Bahan kajian pada
MK. Metode Penelitian Interdisiplin Kajian Lingkungan
Diabstraksikan oleh:
Riset adalah aktivitas manusia yang didasarkan
atas investigasi intelektual dan bertujuan untuk
menemukan, interpretasi, dan memperbaiki
pengetahuan tentang berbagai aspek dunia nyata.
Research can use the scientific method, but need
not do so.
Riaset ilmiah bertumpu pada aplikasi metodemetode ilmiah yang didasarkan pada
paradigma ilmiah.
This research provides scientific information
and theories for the explanation of the nature
and properties of humans and the whole
It makes practical applications possible.
Riset dasar (fundamental atau pure research) mempunyai tujuan
utama pengembangan pengetahuan dan pemahaman teoritis
mengenai huungan-hubungan di antara variabel.
It is exploratory and often driven by the researcher’s curiosity,
interest, or intuition. It is conducted without any practical end in
mind, although it may have unexpected results pointing to
practical applications.
Istilah “basic” atau “fundamental” menyatakan bahwa, melalui
teori yang dihasilkannya, riset-dasar menyediakan landasan
bagi riset selanjutnya, atau riset terapannya.
Tujuan dari proses riset adalah menghasilkan
pengetahuan baru, yang biasanya mempunyai tiga macam
RISET EKSPLORATORI: which structures and
identifies new problems
RISET KOSNTRUKTIF: which develops solutions to
a problem
RISET EMPIRIK: which tests the feasibility of a
solution using empirical evidence
Research can also fall into two distinct types, Primary research and
Secondary research.
Research methods used by scholars include:
Action research
Case study
Experience and intuition
Mathematical models
Participant observation
Statistical analysis
Statistical surveys
Content or Textual Analysis
Generally, research is understood to follow a certain structural
Though step order may vary depending on the subject matter
and researcher, the following steps are usually part of most
formal research, both basic and applied:
Formation of the topic
Conceptual definitions
Operational definitions
Gathering of data
Analysis of data
Test, revising of hypothesis
Conclusion, iteration if necessary
A common misunderstanding is that by this method a
hypothesis can be proven.
Generally a hypothesis is used to make predictions that
can be tested by observing the outcome of an
If the outcome is inconsistent with the hypothesis, then
the hypothesis is rejected.
However, if the outcome is consistent with the
hypothesis, the experiment is said to support the
This careful language is used because
researchers recognize that alternative
hypotheses may also be consistent with the
In this sense, a hypothesis can never be
proven, but rather only supported by
surviving rounds of scientific testing and,
eventually, becoming widely thought of as true
(or better, predictive), but this is not the same
as it having been proven.
Hipotesis yang bagus memungkinkan untuk prediksi
yang baik, dan di dalam kerangka waktu penelitiannya
prediksi tersebut dapat diverifikasi.
As the accuracy of observation improves with time, the
hypothesis may no longer provide an accurate
In this case a new hypothesis will arise to challenge the
old, and to the extent that the new hypothesis makes
more accurate predictions than the old, the new will
supplant it.
The historical method comprises the techniques and
guidelines by which historians use historical sources
and other evidence to research and then to write
There are various history guidelines commonly used
by historians in their work, under the headings of
external criticism, internal criticism, and synthesis.
This includes higher criticism and textual criticism.
Meskipun item-itemnya mungkin saja beragam
tergantung pada obyek dan penelitinya, namun
konsep-konsep berikut ini merupakan bagian
penting dari penelitian historis formal:
Identification of origin date
Evidence of localization
Recognition of authorship
Analysis of data
Identification of integrity
Attribution of credibility.
The word research derives from the
French recherche, from rechercher, to
search closely where "chercher" means
"to search"; its literal meaning is 'to
investigate thoroughly'.
Application of scientific method to the investigation of
relationships among natural phenomenon, or to solve a
medical or technical problem.
Read more:
Scientific method is a body of techniques for investigating phenomena,
acquiring new knowledge, or correcting and integrating previous
To be termed scientific, a method of inquiry must be based on empirical
and measurable evidence subject to specific principles of reasoning.
The Oxford English Dictionary says that scientific method is:
"a method or procedure that has characterized natural science since the
17th century, consisting in systematic observation, measurement, and
experiment, and the formulation, testing, and modification of hypotheses.
A scientific theory is "a well-substantiated explanation of
some aspect of the natural world, based on a body of facts that
have been repeatedly confirmed through observation and
Scientists create scientific theories from hypotheses that have
been corroborated through the scientific method, then gather
evidence to test their accuracy.
As with all forms of scientific knowledge, scientific theories
are inductive in nature and do not make apodictic
propositions; instead, they aim for predictive and explanatory
Diunduh dari: ….. 12/9/2012
“Teori” harus memenuhi kriteria berikut:
1. It makes falsifiable predictions with consistent accuracy across a
broad area of scientific inquiry (such as mechanics).
2. It is well-supported by many independent strands of evidence,
rather than a single foundation. This ensures that it is probably a
good approximation, if not completely correct.
3. It is consistent with pre-existing theories and other experimental
results. (Its predictions may differ slightly from pre-existing
theories in cases where they are more accurate than before.)
4. It can be adapted and modified to account for new evidence as it is
discovered, thus increasing its predictive capability over time.
5. It is among the most parsimonious explanations, sparing in
proposed entities or explanations.
Diunduh dari: ….. 12/9/2012
1. That which underpins research design
Teori sebagai paradigma
2. That which may inform our
understanding of the phenomenon under
Theori sebagai ‘lensa , cermin’
3. That which may emerge from our study
Theori sebagai pengetahuan baru
Diunduh dari: ….. 12/9/2012
1. Asumsi filosofis yang melandasi realita
sosial (ontology)
2. What we accept as valid evidence of that
reality (epistemology)
3. The means by which we investigate that
context (methodology)
4. The means by which we gather evidence
Diunduh dari: ….. 12/9/2012
. TEORi sebagai suatu LENS.
Existing theory(s) which seek to explain how aspects of (social)
reality ‘work’ (models). E.g.
– Models of learning
• Behaviourist (Skinner); Constructivist (Piaget);
Social constructivist (Vygotsky); Deep learning
– Models of professional/expertise
• Situated learning; Communities of practice (Lave;
– Models of second language acquisition
• Krashen’s SLA theory; Oxford’s S2R;
Diunduh dari: ….. 12/9/2012
1. Adaptasi, revisi atau konfirmasi teori
yang ada
2. Menghasilkan teori baru
3. Berhubungan dengan Kerangka Konsep
Diunduh dari: ….. 12/9/2012
KK merupakan penyajian visual atau
tertulis yang:
“explains either graphically, or in narrative
form, the main things to be studied – the
key factors, concepts or variables - and
the presumed relationship among them”
(Miles and Huberman, 1994)
• Riset Kuantitatif
• Typically developed after literature review
• Provides the structure/content for the whole study
based on literature and personal experience
• Revisited at the conclusion of the study.
• Riset Kualitatif
• Initial framework after literature review
• Further developed as participants’ views and issues
are gathered and analysed.
Riset Eksploratori
Eksploratori :
to find out what is happening,
to seek new insights,
to ask questions
to assess phenomena in a new light
Tiga prinsip untuk melakukan riset
1. A search of the literature
2. Interviewing ‘experts’ in the subject
3. Conducting focus group interviews
Diunduh dari: ….. 12/9/2012
1. to establish causal relationships between variables
2. to analyse the quantitative data to prove a
3. to analyse the qualitative data to explain a reason
of an issue.
Diunduh dari: ….. 12/9/2012
Deskriptif adalah:
1. the researcher observes and then describes
what was observed.
