectSize
s1 s2
2
Example:
X1 = 15.08 s1 = 4.05
X2 = 14.36 s2 = 3.63
15.08 14.36 0.72
EffectSize 18.75
4.05 3.63 3.84
2
Cohen’ d Interpretation
~ .2 Small
~ .5 Moderate
~ .8 Large
80
Report
81
Bonferonni Correction for
Multiple Comparisons
For multiple comparisons, Bonferonni
corrections must be made
If the overall level of significance is set
at p < .05 and the number of
comparisons involved is 10, then the
level of significance for each
comparison must be .05/10 which is .
005.
82
Paired t-test
Assumptions
1) Normality of the population difference of scores –
this is ascertained by ensuring the normality of each
variable separately.
2) the other assumptions similar to group t – test
a) Data must be interval or ratio
b) Data must be obtained via random
sampling from population
c) Data must be normally distributed
83
Exercise
1) Is there a significant difference in
the highest year of education between
the respondent’s mother and father?
2) Is there a significant difference in the
highest year of education of respondent
and his/her spouse?
84
Parametric Statistical Analyses
( comparisons - Oneway
ANOVA )
SPSS Data Editor - Compare Means - One-way ANOVA -
85
Parametric Statistical Analyses
( comparisons - Oneway
ANOVA )
Test of Homogeneity of Variances
Levene
Statistic df1 df2 Sig.
WHAT KIND
OF
.469 2 38 .629
PERSON
ARE YOU?
SOMETHING
ABOUT 3.473 2 38 .041
MYSELF
ANOVA
Sum of Mean
Squares df Square F Sig.
WHAT KIND Between
31.145 2 15.573 .632 .537
OF Groups
PERSON Within
ARE YOU? 936.660 38 24.649
Groups
Total 967.805 40
SOMETHING Between
149.208 2 74.604 2.193 .126
ABOUT Groups
MYSELF Within
1292.743 38 34.020
Groups
Total 1441.951 40 86
Understanding the ANOVA table
Variations among the sample means
F = -------------------------------------------
Variance within the samples
Between mean square is computed by subtracting the mean of the observations (the overall
mean) from the mean of each group, squaring each difference, multiplying each square by the
number of cases in its group, and adding the results for each group together. The total is called
between-group sum of squares
Within-group sum of squares is computed by multiplying each group variance by the number
of cases in the group minus 1 and add the results for all groups.
Mean square column reports sum of squares divided by its respective degree of freedom.
F ratio is the ratio of the two mean squares.
87
Presentation of One-way ANOVA
results
Table 3
One-way ANOVA for CRA scores by WKOPAY groups
Total 40 967.805
89
Report
90
Effect Size
Is the degree to which the phenomena exists (Cohen, 1988)
91
Power of a test
Power of a statistical test is the probability of
observing a treatment effect when it occurs.
It is the probability that it will correctly lead to the
rejection of a false null hypothesis (Green, 2000)
The statistical power is the ability of the test to
detect an effect if it actually exists (High, 2000)
The statistical power is denoted by 1 – β, where β is
the Type II error, the probability of failing to reject
the null hypothesis when it is false.
Conventionally, a test with a power greater than .8
level (or β = < .2) is considered statistically powerful.
β = is the probability of not rejecting the false null hypothesis (Type II error)
92
There are four components that
influence the power of a test:
93
94
Parametric Statistical Analyses
( Comparison of more than 2 groups on
interval data - ANOVA - Simple Factorial)
Statistics - General Linear Model - GLM General Factorial
95
Parametric Statistical Analyses
( Comparisonof more than 2 groups on
interval data - ANOVA - Simple Factorial)
Table 2
ANOVAa,b
Unique Method
Sum of Mean
Squares df Square F Sig.
CRA Main Effects (Combined) 14.916 3 4.972 .318 .812
SEX .192 1 .192 .012 .913
sam grps 12.994 1 12.994 .830 .370
wk grps 3.346 1 3.346 .214 .648
2-Way Interactions (Combined) 32.025 3 10.675 .682 .571
SEX * sam
8.403 1 8.403 .537 .470
grps
SEX * wk
15.077 1 15.077 .963 .335
grps
sam grps *
13.149 1 13.149 .840 .367
wk grps
3-Way Interactions SEX * sam
grps * wk 2.472 1 2.472 .158 .694
grps
Model 55.588 7 7.941 .507 .821
Residual 422.583 27 15.651
Total 478.171 34 14.064
a. CRA by SEX, sam grps, wk grps
b. All effects entered simultaneously 96
ANCOVA
Try exercise on ANCOVA on page 10.
97
Presentation of Three-way ANOVA results
Table 4
Analysis of Variance using CRA scores as the dependent variable
Source of Variation Sum of DF Mean F Signif.
