Research Methods – Quantitative research – Summary
Quantitative research designs
- Quantitative research: realist or positivist
o Foundation for positivists/realist epistemology: social
observations are real, they exist outside a person’s mind.
- Qualitative research: constructivist
o Foundation for interpretivists epistemology: social reality is
not the same as physical reality, people create their own
reality through social interactions.
Theories and empirics
- Theories: ideas about how things work, > if you haven’t tested it, it
is a theory
- Empirics: what we can factually observe in research, > these are the
observations of theories.
Induction
Induction (often interpretivist): you first observe reality, after which
you try to order the results and based on this you describe a pattern
(formulate a theory)
Observation > theory
*Mostly used in interpretivism
Deduction
Deduction (often positivism and realism): you first think about
patterns (theorize), then you check with the empirical world if these
make sense.
Theory > observe
*Mostly used in positivism and realism
Overview – quantitative and qualitative research
Qualitative research Quantitative
research
Theory/empirical Induction Deduction
reality
Epistemology Interpretivism Positivism/Realism
Ontology Constructivism Objectivism
Analysis in Words Numbers and words
Inspiration Humanities Natural sciences
Quality criteria for quantitative research
Reliability
o If you would replicate research, would this lead to a similar
outcome?
o If research is not reliable, the findings could be random
Internal validity:
o Is the causal inference claimed in the research, valid?
Does x lead to y?
, o If research is not internally valid, one cannot make a causal
claim
External validity:
o Do the results hold in a different context?
o If results are not externally valid, the results do not say much
about the ‘real world’
Three different research designs for quantitative research:
1. Cross-sectional
Analysis in one moment in time. In a typical cross-sectional design a large
group of people is surveyed with closed (mc) questions or social reality is
coded.
Advantages:
+ High reliability
Because it is often cheap, many people can participate, which
increases the chance that findings are random.
+ High external validity
It is relatively easy to find a representative sample
Usually the participants share many characteristics with the
population which helps to generalize the research findings.
Disadvantages
- Low internal validity
It is harder to make causal claims because the results can be
spurious or there is endogeneity (i.e. reverse causality).
To increase internal validity:
- For spurious relation: include control variables
- For endogeneity: strong theory or addition of other research
designs (i.e. longitudinal or experiment)
2. Longitudinal
Analysis done over time. The same people are surveyed on different
moments in time.
Advantages
+ Better internal validity than cross-sectional design: because you have a
sequence in time and you can control for associations in groups. Better
chance to establish a cause-effect relationship.
Sequence in time (endogeneity)
Correlation with groups (spurious relation)
+ Sometimes more data than cross sectional research: especially when
researching countries, which is a limited source of data (195 countries in
the world in total)
Disadvantages
- Reliability tends to be lower than in cross-sectional design
Often harder to find participants, at the same time statistical models
are more complex. Thus, increase in chances that replication on a
different sample would produce (somewhat) different results.
- Lower external validity
Participants who drop out (attrition), makes it harder to generalize
to the entire population.
Quantitative research designs
- Quantitative research: realist or positivist
o Foundation for positivists/realist epistemology: social
observations are real, they exist outside a person’s mind.
- Qualitative research: constructivist
o Foundation for interpretivists epistemology: social reality is
not the same as physical reality, people create their own
reality through social interactions.
Theories and empirics
- Theories: ideas about how things work, > if you haven’t tested it, it
is a theory
- Empirics: what we can factually observe in research, > these are the
observations of theories.
Induction
Induction (often interpretivist): you first observe reality, after which
you try to order the results and based on this you describe a pattern
(formulate a theory)
Observation > theory
*Mostly used in interpretivism
Deduction
Deduction (often positivism and realism): you first think about
patterns (theorize), then you check with the empirical world if these
make sense.
Theory > observe
*Mostly used in positivism and realism
Overview – quantitative and qualitative research
Qualitative research Quantitative
research
Theory/empirical Induction Deduction
reality
Epistemology Interpretivism Positivism/Realism
Ontology Constructivism Objectivism
Analysis in Words Numbers and words
Inspiration Humanities Natural sciences
Quality criteria for quantitative research
Reliability
o If you would replicate research, would this lead to a similar
outcome?
o If research is not reliable, the findings could be random
Internal validity:
o Is the causal inference claimed in the research, valid?
Does x lead to y?
, o If research is not internally valid, one cannot make a causal
claim
External validity:
o Do the results hold in a different context?
o If results are not externally valid, the results do not say much
about the ‘real world’
Three different research designs for quantitative research:
1. Cross-sectional
Analysis in one moment in time. In a typical cross-sectional design a large
group of people is surveyed with closed (mc) questions or social reality is
coded.
Advantages:
+ High reliability
Because it is often cheap, many people can participate, which
increases the chance that findings are random.
+ High external validity
It is relatively easy to find a representative sample
Usually the participants share many characteristics with the
population which helps to generalize the research findings.
Disadvantages
- Low internal validity
It is harder to make causal claims because the results can be
spurious or there is endogeneity (i.e. reverse causality).
To increase internal validity:
- For spurious relation: include control variables
- For endogeneity: strong theory or addition of other research
designs (i.e. longitudinal or experiment)
2. Longitudinal
Analysis done over time. The same people are surveyed on different
moments in time.
Advantages
+ Better internal validity than cross-sectional design: because you have a
sequence in time and you can control for associations in groups. Better
chance to establish a cause-effect relationship.
Sequence in time (endogeneity)
Correlation with groups (spurious relation)
+ Sometimes more data than cross sectional research: especially when
researching countries, which is a limited source of data (195 countries in
the world in total)
Disadvantages
- Reliability tends to be lower than in cross-sectional design
Often harder to find participants, at the same time statistical models
are more complex. Thus, increase in chances that replication on a
different sample would produce (somewhat) different results.
- Lower external validity
Participants who drop out (attrition), makes it harder to generalize
to the entire population.