2. to portray an accurate profile of persons,
events or situations.
3. an extension of an exploratory/explanatory
Diunduh dari: ….. 12/9/2012
Diunduh dari: ….. 12/9/2012
The “N” side in the Paradigm War
Marilyn K. Simon, Ph.D.
“an inquiry into a social or human problem based on
testing a theory composed of variables, measured
with numbers, and analyzed with statistical
procedures, in order to determine whether the
predictive generalizations of the theory hold true.”
(Creswell, J. Research Design: Qualitative and Quantitative Approaches. Sage: 1994.)
"a formal, objective, systematic process in which
numerical data are utilized to obtain information
about the world"
(Burns & Grove, as cited by Cormack, 1991, p. 140).
Numerical means expressed in numbers or
relating to numbers.
Numerical data is data measured or identified on a
numerical scale.
Numerical data can be analyzed using statistical methods,
and results can be displayed using tables, charts,
histograms, and graphs.
Read more:
Diunduh dari: ….. 12/9/2012
Absolute Population:
France, Germany, and
the United Kingdom,
Diunduh dari ….. 12/9/2012
Statistical Models:
include issues such as
statistical characterization
of numerical data,
estimating the probabilistic
future behavior of a system
based on past behavior,
extrapolation or
interpolation of data based
on some best-fit, error
estimates of observations,
or spectral analysis of data
or model generated output.
Diunduh dari ….. 12/9/2012
Pain Assessment
By: Bram Riegel, M.D.
Numeric Pain Intensity Scale
Diunduh dari:….. 12/9/2012
Long and short numeric scales
Diunduh dari ….. 12/9/2012
Moving from Qualitative
to Quantitive Assessment Assigning Numeric Scales
At this point you may wish to
add a numeric scale and use
some form of traffic light
system to break the risks into
groups requiring different
response strategies.
This table uses the same linear
scale for both axes:
Diunduh dari ….. 12/9/2012
Diunduh dari ….. 12/9/2012
• Quantitative research is about quantifying
the relationships between variables.
– We measure them, and
– construct statistical models to explain what
we observed.
• The researcher knows in advance what he
or she is looking for.
• TUJUAN: Prediksi, Kontrol, Konfirmasi, Uji
Ashok Jashapara, (2003) "Cognition, culture and competition: an empirical test of
the learning organization", Learning Organization, The, Vol. 10 Iss: 1, pp.31 - 50
Diunduh dari: ….. 12/9/2012
Irene M. Herremans, Robert G. Isaac, (2005) "Management planning and control:
Supporting knowledge-intensive organizations", Learning Organization, The, Vol. 12
Iss: 4, pp.313 - 329
Diunduh dari: ….. 12/9/2012
The effects of post-adoption beliefs on the expectation-confirmationmodel for information
technology continuance
James Y.L. Thong, Se-Joon Hong, Kar Yan Tam.
International Journal of Human-Computer Studies. Volume 64, Issue 9, September 2006, Pages 799–810.
Diunduh dari: ….. 12/9/2012
Investigating latent trait and life course theories as predictors of recidivism among an
offender sample
Daniel J O'Connell.
Journal of Criminal Justice. Volume 31, Issue 5, September–October 2003, Pages 455–467.
Diunduh dari: ….. 12/9/2012
Value creation and firm sales performance: The mediating roles of strategic account management and
relationship perception
Ursula Y. Sullivan, Robert M. Peterson, Vijaykumar Krishnan, Industrial Marketing Management. Volume 41, Issue 1, January
2012, Pages 166–173.
Diunduh dari:….. 12/9/2012
• All aspects of the study are carefully
designed before data are collected.
• Quantitative research is inclined to be
deductive -- it tests theory. This is in
contrast to most qualitative research
which tends to be inductive --- it
generates theory
• The researcher tends to remain
objectively separated from the subject
• Descriptive research
– Correlational research
– Evaluative
– Meta Analysis
• Causal-comparative research
• Experimental Research
– True Experimental
– Quasi-Experimental
– Shared with full permission from IDTL Journal.
• Descriptive research involves collecting data
in order to test hypotheses or answer
questions regarding the participants of the
study. Data, which are typically numeric, are
collected through surveys, interviews, or
through observation.
• In descriptive research, the investigator
reports the numerical results for one or more
variable(s) on the participants (or unit of
analysis) of the study.
Used to obtain information
concerning the current status of
a phenomena.
Purpose of these methods is to
describe “what exists” with
respect to situational variables.
1. Status descriptive
2. Explanatory
descriptive studies
Descriptive Research Steps
1. Statement of the problem.
2. Identification of information.
3. Selection or development of
data gathering instruments.
4. Identification of target
population and sample.
5. Design of information collection
6. Collection of information.
7. Analysis of information.
8. Generalization and/or
Diunduh dari: ….. 12/9/2012
. Causal-comparative research .
1. Causal-comparative research is sometimes treated as a type of descriptive research since it
describes conditions that already exist.
2. ausal comparative research attempts to determine reasons, or causes, for the existing
3. n causal-comparative or ,ex-post facto, research the researcher attempts to determine the
cause, or reason, for preexisting differences in groups of individuals
Such research is referred to as ex post facto (Latin for “after the fact”) since both the
effect and the alleged cause have already occurred and must be studied in retrospect
4. The basic causal-comparative approach involves starting with an effect and seeking possible
5. The basic approach starts with cause and investigates its effects on some variable
6. The basic approach is sometimes referred to as retrospective causal-comparative research
(since it starts with effects and investigates causes)
7. The variation as prospective causal-comparative research (since it starts with causes and
investigates effects)
8. Retrospective causal-comparative studies are far more common in educational research
9. Causal-comparative studies attempt to identify cause-effect relationships; correlational
studies do not
10. Causal-comparative studies typically involve two (or more) groups and one independent
variable, whereas correlational studies typically involve two or more variables and one group
11. Causal-comparative studies involve comparison, correlational studies involve relationship
Diunduh dari: ….. 12/9/2012
• Causal-comparative research attempts to
establish cause-effect relationships among
the variables of the study.
• The attempt is to establish that values of
the independent variable have a
significant effect on the dependent
• This type of research usually involves group
comparisons. The groups in the study make up the
values of the independent variable, for example gender
(male versus female), preschool attendance versus no
preschool attendance, or children with a working
mother versus children without a working mother.
• In causal-comparative research the independent
variable is not under the researchers control, that is,
the researcher can't randomly assign the participants
to a gender classification (male or female) or socioeconomic class, but has to take the values of the
independent variable as they come. The dependent
variable in a study is the outcome variable.
Causal-Comparative Research
• The aim of causal-comparative research is to
determine the cause of existing differences
among groups.
– Whereas correlational research involves
collecting data on TWO or more variables on
ONE group, causal comparative research
involves the collection of data on ONE
independent variables for TWO or more groups.
Causal-Comparative Research is
Differentiated from Experimental
• In an experiment, the independent
variable is manipulated by the researcher.
• In causal comparative research the
independent has already occurred.
– Examples of independent variables include
socioeconomic status, pre-school history,
number of siblings, and so on.
Causal-Comparative Designs:
Similarities to Experimental Designs
• Purpose
– Trying to determine cause-effect relation
between variables
• Designs used
– Single-factor
– Two-factor
– Multi-factor
• Analysis of data
Primary cause loop
diagram of basic
variables in the
Prediction of China's
coal productionenvironmental
pollution based on a
hybrid genetic
dynamics model.
Shiwei Yu, Yi-ming
Energy Policy.