Squares Squares of F
Main Effects 14.916 3 4.972 .318 .812
Sex .192 1 .192 .012 .913
SAM grps 12.994 1 12.994 .830 .370
WK grp 3.346 1 3.346 .214 .648
The results indicate male parents do not differ from female parents
in their child rearing practices. Their creative perceptions also do
not affect their child rearing practices.
99
Multiple Regression
Bivariate Multiple Regression
Aca Ach = Constant + b Motivation
confidence
100
Multiple Regression - Assumptions
101
Multivariate Outlier – an example
It is usual to find a person who is 15 years old and
will not be a outlier when you plot a histogram for age
(univariate)
It is also common to find a person earning a salary of
RM10,000 a month and this person may not be an
outlier when you plot a histogram for salary (univariate)
However, if you combine both age and salary
(multivariate) a person who is 15 years old earning
RM10,000 may become an outlier called multivariate
outlier
You need to get rid of multivariate outlier using
Mahalanobis Distance before you run your multiple
regression
102
What havoc a multivariate outlier can do to your results?
It can change your R from .08 to .88!
103
Methods for Selecting
Variables
Forward Selection – starting from the
constant term, variable is added to the equation
or regression model if it results in the largest
significant (at p < .05 for e.g.) increase in
multiple R2 .
Backward Selection – all variables are put
into the equation or regression model. At each
step, a variable is removed if this removal
results in only a small insignificant change in R2.
Stepwise variable Selection – most
commonly used method for model building. Is a
combination of Forward Selection and Backward
Selection. Variables already in the model can be
removed if they are no longer significant
predictors when new variables are added to the
regression model. 104
Types of Regression Analyses
Standard Multiple Regression
Sequential / Hierarchical Multiple
Regression
Statistical / Stepwise Multiple
Regression
105
Coding for Dummy
Variables
Example:
Gender – dichotomous
Male – 1
Female - 2
Need to convert to dummy variable
Male - 1
Female - 0
to study the effect of gender on the DV
if r = sig + , male has higher significant effect
on DV
if r = sig - , female has higher significant effect
on DV
106
Using PRACTICE data file
Research Question:
1) To what extent do PAEDU and
107
Results of Mul Reg for Research Question 1
108
Results of Mul Reg for Research Question 2
Descriptive Statistics
Correlations
Change Statistics
Adjusted Std. Error of R Square Durbin-
Model R R Square R Square the Estimate Change F Change df1 df2 Sig. F Change Watson
1 .450a .203 .202 2.499 .203 246.937 1 971 .000
2 .481b .232 .230 2.454 .029 36.704 1 970 .000
3 .486c .236 .234 2.448 .004 5.670 1 969 .017 1.738
a. Predictors: (Constant), paeduc
b. Predictors: (Constant), paeduc, maeduc
c. Predictors: (Constant), paeduc, maeduc, sexdummy
d. Dependent Variable: educ
ANOVAd
Sum of
Model Squares df Mean Square F Sig.
1 Regression 1541.572 1 1541.572 246.937 .000a
Residual 6061.733 971 6.243
Total 7603.305 972
2 Regression 1762.582 2 881.291 146.361 .000b
Residual 5840.724 970 6.021
Total 7603.305 972
3 Regression 1796.560 3 598.853 99.934 .000c
Residual 5806.745 969 5.993
Total 7603.305 972
a. Predictors: (Constant), paeduc
b. Predictors: (Constant), paeduc, maeduc
c. Predictors: (Constant), paeduc, maeduc, sexdummy
d. Dependent Variable: educ 110
Multiple Regression Results
Coefficientsa
Unstandardized Standardized
Coefficients Coefficients 95% Confidence Interval for B Collinearity Statistics
Model B Std. Error Beta t Sig. Lower Bound Upper Bound Tolerance VIF
1 (Constant) 10.178 .229 44.499 .000 9.729 10.627
paeduc .306 .019 .450 15.714 .000 .268 .344 1.000 1.000
2 (Constant) 9.254 .272 34.077 .000 8.721 9.787
paeduc .201 .026 .295 7.768 .000 .150 .251 .548 1.826
maeduc .189 .031 .230 6.058 .000 .128 .250 .548 1.826
3 (Constant) 9.142 .275 33.250 .000 8.602 9.681
paeduc .196 .026 .288 7.574 .000 .145 .246 .544 1.837
maeduc .189 .031 .231 6.085 .000 .128 .250 .548 1.826
sexdummy .380 .160 .067 2.381 .017 .067 .693 .990 1.011
a. Dependent Variable: educ
111
Collinearity Statistics - Tolerance
Tolerance – is the statistic used to
determine how much the independent
variables are linearly related to one
another (Multicollinear)
-Tolerance is the proportion of a
variable's variance not accounted for by
other independent variables in the model.
