Summary – Research methods: the essential knowledge base (Chapter 1 t/m 12) + lecture
Chapter 1- Foundations
1.1 the research enterprise
There is almost no aspect in our world that is not the subject of considerable research, but what is
research and how is knowledge different from research? In short; knowledge is conducted by
experience and research is evidence conducted by a systematic plan which can be controlled and it is
related to theory. Research is a type of systematic investigation that is empirical in nature and is
designed to contribute to public knowledge. Keep in mind during this course that all research is
The nature of business and management research is:
Transdisciplinary (a certain amount of disciplines)
Double hurdle (theoretical and practical impact)
Science practice gap/ translation research hard to find respondents: there is a gap
between the practice and research world
Evidence Based Management to facilitate the managerial decisions based on evidence.
Currently managers still strongly go for their own intuition. I know this company/job; my
judgement is better.
Research enterprise the macro-level effort to accumulate knowledge across multiple empirical
systematic public research. So the broader effect of research. After hundreds of years of conducting
individual research studies and then series of studies, we are finally turning our attention to the
broader environment within which all this activity takes place.
Why do we do research? Classic answer; to contribute knowledge. But it often happens that research
that led to the knowledge is contributed in unanticipated ways (the yellow notes example glue).
Actually you can split research in two types; basic research and applied research. The picture below
shows the differences:
Translational research moving research to practice in our daily lives. It’s the systematic effort to
move research from initial discovery to practice and ultimately to impact our lives. It takes a lot of
time for these theory’s to filter into practice. An example of translational research is organisational
research focused on finding solutions as soon as possible; more profit for example. It is not
published. This is described in the The Research-practice continuum the process of moving from
an initial research idea or discovery to practice, and the potential for the idea to influence our lives
the world. The research practice continuum assumes that different discoveries take different
pathways trough the continuum. The translation process works in both directions.
You start with Basic research research that is designed to generate discoveries and to understand
how the discoveries work. For discoveries related to humans you can call it applied research
projects. The process of testing if this applied research can be implanted in and disseminated to a
broad range of context is called implementation and dissemination research. Many of these studies
are done to test the impact on the society. Impact research research that assesses the broader
effects of a discovery or innovation on society. Sometimes discoveries lead to new policies that are
investigated than you do policy research (research that is designed to investigate existing policies
or develop and test new ones.
Research syntheses and guidelines
During the testing of new discovery during the basic and applied research period a number of
separate research projects are likely to be conducted. It’s a good idea to check the research synthesis
this is a systematic study of multiple prior research projects that addresses the same research
questions/topics. The synthesis summarizes the results in a way that can be used by practioners.
There are two types of research synthesis.
Meta-analysis Uses statistical methods to combine the results of similar studies
quantitatively in order to allow general conclusions to be made
Systematic review Focuses on a specific question or issue and uses specific pre-planned
methods to identify, select, assess, and summarize the findings of multiple research studies
Can be a panel of experts who discuss the research literature.
The disadvantage is that this can be written in a scientific style, which makes it hard to use. To
provide this the guideline is a useful mechanism. A guideline is a result of a systematic process
that leads to a specific set of research-based recommendations for practice that usually includes
some estimates of how strong the evidence of each recommendation.
Evidence based practice a movement designed to encourage or require practitioners to employ
practices that are based on research evidence as reflected in research synthesis or practice
guidelines. This represents a major attempt of the research enterprise to achieve a better integration
of research and practice. It’s a hard thing to identify what evidence can be.
Evolutionary epistemology the branch of philosophy that holds that ideas involve through the
process of natural selection. In this view, an individual discovery or idea is like an organism in biology
it competes with other established and emerging discoveries.
1.2 Conceptualizing research
One of the most common sourses for an research problem is a practically field problem. Another
source is literature in your specific field. Another type is the request for proposals (RFPs) published
by the government those RFPs describe some problem that the agency would like researchers to
address; they are virtually handing the researcher an idea. Of course researchers can come up with
an idea by themselves as well.
The literature review is a systematic compilation and written summary of all the literature
published in scientific journals that is related to your research topic. Check if it’s peer-reviewed, most
of the time the credibility is higher.
Feasibility (haalbaarheid) how long will the research take? Are there any ethical constraints, is it
possible to acquire the cooperation and what are the costs?
1.3 The language of research
Research has its own language. A few important basics are discussed here to have a better
Theoretical is pertaining to theory. Social research is theoretical, meaning that much of it is
concerned with developing, exploring or testing the theories or ideas that social researches have
about the world operates. Empirical based on direct observations and measurements. Probabillistic based on probabilities. Statistics enable to estimation of the probabilities for the
situation being studied. Causal pertaining to a cause-effect relationship, hypothesis or relationship. Something is causal if
it leads to an outcome or makes an outcome happen. You can say that there is a causal relationship.
For example whether your treatment or program causes an outcome to prevent/occur, you are
examining a causal relationship. So this becomes important if you study a relationship and want to
change something ‘in the world’ with your research. You can also choose to just observe, but what is
the additional value of your research? There are different types of studies
1. Descriptive studies a study that document what is going on or what exists public
2. Relational studies a study that investigated the connection between two or more
variables. A public opinion poll that compares the proportion of males and females who say
they would vote democratic or republican.
3. Causal studies a study that investigates a causal relationship between two variables. Try to
find of whether a recent political advertising campaign (cause) changed voter preferences
and their eventual vote (effect).