Volume 42, March
2012, Pages 521–529
Hypothesized model
of relationships
among variables
Variables Predicting
Students’ First
Achievement in a
Dental School in
Minkang Kim and
Jae Il Lee
Journal of Dental
Education April 1,
2007 vol. 71 no. 4
Causal-Comparative Designs vs Experimental
• Start with effect, then seek causes
– Less often start with cause (prospective)
• No manipulation of variables
– Cannot be manipulated (SES, race, sex)
– Should not be manipulated (# cigarettes
– Were not manipulated (method of reading
Causal-Comparative Designs vs Experimental
• Assignment of subjects to groups
– In experimental, assignment MUST be
– In causal-comparative, assignment is based
on preexisting characteristics
• Determination of cause is not as robust
– It is more that of a relationship, with a
suggestion of cause
Causal Comparative Research
• Groups…
– are classified according to common
preexisting characteristic, and
– compared on some other measure
• There is NO
– intervention,
– manipulation, or
– random assignment
Example: What causes lung cancer?
• Finding: People with lung cancer
smoke more than people without lung
cancer. There are no other differences
in lifestyle characteristics between the
• Conclusion: Smoking is a possible
cause of lung cancer.
• Caution: A third factor? Proper
Value of Causal
Comparative Research
• Uncovers relationships to be investigated
• Used to establish cause-effect when
experimental design not possible.
• Less expensive and time consuming than
experimental research.
• Note: if you conduct a quantitative
research study it most likely will be a
causal-comparative study.
Strengthening Causal Comparative
• Strong inference (theory).
• Time sequence (presumed cause precedes
presumed effect).
• Incorporate other, possible, causes in the
design (measure common antecedents) .
• Use designs that control for extraneous
– matched group design
– Extreme groups design
– Statistical control (Analysis of Covariance)
Wide Variety of Statistical Procedures
• t tests, ANOVA, ANCOVA when two or more
groups are being compared.
• Regression analysis when there are multiple
independent variables.
• MANOVA, and multivariate regression, when
there are multiple dependent variables.
• Path analysis and structural equation
modeling when the theoretical causal paths
are being investigated.
The objective, systematic, controlled
investigation for the purpose of
predicting and controlling phenomena
and examining probability and causality
among selected variables.
Diunduh dari: ….. 12/9/2012
Experimental research is guided by a hypotheses (or several
hypothesis) that states an expected relationship between two or more
An experiment is conducted to support or
disconfirm this experimental hypothesis.
Experimental research, although very demanding of time and
resources, often produces the soundest evidence concerning
hypothesized cause-effect relationships (Gay, 1987).
Read more:
is a systematic and scientific approach to research in which the
researcher manipulates one or more variables, and controls and
measures any change in other variables.
Experimental Research is often used where:
There is time priority in a causal relationship (cause precedes effect)
There is consistency in a causal relationship (a cause will always lead to
the same effect)
The magnitude of the correlation is great.
Aims of Experimental Research
Experiments are conducted to be able to predict phenomenons.
Typically, an experiment is constructed to be able to explain some kind
of causation. Experimental research is important to society - it helps us
to improve our everyday lives.
Diunduh dari: ….. 12/9/2012
Steven M. Ross (The University of Memphis)
Gary R. Morrison (Wayne State University)
The experimenter’s interest in the effect of environmental
change, referred to as “treatments,” demanded designs
using standardized procedures to hold all conditions
constant except the independent (experimental) variable.
This standardization ensured high internal validity (experimental
control) in comparing the experimental group to the control
group on the dependent or “outcome” variable. That is, when
internal validity was high, differences between groups could be
confidently attributed to the treatment, thus ruling out rival
hypotheses attributing effects to extraneous factors.
Diunduh dari: ….. 12/9/2012
Research Strategy: EXPERIMENT
1. Define a theoretical hypothesis
2. Selection of samples of individuals from the
3. Random allocation of samples to different
experimental conditions: the experimental vs.
control group
4. Introduction of intervention to one more of the
5. Measurement on a small number of dependent
6. Control of all other variables
Research Strategy: EXPERIMENT
Figure 5.2
A classic experiment strategy
Diunduh dari: …. … 13/9/2012
True Experimental Design
• Experimental research like causal-comparative research
attempts to establish cause-effect relationship among the
groups of participants that make up the independent variable
of the study, but in the case of experimental research, the
cause (the independent variable) is under the control of the
• The researcher randomly assigns participants to the groups
or conditions that constitute the independent variable of the
study and then measures the effect this group membership
has on another variable, i.e. the dependent variable of the
• There is a control and experimental group, some type of
“treatment” and participants are randomly assigned to both:
Control Group, manipulation, randomization).
True Experimental Design
Experimental Designs
It is a controlled method of observation in
which the value of one or more
independent variables is changed to
assess its causal effect on one or more
dependent variables
(Monette et al., 1994).
Diunduh dari: …. … 13/9/2012
True Experimental Design
Characteristics of a True Experimental
1. Time order of variable.
2. Manipulation of the INDEPENDENT VARIABLE
3. Relationships between variable.
4. Control of rival (alternative) hypothesis.
5. Use of a control group.
6. Random sampling and random assignment
(Grinnell, 1997).
Diunduh dari: …. … 13/9/2012
True Experimental Design
Concepts in Experimental Designs
1. Independent variable (treatment,
stimulus, or manipulation)
2. Dependent variable (or outcomes)
3. Pre-testing and post-testing
4. Experimental and control group
Diunduh dari: …. … 13/9/2012
Strengths of Experimental Designs
1. Control over study
2. Can ordinarily use random
assignment manipulation of
one or more IVs.
3. The isolation of the
experimental variable and
its impact over time.
4. Replication due to the fact
that it requires little time
and money.
Weaknesses of
Experimental Designs
1. Very artificial
2. Lack external
Diunduh dari: …. … 13/9/2012
Quasi-Experimental Design
• Quasi-experimental designs provide alternate
means for examining causality in situations
which are not conducive to experimental
• The designs should control as many threats to
validity as possible in situations where at least
one of the three elements of true experimental
research is lacking (i.e. manipulation,
randomization, control group).
• Correlational research attempts to determine
whether and to what degree, a relationship exists
between two or more quantifiable (numerical)
• It is important to remember that if there is a
significant relationship between two variables it
does not follow that one variable causes the other.
• When two variables are correlated you can use the
relationship to predict the value on one variable for
a participant if you know that participant’s value on
the other variable.
C.R. = the systematic investigation of
relationships among two or more variables,
without necessarily determining cause and effect.
Correlation implies prediction but not causation.
The investigator frequently reports the
correlation coefficient, and the p-value to
determine strength of the relationship.
Diunduh dari: ….. 12/9/2012
The purpose of correlational research is to discover relationships
between two or more variables.
Relationship means that an individuals status on one variable
tends to reflect his or her status on the other.
Helps us understand related events, conditions, and behaviors.
– Is there a relationship between educational levels of farmers
and crop yields?
• To make predictions of how one variable might predict another
– Can high school grades be used to predict college grades?
Diunduh dari: ….. 12/9/2012
• Variables to be study are identified
• Questions and/or hypotheses are stated
• A sample is selected (a minimum of 30 is needed)
• Data are collected
• Correlations are calculated
• Results are reported
Diunduh dari:
QDAS_ZV_Rjqgm2Kpw6sfLzlMPrCXY2kABxq8H&sig=AHIEtbSOr4WHUjdtaIBisvUJufOzs6y0mg ….. 12/9/2012
direction and
strength of a
source: Diunduh dari:….. 12/9/2012
With correlation
analysis, the relationship
may be a causal
(independent and
dependent variable) or a
non-causal relationship
(variable 1 and variable
Classic Example of a
source: Diunduh dari:….. 12/9/2012
Diunduh dari: ….. 12/9/2012
Cross-correlation analysis between serum biochemical indices and metabolic risk factors of T2DM.