Tolerance level must be more than .1
112
Collinearity Statistics - VIF
VIF – Variance Inflation Factor
- is the reciprocal of the tolerance
VIF should be less than 10
113
Durbin-Watson
Gives a measure of autocorrelations in the
residuals (or errors) in the values or
observations in the multiple regression
analyses
If the Durbin-Watson value is between 1.5
and 2.5, then the observations or values are
independent there are no systematic trend
in the errors of the observation of the values
(there should not be a systematic trend in the
errors)
114
Reporting Results of Mul Reg for Research
Question 2
Table XX
Standard Multiple Regression of PAEDUC, MAEDUC and SEXDUMMY on EDUC
Intercept = 9.14
115
Reporting Multiple Regression Results
117
Non-parametric tests
do not require a normal distribution
do not require equal group variances
used with variables that are ordinal or nominal
e.g. Chi-square for determining relationship between
nominal - nominal data or nominal - ordinal data (SPSS-
Data Editor-Statistics-Summarize-Crosstabs)
e.g Spearman Rank- Order correlation for seeking
relationship between ordinal - ordinal data
e.g. Mann-Whitney U-test to compare 2 different
groups on a ordinal/interval data
118
Non-parametric tests
Kruskall-Wallis Test (To compare > 2
different groups)
Fiedman Test (To compare same group
> 2 times)
119
Non - Parametric Statistical
Analyses
(Degree of Association)
SPSS Data Editor - Statistics - Summarize - Crosstabs
120
Non - Parametric Statistical Analyses
(Degree of Association)
Chi-square: used to find the degree of
association between 2 nominal variables
Count CR - CREATIVE
cr groups CHILDREARING
low cr av cr hi cr Total
item29 .00 16 8 8 32
1.00 1 8 9
Total 16 9 16 41
Chi-Square Tests
Asymp.
Sig.
Value df (2-tailed)
Pearson a
12.465 2 .002
Chi-Square
Likelihood Ratio 14.696 2 .001
Linear-by-Linear
11.389 1 .001
Association
N of Valid Cases 41
a. 3 cells (50.0%) have expected count less than
5. The minimum expected count is 1.98. 121
Reporting Cross Tabulations
Descriptive:
Sixteen low, 8 average and 9 high creative
parents answered ‘no’ while 1 average and 8 high creative
parents answered “yes” on item 29. The chi-square analyses
reveal a significant association between parents’ creativity
and their responses, χ2 (2, 41) = 12.47, p <.05.
Interpretation:
The results show that creative parents do answer differently
on item 29 with the creative parents significantly answering “Yes”
on the item compared to the non-creative parents.
122
Non - Parametric Statistical Analyses
(Relationship)
Crosstab
Count
cr groups
low cr av cr hi cr Total
item30 .00 8 2 3 13
1.00 8 7 13 28
Total 16 9 16 41
Chi-Square Tests
Asymp. NS
Sig.
Value df (2-tailed)
Pearson a
4.087 2 .130
Chi-Square
Likelihood Ratio 4.063 2 .131
Linear-by-Linear
3.520 1 .061
Association
N of Valid Cases 41
a. 1 cells (16.7%) have expected count less than
5. The minimum expected count is 2.85.
FINDING:
123
There is no relationship between item 30 and the childrearing practices
Non-Parametric Statistical Analyses
(Relationship)
sam grps * cr groups Crosstabulation
Count
cr groups
low cr av cr hi cr Total
sam grps 1 12 5 8 25
2 4 4 8 16
Total 16 9 16 41
Chi-Square Tests
Asymp.
Value df
Sig.
(2-tailed)
NS
Pearson a
2.244 2 .326
Chi-Square
Likelihood Ratio 2.306 2 .316
Linear-by-Linear
2.050 1 .152
Association
N of Valid Cases 41
a. 1 cells (16.7%) have expected count less than
5. The minimum expected count is 3.51.
FINDING:
124
There is no relationship between SAM and CR
Non - Parametric Statistical
Analyses (Comparison of Groups
on ordinal data)
SPSS Data Editor - Nonparametric Tests - 2 Independent sample
125
Non - Parametric Statistical Analyses
(Comparison of Groups on ordinal
data)
Mann-Whitney U-Test
Ranks Test Statisticsa
127
Used as data reduction method to
reduce a large number of variables to
a smaller set of factors that is
representative of all the variables
128
Conclusion
Research Process
Types of data
Data Entry and Data Examination
Data Exploration - both graphical +
statistical
Data Analyses - Parametric & Non-
parametric, Interpreting and Reporting
129
Output
KMO and Bartlett's Test
Kaiser-Meyer-Olkin Measure of Sampling
Adequacy. .466
130
Interpreting Output
131
132