Don’t see the three types of research separately. To investigate a causal relationship, you
should be able to describe it and you would assume that there is a relationship. You can see
Time in research
Cross-sectional studies this take place at a single point in time.
Longitudinal studies is a study that takes places over multiple point is time, but at least
two separate occasions. You can split this up in repeated measures two or a few ‘waves’
of measurement or in time series many waves over time (at least 20).
Types of relationships
Correlational relationship says that two things perform in a synchronized manner. Example:
economics often talk about a correlation between inflation and unemployment. When inflation is
high, unemployment is also high. The two are correlated, but the relation does not tell which causes
the other. A correlation doesn’t always mean that there is a causality as well.
Causal relationship is a synchronized relationship between two variables just as a correlational
relationship, but in a causal relationship one variable causes the other to occur.
Be aware of the third/missing variable sometimes a third variable is causing a response on two
values. For example; there seemed to be a relationship between the number of children born and
the road building in Europe. Does this cause each other? Of course not, maybe a third variable as
economic growth is forcing it. So be careful with the interpretation of correlations.
Patterns of relationships
Positive relationship high values on variable one is related to high values on variable two
as well. Same with low values. Relationship between years in study and salary.
Negative relationship a relationship between variables in which high values for one
variable are associated with low values on another variable.
Curvilinear relationship the relationships can be more complex (picture D). drug for
illness. Higher dosage means feeling better, but there will be a tipping point where it does
not help you anymore.
An hypothesis is a specific statement or prediction and it describes in concrete terms what you
expect to happen in your study. Not all studies have hypotheses, for example when a study is
designed to be exploratory. It’s hard to test something you know such little things about, so a
hypotheses doesn’t make sense it those cases. We can split this up in:
Alternative hypothesis this is what you think what is going to happen (for example a relationship)
Zero hypotheses the hypothesis that describes the remaining possible outcomes (so what you
don’t think that is going to happen).
One- tailed hypothesis a hypothesis that specifies a direction; for example when your hypothesis
predicts that your program will increase the outcome of depressively.
Two-tailled hypotheses when your prediction does not specify a direction. You’re studying a new
treatment for depression. You assume that there will be an affect, but you are not sure if this is a
positive or negative effect. So 0=there is no significance difference in depression and H1=there is a
significant difference (doesn’t say if it’s positive or negative).
Hypothese-detuctive model a model in which two mutually exclusive hypotheses that together
exhaust all possible outcomes are tested, such that one hypotheses is accepted, the second must
therefore be rejected.
A variable is any entity that can take on different values. They aren’t always qualitative or numerical.
An attribute is a specific value on a variable for instance the variable sex or gender has two
attributes; male and female. Or agreement (likert scale).
It’s important to know the difference between dependent and independent variables. The
independent variable is the variable that you manipulate. For instance a program of treatment. The
dependent variable is the one that is affected by the independent variable. So the outcome of the
treatment. So independent is what you/nature does and the dependent is the result of that.
Each variable should be exhaustive what means that they should include all possible answerable
responses. So all religions for example (not only Jewish, Christen and Muslim). To prevent this you
can use the most common and use other. Than you never exclude someone. Thereby it must be
mutually exclusive this means that the respondent should only be able to answer 1 answer. Not
age; 12-15 and second 15-18, what if you’re 15?
Types of data
Qualitative data in which the variables are not in a numerical form, but are in the form of text,
photographs , sound bites and so on.
Quantitative data that appear numerical form.
Don’t take this to black/white all quantitative data are based upon qualitative judgements and all
qualitative data can be summarized into numerical information.
The units of analysis The entity that you are analysing in your analysis; for example individuals,
groups or social interactions. It is the analysis that determine what your unit is, so it doesn’t have to
be the same as your sample. So for different analysis in the same study you can take another unit. Be
aware of hierarchical modelling this is a statistic model that allows for the inclusion of data at
different levels, where the unit of analysis at some levels is nested within the unit of analysis at
Deduction versus inductive reasoning
Deductive top-down reasoning from general to more specific, so theory, hypothesis, observation,
Inductive the other way around. So bottom-up. Observation, pattern, tentative hypothesis,
theory. This is more open-ended and exploratory.
1.4 the structure of research
Most research projects share the same general structure a shape of an hourglass
Begin with broad questions
Narrow down, focus in might involve formulating a
Observation Measurement of the question of
interest. Identify a gap in the research literature
Analyse data match the results
Generalize back to conclusions
Research is a cycle: when there is no theory to test in quantitative research it should be find
somewhere and that’s where qualitative research is being important. So qualitative theory creation
and quantitative testing.
The components of a research study
Research question the central issue being addressed in the study, typically phrased in the
language of theory.
In research a distinction is made between your view of an entity (the construct) and the
entity as it exist (the operationalisation). So operationalisation is the translation of construct
into its manifestation. For example translating the idea of your treatment or program into
the actual program, or translating the idea of what you want to measure into the real
Research program (cause)
1.5 the validity of research
Validity the best available approximation of the truth of a given proposition, inference or
conclusion. Measures, samples and designs don’t have validity, only propositions can be said to be
valid. So you say that the measures leads to valid conclusions. Many of the conclusions are related to
the process of doing research and are not the major question of hypotheses of the study. So do you
measure what you intended to measure.
Cause construct the abstract idea of theory of what the cause is in a cause-effect relationship. You
can operationalize this in a program.
Effect construct the abstract idea of theory of what the outcome is in a cause-effect relationship.
You can operationalize this in observations.