Only significant correlations are highlighted and numbered. For each significant correlation, Pearson's correlation
coefficients (r), p-values and sample sizes are shown in parentheses.
Arora et al. BMC Medical Genetics 2011 12:95 doi:10.1186/1471-2350-12-95
Meta-analysis is essentially a
synthesis of available studies
about a topic to arrive at a single
From data that is after the fact that has occurred naturally
(no interference from the researcher), a hypothesis of
possible future correlation is drawn. Correlation studies
are not cause and effect, they simply prove a correlation
or not (Simon & Francis, 2001).
Meta-analysis combines the results of several studies that
address a set of related research hypotheses. "The first
meta-analysis was performed by Karl Pearson in 1904, in
an attempt to overcome the problem of reduced statistical
power in studies with small sample sizes; analyzing the
results from a group of studies can allow more accurate
data analysis" (Wekipedia., 2006.
Pearson (1904) reviewed evidence on the effects of a vaccine
against typhoid.
– Pearson gathered data from eleven relevant studies of immunity and
mortality among soldiers serving in various parts of the British Empire.
– Pearson calculated statistics showing the association between the
frequency of vaccination and typhoid for each of the eleven studies,
and then synthesized the statistics, thus producing statistical averages
based on combining information from the separate studies.
– Begins with a systematic process of identifying similar studies.
– After identifying the studies, define the ones you want to keep for the
meta-analysis. This will help another researcher faced with the same
body of literature applying the same criteria to find and work with the
same studies.
– Then structured formats are used to key in information taken from the
selected studies.
– Finally, combine the data to arrive at a summary estimate of the effect,
it’s 95% confidence interval, and a test of homogeneity of the studies.
• Begins with a systematic process of identifying
similar studies.
• After identifying the studies, define the ones you
want to keep for the meta-analysis. This will help
another researcher faced with the same body of
literature applying the same criteria to find and work
with the same studies.
• Then structured formats are used to key in
information taken from the selected studies.
• Finally, combine the data to arrive at a summary
estimate of the effect, it’s 95% confidence interval,
and a test of homogeneity of the studies.
In statistics, a meta-analysis refers to methods focused on contrasting
and combining results from different studies, in the hope of
identifying patterns among study results, sources of disagreement
among those results, or other interesting relationships that may come
to light in the context of multiple studies.
In its simplest form, this is normally by identification of a common
measure of effect size, of which a weighted average might be the
output of a meta-analysis.
The general aim of a meta-analysis is to more powerfully estimate the
true effect size as opposed to a less precise effect size derived in a
single study under a given single set of assumptions and conditions.
Diunduh dari: ….. 12/9/2012
Advantages of Meta-Analysis
The advantages of meta-analysis (e.g. over classical literature reviews,
simple overall means of effect sizes etc.) are that it:
1. Shows whether the results are more varied than what is expected from the
sample diversity,
2. Allows derivation and statistical testing of overall factors and effect-size
parameters in related studies,
3. Is a generalization to the population of studies,
4. Is able to control for between-study variation,
5. Includes moderators to explain variation,
6. Has higher statistical power to detect an effect than in 'n=1 sized study
7. Deals with information overload: the high number of articles published each
8. Combines several studies and will therefore be less influenced by local
findings than single studies will be, and
9. Makes it possible to show whether a publication bias exists.
Diunduh dari: ….. 12/9/2012
Meta Analisis merupakan metode yang digunakan
untuk menganalisis gagasan, ide, bahasa, asal usul,
asumsi, model, dan signifikansi dalam analisis
kebijakan publik.
Proses meta-analisis kebijakan publik diawali dengan
memahami makna dan gagasan tentang publik. Istilah
“publik” dimaknai sebagai aktivitas manusia yang
dipandang perlu untuk diatur atau diintervensi oleh
pemerintah atau aturan sosial, atau setidaknya oleh
tindakan bersama.
Diunduh dari: ….. 12/9/2012
Meta-analisis merupakan suatu teknik statistika yang
menggabungkan dua atau lebih penelitian
sejenis sehingga diperoleh paduan data secara kuantitatif.
Meta-analisis merupakan suatu studi observasional
retrospektif, dalam artian peneliti membuat rekapitulasi
data tanpa melakukan manipulasi eksperimental.
Meta analysis tidak fokus pada kesimpulan yang didapat
pada berbagai studi, melainkan fokus pada data; seperti
melakukan operasi pada variabel- variabel, besarnya
ukuran efek, dan ukuran sampel.
Diunduh dari: ….. 12/9/2012
Should I do a Quantitative Study?
• Problem definition is the first step in any
research study.
• Rather than fitting a technique to a
problem, we allow the potential solutions
to a problem determine the best
methodology to use.
• Problem drives methodology…most of the
Diunduh dari: ….. 12/9/2012
Quantitative studies require the researcher to
measure variables, such as time, treatment, and
weight; and analyse the relationships among
variables using statistics.
The study can be either descriptive, which simple
measures things as they are; or experimental,
where there is an attempt to change or otherwise
affect the subjects of the study to observe the
Diunduh dari: ….. 12/9/2012
1. Research design & procedures
What is the research design? Experimental? Quasi-experimental?
Descriptive? Ex post facto? How will the study be conducted?
2. Sample, Population, or Subjects
Describe the sample: Who are the subjects? How are they to be
selected? What are important characteristics of the sample
3. Variables in the Study
Describe both the dependent and independent variables in the study
4. Instrumentation and Materials
How will each variable be measured? What measurement
instruments will be used?
What materials
5. Data Analysis
What statistical treatments of the data will be carried out?
Diunduh dari: - Amerika Serikat ….. 12/9/2012
• A variable, as opposed to a constant, is anything
that can vary, or be expressed as more than one
value, or is in various values or categories
(Simon, 2006).
• Quantitative designs have at least two types of
variables: independent and dependent
(Creswell, 2004).
• independent variable (x-value) can be
manipulated, measured, or selected prior to
measuring the outcome or dependent variable
Diunduh dari: ….. 12/9/2012
• Intervening or moderating variables affect
some variables and are affected by other
• They influence the outcome or results and
should be controlled as much as possible
through statistical tests and included in the
design (Sproull, 1995).
• (ANCOVA) may be used to statistically control
for extraneous variables. This approach adjusts
for group differences on the moderating
variable (called a covariate) that existed before
the start of the experiment.
Diunduh dari: ….. 12/9/2012
Data is a collection of a
number of pieces of
information. Each specific
piece of information is called
an observation.
The observations are
measurements of certain
characteristics which we call
The word “variable” is used
because the pieces of
information, the
observations, vary from one
person to the next.
Diunduh dari: ….. 12/9/2012
Research Variables
Any factor that can take on different values is a scientific variable and
influences the outcome of experimental research.
Most scientific experiments measure quantifiable factors, such as time or
weight, but this is not essential for a component to be classed as a variable.
Gender, color and country are all perfectly acceptable variables, because
they are inherently changeable.
As an example, most of us have filled in surveys where a researcher asks
questions and asks you to rate answers. These responses generally have a
numerical range, from ‘1 - Strongly Agree’ through to ‘5 - Strongly
Disagree’. This type of measurement allows opinions to be statistically
analyzed and evaluated.
Diunduh dari:….. 12/9/2012
1. A variable is something that can change, such as 'gender' and are typically
the focus of a study.
2. Attributes are sub-values of a variable, such as 'male' and 'female'. An
exhaustive list contains all possible answers, for example gender could also
include 'male transgender' and 'female transgender' (and both can be preor post-operative).
3. Mutually exclusive attributes are those that cannot occur at the same time.
Thus in a survey a person may be requested to select one answer from a list
of alternatives (as opposed to selecting as many that might apply).
4. Quantitative data is numeric. This is useful for mathematical and statistical
analysis that leads to a predictive formula.
5. Qualitative data is based on human judgement. You can turn qualitative data
into quantitative data, for example by counting the proportion of people who
hold a particular qualitative viewpoint.
6. Units are the ways that variables are classified. These include: individuals,
groups, social interactions and objects.
Diunduh dari:….. 12/9/2012
1. Descriptive variables are those that which will be reported on, without
relating them to anything in particular.
2. Categorical variables result from a selection from categories, such as
'agree' and 'disagree'. Nominal and ordinal variables are categorical.
3. Numeric variables give a number, such as age.
4. Discrete variables are numeric variables that come from a limited set of
numbers. They may result from , answering questions such as 'how
many', 'how often', etc.
5. Continuous variables are numeric variables that can take any value,
such as weight.
Diunduh dari: ….. 12/9/2012
Variable and Atribute
In science and research, attribute is a characteristic of an
object (person, thing, etc.).
While an attribute is often intuitive, the variable is the operationalized
way in which the attribute is represented for further data processing.
In data processing data are often represented by a combination of items
(objects organized in rows), and multiple variables (organized in columns).
Values of each variable statistically "vary" (or are distributed) across the
variable's domain.
Domain is a set of all possible values that a variable is allowed to have. The
values are ordered in a logical way and must be defined for each variable.
Domains can be bigger or smaller. The smallest possible domains have
those variables that can only have two values, also called binary (or
dichotomous) variables. Bigger domains have non-dichotomous variables
and the ones with a higher level of measurement.
Diunduh dari: ….. 12/9/2012
Variable and Atribute
An example
Age is an attribute that can be operationalized in many ways. It can be
dichotomized so that only two values - "old" and "young" - are allowed
for further data processing.
In this case the attribute "age" is operationalized as a binary variable. If
more than two values are possible and they can be ordered, the attribute is
represented by ordinal variable, such as "young", "middle age", and
"old". Next it can be made of rational values, such as 1, 2, 3.... 99
The "social class" attribute can be operationalized in similar ways as age,
including "lower", "middle" and "upper class" and each class could be
differentiated between upper and lower, transforming thus changing the
three attributes into six or it could use different terminology.
Diunduh dari:….. 12/9/2012
Independent Variables
An independent variable is a factor that can be varied or manipulated
in an experiment (e.g. time, temperature, concentration, etc). It is
usually what will affect the dependent variable.
There are two types of independent variable, which are often treated
differently in statistical analyses:
1. Quantitative variables that differ in amounts or scale and can be
ordered (e.g. weight, temperature, time).
2. Qualitative variables which differ in "types" and can not be
ordered (e.g. gender, species, method).
By convention when graphing data, the independent variable is
plotted along the horizontal X-axis with the dependent variable on
the vertical Y-axis
Diunduh dari: ….. 12/9/2012
Research Questions and
The aim is :
1. to determine what the relationship is
between one thing (an independent
variable) and another (dependent
2. the difference between groups with
regard to a variable measure;
3. the degree to which a condition exists.
Diunduh dari: ….. 12/9/2012
Research Questions and Hypotheses
• Although a research question may contain more than one
independent and dependent variable, each hypothesis can
contain only one of each type of variable. There must be a
way to measure each type of variable.
• A correctly formulated hypotheses, should answer the
following questions:
1. What variables am I, the researcher, manipulating, or is
responsible for a situation? How can this be measured?
2. What results do I expect? How can this be measured?
3. Why do I expect these results? The rationale for these
expectations should be made explicit in the light of the
review of the literature and personal experience.
This helps form the conceptual or theoretical framework for the
Research Questions and Hypotheses
• A hypothesis is a logical supposition, a reasonable
guess, or an educated conjecture. It provides a
tentative explanation for a phenomenon under
• Research hypothesis are never proved or disproved.
They are supported or not supported by the data.
• If the data run contrary to a particular hypothesis,
the researcher rejects that hypothesis and turns to
an alternative as being a more likely explanations of
the phenomenon in question, (Leedy & Ormrod,
Diunduh dari: ….. 12/9/2012
According to Schick and Vaughn (2002), researchers weighing up
alternative hypotheses may take into consideration:
1. Test-ability (compare falsifiability)
2. Parsimony (as in the application of "Occam's razor",
discouraging the postulation of excessive numbers of entities)
Scope – the apparent application of the hypothesis to multiple cases
of phenomena
Fruitfulness – the prospect that a hypothesis may explain further
phenomena in the future
Conservatism – the degree of "fit" with existing recognized
What is a research question?
A research question is a clear, focused, concise, complex and
arguable question around which you center your research.
You should ask a question about an issue that you are
genuinely curious about.
Research questions help writers focus their research by
providing a path through the research and writing process.
The specificity of a well-developed research question helps
writers avoid the “all-about” paper and work toward
supporting a specific, arguable thesis.
Diunduh dari: ….. 12/9/2012
Steps to developing a research question
1. Choose an interesting general topic. Even directed academic research should focus on a
topic in which the writer is at least somewhat personally invested. Writers should choose
a broad topic about which they genuinely would like to know more.
2. Do some preliminary research on your general topic. Do a few quick searches in current
periodicals and journals on your topic to see what’s already been done and to help you
narrow your focus. What questions does this early research raise?
3. Consider your audience. For most college papers, your audience will be academic, but
always keep your audience in mind when narrowing your topic and developing your
question. Would that particular audience be interested in this question?
4. Start asking questions. Taking into consideration all of the above, start asking yourself
open-ended “how” and “why” questions about your general topic. For example, “How
did the slave trade evolve in the 1850s in the American South?” or “Why were slave
narratives effective tools in working toward the abolishment of slavery?”
5. Evaluate your question.
Is your research question clear? Is your research question focused?
Is your research question complex?
Diunduh dari:….. 12/9/2012
Theoretical Framework
A theoretical framework is a collection of interrelated concepts,
like a theory but not necessarily so well worked-out.
A theoretical framework guides your research, determining what
things you will measure, and what statistical relationships you will
look for.
Theoretical frameworks are obviously critical in deductive,
theory-testing sorts of studies.
In those kinds of studies, the theoretical framework must be very
specific and well-thought out.
Diunduh dari:….. 12/9/2012
Theoretical Framework
The independent variables, also
known as the predictor or
explanatory variables, are the factors
that you think explain variation in
the dependent variable.
In other words, these are the causes.
For example, you may think that
people are more satisfied with their
jobs if they are given a lot of freedom
to do what they want, and if they are
So 'job freedom' and 'salary' are the
independent variables, and 'job
satisfaction' is the dependent
Diunduh dari: ….. 16/9/2012
Theoretical Framework
Barry P. Haynes, (2007) "Office
productivity: a theoretical framework",
Journal of Corporate Real Estate, Vol. 9
Iss: 2, pp.97 – 110.
Validated theoretical framework of
office productivity.
A model can be developed to represent
the concept of office productivity with
the dimensions of physical environment
and behavioural environment.
It can therefore be concluded that a
validated model has been developed,
and in light of this study's research
findings, the theoretical framework for
office productivity can be redefined.
Diunduh dari: ….. 16/9/2012
Theoretical Framework
A theoretical framework consists of concepts, together with their definitions,
and existing theory/theories that are used for your particular study.
The theoretical framework must demonstrate an understanding of theories and
concepts that are relevant to the topic of your research paper and that will relate it
to the broader fields of knowledge in the class you are taking.
The theoretical framework is not something that is found
readily available in the literature.
You must review course readings and pertinent research literature for theories and
analytic models that are relevant to the research problem you are investigating. The
selection of a theory should depend on its appropriateness, ease of application, and
explanatory power.
Diunduh dari:….. 16/9/2012
Theoretical Framework
The theoretical framework strengthens the study in the following
1. An explicit statement of theoretical assumptions permits the reader to evaluate them
2. The theoretical framework connects the researcher to existing knowledge. Guided by a
relevant theory, you are given a basis for your hypotheses and choice of research
3. Articulating the theoretical assumptions of a research study forces you to address
questions of why and how. It permits you to move from simply describing a phenomenon
observed to generalizing about various aspects of that phenomenon.
4. Having a theory helps you to identify the limits to those generalizations. A theoretical
framework specifies which key variables influence a phenomenon of interest. It alerts you
to examine how those key variables might differ and under what circumstances.
5. By virtue of its application nature, good theory in the social sciences is of value precisely
because it fulfills one primary purpose: to explain the meaning, nature, and challenges of
a phenomenon, often experienced but unexplained in the world in which we live, so that
we may use that knowledge and understanding to act in more informed and effective
Diunduh dari: ….. 16/9/2012
Theoritical Framework
Relationship between
green management and
environmental training in
companies located in
A theoreticalframework
and case studies
Adriano Alves Teixeira , Charbel
José Chiappetta Jabbour , Ana
Beatriz Lopes de Sousa Jabbour.
International Journal of Production
Economics. Volume 140, Issue 1,
November 2012, Pages 318–329.
relating green
management and
environmental training.
Diunduh dari: ….. 16/9/2012
Theoretical Framework
The effect of
friendly perceptions on
festival visitors’
process using an
extended model of
goal-directed behavior
Hak Jun Song, Choong-Ki Lee,
Soo K. Kang, Sug-jin Boo.
Tourism Management. Volume
33, Issue 6, December 2012,
Pages 1417–1428.
A proposed research
Diunduh dari:….. 16/9/2012
Poh Lean Chuah, Wai
Peng Wong, T.
Ramayah, M. Jantan,
context, supplier
practices and
performance: A case
study of a
company in
Journal of Enterprise
Information Management, Vol.
23 Iss: 6, pp.724 – 758.
Diunduh dari: ….. 16/9/2012
management for
aircraft noise
Theoritical Framework
We have developed an
optimisation tool to compute
noise annoyance optimal
trajectories for specific
The involved airport, with
its surrounding cartography,
geography and
meteorological data, define
an scenario.
In this scenario, a given
trajectory produces a given
amount of noise annoyance,
in function of the emitted
aircraft noise.
Diunduh dari: ….. 16/9/2012
Modelling instantaneous
traffic emission and the
influence of traffic
speed limits
Theoritical Framework
Luc Int Panis, Steven Broekx,
Ronghui Liu.
Science of The Total
Environment. Volume 371,
Issues 1–3, 1 December 2006,
Pages 270–285.
The proposed model
framework to analyze the
relationship between
transport policy, traffic
network conditions,
vehicle emissions and
urban air pollution.
Diunduh dari: ….. 16/9/2012
Minga Negash, (2012)
Management Research Review. Vol. 35 Iss: 7, pp.577 – 601.
Diunduh dari: ….. 16/9/2012
Aldónio Ferreira, Carly Moulang, Bayu Hendro.
Environmental management accounting and innovation: an exploratory
analysis. Emerald 23, (2010)
Diunduh dari: ….. 16/9/2012
Guy Assaker, Vincenzo Esposito Vinzi, Peter O'Connor, (2011).
Modeling a causality network for tourism development: an empirical
Journal of Modelling in Management, Vol. 6 Iss: 3, pp.258 - 278
Diunduh dari:….. 16/9/2012
Typologi of
sampling design
There are many
different sampling
designs, each with
advantages and
disadvantages for
assessment of
different products.
Figure provides a
typology of sampling
Diunduh dari: ….. 16/9/2012
Analysis of the
Performance of MFIs: A
Case Study of the
Initiatives for
Development Foundation
- Financial Service
Private Limited (IDFFSPL),
Using a random sampling
technique, he focused on
cases in the rural and urban
parts of the Dharwad district
of Karnataka State in India.
Diunduh dari: ….. 16/9/2012
Cluster Sampling
A sampling strategy where
the population of interest is
divided into representative
"clusters" of individuals,
among whom a random
selection of subjects is
Cluster sampling is often
conducted when it is
impossible or impractical to
draw a simple random
sample or stratified sample
because the researcher
cannot get a complete list of
members of the population.
Diunduh dari:….. 16/9/2012
Choosing a representative sample from a population is a multistep process that
ensures the information received is useful. In the sampling process, the
following steps must be conducted:
Defining the population
In this step, a population is defined for surveying. If an organization is
interested in the purchasing behaviors of college students in a particular city,
then all students in that city are considered a population.
For some survey studies, the population is simply defined as the consumers (e.g.
Internet users or mall shoppers). However, marketing strategies focus on
specific demographics to survey in a population. If the manufacturer of
specialty rugs is interested only in the buying preferences of upper middle class
residents, people who make a certain amount of money and above (e.g. $250K
per year) would be the population. A clear definition of a population is
important for the accuracy of the remainder of the steps.
Diunduh dari: ….. 16/9/2012
Choosing a representative sample from a population is a multistep process that
ensures the information received is useful. In the sampling process, the
following steps must be conducted:
Developing a sampling frame
A sampling frame provides a source or a listing of all elements
or individuals within a population.
In the example of the specialty rugs manufacturer, a sampling frame of upper
middle class individuals could be public records that show tax and income
figures. Since those records reflect all high income earners in one city, they are
considered the sampling frame for the survey study.
In sales and marketing, a sampling frame is not as easy to obtain as customer
lists may not be available.
For many organizations, sampling frames are usually previous customers’ lists
or those purchased from other companies.
Diunduh dari: ….. 16/9/2012
Choosing a representative sample from a population is a multistep process that
ensures the information received is useful. In the sampling process, the
following steps must be conducted:
Determining sample size
Once a sampling frame is identified, a sample size is determined.
The size of a chosen sample depends on a number of factors: the
number of questions in the survey, the type of questions, and the
purpose of the survey.
Sample sizes can range from 30 to several hundred depending on
the availability of time and cost.
Diunduh dari: ….. 16/9/2012
Specifying sample method
This final step in the sampling
process determines the
sampling methodology.
For instance, a survey may
require only answers from
experts in a field.
Another survey that is
informal may be given to any
customers that frequent a
business without regard for
the population from which it
is drawn.
Diunduh dari: ….. 16/9/2012
In the final step of the
sampling process, a
particular methodology
is chosen and applied.
This methodology
depends on the type of
sample that is surveyed.
Samples are divided in
probability and nonprobability samples
Diunduh dari: ….. 16/9/2012
Sample Size
• Note: We can use the following formula to determine the sample size
necessary to discover the “true” mean value from a population.
• where zа/2 corresponds to a confidence level (found on a table or
computer program). Some common values are 1.645 or 1.96, which
might reflect a 95% confidence level (depending on the statistical
hypothesis under investigation), and 2.33, which could reflect a 99%
confidence level in a one-tailed test and 2.575 for a two-tailed test s
is the standard deviation, and E is the margin of error.
• Example: If we need to be 99% confident that we are within 0.25 lbs
of a true mean weight of babies in an infant care facility, and s = 1.1,
we would need to sample 129 babies:
• n = [2.575 (1.1)/0.25]2 = 128.3689 or 129.
Diunduh dari: ….. 12/9/2012
Sample Size –sigma unknown
In most studies, 5%
sampling error is
Sample Size
• Gay (1996, p. 125) suggested general rules
similar to Suskie’s for determining the sample
– For small populations (N < 100), there is little point in
sampling and surveys should be sent to the entire
– For population size ≈ 500 50% of the population should
be sampled
– For population size ≈ 1,500, 20% should be sampled
– At approximately N = 5,000 and beyond, the population
size is almost irrelevant and a sample size of 400 is
adequate. Thus, the larger the population, the smaller the
percentage needed to get a representative sample.
Other Considerations in Selecting a sample
• Characteristics of the sample. Larger samples are
needed for heterogeneous populations; smaller
samples are needed for homogeneous populations
(Leedy & Ormrod, 2001).
• Cost of the study. A minimum number of participants is
needed to produce valid results.
• Statistical power needed. Larger samples yield greater
the statistical power. In experimental research, power
analysis is used to determine sample size (requires
calculations involving statistical significance, desired
power, and the effect size).
Other Considerations in Selecting a sample
• Confidence level desired (reflects accuracy of
sample; Babbie, 2001)
• Purpose of the study. Merriam (1998) stated,
"Selecting the sample is dependent upon the
research problem“ .
• Availability of the sample. Convenience samples
are used when only the individuals that are
convenient to pick are chosen for the sample. It
is sometimes known as a location sample as
individuals might be chosen from just one area.
Analisis Data
• Sample Size (n), Statistic (descriptive),
substantive hypothesis
• Data Type (NOIR), Distribution
Determines the type of Test:
T-test, chi-square, ANOVA, Pearson,
Analysis of data is a process of inspecting, cleaning,
transforming, and modeling data with the goal of highlighting
useful information, suggesting conclusions, and supporting
decision making.
Data analysis has multiple facets and approaches,
encompassing diverse techniques under a variety of names, in
different business, science, and social science domains.
Data mining is a particular data analysis technique that
focuses on modeling and knowledge discovery for predictive
rather than purely descriptive purposes.
Business intelligence covers data analysis that relies heavily on
aggregation, focusing on business information.
Diunduh dari: ….. 16/9/2012
In statistical applications, some people divide data analysis
into descriptive statistics, exploratory data analysis (EDA),
and confirmatory data analysis (CDA).
EDA focuses on discovering new features in the data and CDA
on confirming or falsifying existing hypotheses.
Predictive analytics focuses on application of statistical or
structural models for predictive forecasting or classification,
while text analytics applies statistical, linguistic, and
structural techniques to extract and classify information from
textual sources, a species of unstructured data.
Diunduh dari: ….. 16/9/2012
Data integration is a precursor to data analysis,
and data analysis is closely linked to data
visualization and data dissemination.
The term data analysis is sometimes used as a
synonym for data modeling.
Diunduh dari: ….. 16/9/2012
Data cleaning
Data cleaning is an important procedure during which the data are
inspected, and erroneous data are—if necessary, preferable, and
Data cleaning can be done during the stage of data entry. If this is done, it
is important that no subjective decisions are made.
The guiding principle is: during subsequent manipulations of the data,
information should always be cumulatively retrievable.
In other words, it should always be possible to undo any data set
alterations. Therefore, it is important not to throw information away at
any stage in the data cleaning phase.
All information should be saved (i.e., when altering variables, both the
original values and the new values should be kept, either in a duplicate
data set or under a different variable name), and all alterations to the data
set should carefully and clearly documented, for instance in a syntax or a
Diunduh dari:….. 16/9/2012
Quality of data
The quality of the data should be checked as early as possible. Data quality can be assessed in
several ways, using different types of analyses: frequency counts, descriptive statistics (mean,
standard deviation, median), normality (skewness, kurtosis, frequency histograms, normal
probability plots), associations (correlations, scatter plots).
Other initial data quality checks are:
1. Checks on data cleaning: have decisions influenced the distribution of the variables? The
distribution of the variables before data cleaning is compared to the distribution of the
variables after data cleaning to see whether data cleaning has had unwanted effects on the
2. Analysis of missing observations: are there many missing values, and are the values
missing at random? The missing observations in the data are analyzed to see whether
more than 25% of the values are missing, whether they are missing at random (MAR),
and whether some form of imputation is needed.
3. Analysis of extreme observations: outlying observations in the data are analyzed to see if
they seem to disturb the distribution.
4. Comparison and correction of differences in coding schemes: variables are compared with
coding schemes of variables external to the data set, and possibly corrected if coding
schemes are not comparable.
5. Test for common-method variance.
Diunduh dari:….. 16/9/2012
Quality of measurements
The quality of the measurement instruments should only be checked
during the initial data analysis phase when this is not the focus or
research question of the study. One should check whether structure of
measurement instruments corresponds to structure reported in the
There are two ways to assess measurement quality:
1. Confirmatory factor analysis
2. Analysis of homogeneity (internal consistency), which gives an
indication of the reliability of a measurement instrument. During
this analysis, one inspects the variances of the items and the
Diunduh dari: ….. 16/9/2012
Initial transformations
After assessing the quality of the data and of the measurements, one might
decide to impute missing data, or to perform initial transformations of one
or more variables, although this can also be done during the main analysis
Possible transformations of variables are:
1. Square root transformation (if the distribution differs moderately from
2. Log-transformation (if the distribution differs substantially from
3. Inverse transformation (if the distribution differs severely from
4. Make categorical (ordinal / dichotomous) (if the distribution differs
severely from normal, and no transformations help)
Diunduh dari: ….. 16/9/2012
Characteristics of data sample
In any report or article, the structure of the sample must be
accurately described. It is especially important to exactly determine
the structure of the sample (and specifically the size of the subgroups)
when subgroup analyses will be performed during the main analysis
The characteristics of the data sample can be assessed by looking at:
1. Basic statistics of important variables
2. Scatter plots
3. Correlations
4. Cross-tabulations
Diunduh dari: ….. 16/9/2012
Exploratory and confirmatory approaches
In an exploratory analysis no clear hypothesis is stated before analysing
the data, and the data is searched for models that describe the data well. In
a confirmatory analysis clear hypotheses about the data are tested.
Exploratory data analysis should be interpreted carefully.
An exploratory analysis is used to find ideas for a theory, but not to test
that theory as well. When a model is found exploratory in a dataset, then
following up that analysis with a comfirmatory analysis in the same
dataset could simply mean that the results of the comfirmatory analysis
are due to the same type 1 error that resulted in the exploratory model in
the first place.
The comfirmatory analysis therefore will not be more informative than the
original exploratory analysis.
Diunduh dari: ….. 16/9/2012
Many statistical methods have been used for statistical
A very brief list of four of the more popular methods is:
General linear model: A widely used model on which various
statistical methods are based (e.g. t test, ANOVA, ANCOVA,
MANOVA). Usable for assessing the effect of several predictors on
one or more continuous dependent variables.
Generalized linear model: An extension of the general linear model
for discrete dependent variables.
Structural equation modelling: Usable for assessing latent
structures from measured manifest variables.
Item response theory: Models for (mostly) assessing one latent
variable from several binary measured variables (e.g. an exam).
Diunduh dari: ….. 16/9/2012
• Hypothesis testing is a method of testing
claims made about populations by using a
sample (subset) from that population.
– Like checking out a carefully selected hand full of
M&Ms to determine the makeup of a Jumbo Size
• After data are collected, they are used to
produce various statistical numbers such as
means, standard deviations, and percentages.
• These descriptive numbers summarize or describe
the important characteristics of a known set of data.
• In hypothesis testing, descriptive numbers are
standardized (Test Values) so that they can be
compared to fixed values (found in tables or in
computer programs) (Critical Values) that indicate
how unusual it is to obtain the data collected.
• Once data are standardized and significance
determined, we can make inferences about an entire
population (universe).
• A p-value (or probability value) is the
probability of getting a value of the sample
test statistic that is at least as extreme as the
one found from the sample data, assuming
the null hypothesis is true.
• Traditionally, statisticians used alpha (а)
values that set up a dichotomy: reject/fail to
reject null hypothesis. P-values measure how
confident we are in rejecting a null
• Note: If the null hypothesis is not rejected, this does
not lead to the conclusion that no association or
differences exist, but instead that the analysis did not
detect any association or difference between the
variables or groups.
• Failing to reject the null hypothesis is comparable to
a finding of not guilty in a trial. The defendant is not
declared innocent. Instead, there is not enough
evidence to be convincing beyond a reasonable
doubt. In the judicial system, a decision is made and
the defendant is set free.
p < 0.01
p < 0.05
Moderate evidence against H0
p < 0.10
Suggestive evidence against H0
p > 0.10
Little or no real evidence against H0
In statistics, validity has no single agreed definition but generally refers
to the extent to which a concept, conclusion or measurement is wellfounded and corresponds accurately to the real world.
The word "valid" is derived from the Latin “validus,
meaning strong”.
The validity of a measurement tool (for example, a test in education) is
considered to be the degree to which the tool measures what it claims to
In the area of scientific research design and experimentation, validity
refers to whether a study is able to scientifically answer the questions it
is intended to answer.
Diunduh dari: ….. 12/9/2012
Internal validity is an inductive estimate of the degree to which conclusions
about causal relationships can be made (e.g. cause and effect), based on the
measures used, the research setting, and the whole research design.
Eight kinds of confounding variable can interfere with internal validity (i.e.
with the attempt to isolate causal relationships):
1. History, the specific events occurring between the first and second measurements in
addition to the experimental variables
2. Maturation, processes within the participants as a function of the passage of time (not
specific to particular events), e.g., growing older, hungrier, more tired, and so on.
3. Testing, the effects of taking a test upon the scores of a second testing.
4. Instrumentation, changes in calibration of a measurement tool or changes in the
observers or scorers may produce changes in the obtained measurements.
5. Statistical regression, operating where groups have been selected on the basis of their
extreme scores.
6. Selection, biases resulting from differential selection of respondents for the comparison
7. Experimental mortality, or differential loss of respondents from the comparison groups.
8. Selection-maturation interaction, etc. e.g., in multiple-group quasi-experimental designs
Diunduh dari: ….. 12/9/2012
External validity concerns the extent to which the (internally valid)
results of a study can be held to be true for other cases, for example to
different people, places or times.
If the same research study was conducted in those other cases, would it
get the same results?
A major factor in this is whether the study sample (e.g. the research
participants) are representative of the general population along
relevant dimensions. Other factors jeopardizing external validity are:
1. Reactive or interaction effect of testing, a pretest might increase the
scores on a posttest
2. Interaction effects of selection biases and the experimental variable.
3. Reactive effects of experimental arrangements, which would preclude
generalization about the effect of the experimental variable upon
persons being exposed to it in non-experimental settings
4. Multiple-treatment interference, where effects of earlier treatments are
not erasable.
Diunduh dari:….. 12/9/2012
1. To be ethical, scientific research must be
conducted in a methodologically rigorous
2. Scientifically significant, good question + bad
method and/or conduct = invalid results
3. Invalid research is a waste of resources
4. Exploits people.
Diunduh dari: ….. 12/9/2012
Method must be valid
Practically feasible
A clear scientific objective
Well designed, accepted principles
Sufficiently powered – adequate
6. A plausible data analysis plan
7. Must be executable
Diunduh dari: ….. 12/9/2012
Threats to Internal validity
1. History
2. Maturation
3. Testing
4. Instrumentation
5. Statistical Regression
6. Selection bias
7. Experimental Mortality (Attrition)
8. Diffusion or imitation of treatments
9. Demoralization
Diunduh dari: …. … 13/9/2012
Threats to External validity
External Validity
1. This refers to the
extent to which we can
generalize the findings
of a study to settings
and populations beyond
the study conditions.
2. It deals with the
representativeness of
the study sample,
setting, and
Threats to External Validity
1. Reactive or interactive effect of
2. Interaction effects of selection
biases and any research
3. Reaction effects of
4. Multiple-treatment interaction
(Grinnell, 1997).
Diunduh dari: …. … 13/9/2012
Threats to validity
John Henry Effect:
A tendency of people in a control group to take the
experimental situation as a challenge and exert more
effort than they otherwise would; they try to beat
the experimental group.
This negates the whole purpose of a control group. So
called because this was discovered at the John Henry
Company where a new power tool was being tested
to see if it could improve productivity.
The workers using the old tool took it as a challenge to
work harder to show they were just as good and
should get the new tool.
Best, J. W. & Kahn, J. V. (1993). Research in education (7th ed.). Boston: Allyn and Bacon.
Babbi, E. (2001). The practice of social research. Australia: Wadsworth Thomson Learning.
Burns, n., & Grove, K. (1993). The practice of nursing research: Conduct, critique and utilization (2nd ed.). Philadelphia: Saunders.
Cooper, D. R., & Schindler, P.S. (2002). Business research methods (8th ed.). Boston: Irwin.
Cormack, D. (1991). Team spirit motivation and commitment team leadership and membership, team evaluation. Grand Rapids, MI:
Pyranee Books.
Creswell, J. W. (2004). Educational research: Planning, conducting, and evaluating quantitative and qualitative research (2nd
ed.). Columbus, Ohio: Merrill Prentice Hall.
Emerson, R. W. (1983).New England Reformers', lecture to the Society, 3 March 1844
Gay. L. R. (1996). Educational research: Competencies for analysis and application (4th ed.). Beverly Hills, CA: Sage.
Leedy, P., & Ormrod, J. E. (2001). Practical research planning and design (8th ed.). New York: Macmillan.
Merriam, S. B. (1997). Qualitative research and case study applications in education. San Francisco: Jossey-Bass.
Pearson, K (1904). Report on certain enteric fever inoculation statistics. BMJ 3:1243-1246.
Simon, M. K. (2006). Dissertation and scholarly research: A practical guide to start and complete your dissertation, thesis, or formal
research project. Dubuque, Iowa: Kendall/Hunt.
Simon, M. K., & Francis, B. J. (2001). The dissertation cookbook: From soup to
nuts a practical guide to start and complete your dissertation (3rd. Ed.). Dubuque, Iowa: Kendall/Hunt.
Sproull, N. D. (1995). Handbook of research methods: A guide for practitioners and Students in the social sciences (2nd. Ed.). New Jersey:
The Scarecrow Press.
Sproull, N. D. (2004). Handbook of research methods: A guide for practitioners and Students in the social sciences (3rd Ed.). New Jersey:
The Scarecrow Press.
Suskie, L. (1996). Survey Research: What works. Washington D.C.: International Research.
Wekipedia. (2005). Meta-analysis. Retreived January 5, 2006, from,
Yakoobian, V. (2005). Successful leadership styles of elementary school principals and parent-teach organization leaders. Doctoral
Dissertation. University of Phoenix.
Shared with full permission from IDTL Journal – copyright IDTL, University of Phoenix, Dr. Marilyn Simon, and Dr. Kimberly Blum

similar documents