Experimenteel onderzoek samenvatting
Chapter 10 introduction to simple experiments
Experiment = the researchers manipulated at least one variable and measured another.
Manipulated variable / causal variable / independent variable = controlled/ participants can’t choose
Conditions = the levels in the manipulated variable
Measured variables / outcome variable / dependent variable = form of record of behaviour or
attitudes
The independent variable is almost always on the x-axis, and the dependent variable is almost always
on the y-axis
Control variable = any variable that an experimenter holds constant on purpose. They are important
for establishing internal validity, because they eliminate alternative explanations for results.
Causal claims:
1. Covariance
2. Temporal precedence
3. Internal validity
Experiments establish covariance between the causal variable and the outcome variable.
Comparison group / comparison condition = you can compare two groups, instead of your own
experience “compared to what?”
Treatment group = the other level or levels of the independent variable
Control group = a level of an independent variable that is intended to represent “no treatment” or a
neutral condition.
Placebo group = when the control group is exposed to an inert treatment such as a sugar pill
Experiments establish temporal precedence by manipulating the causal (independent) variable to
ensure that it came first in time.
Well-designed experiments establish internal validity
To be internally valid, a study must ensure that the causal variable (the active ingredient) (and not
other factors) is responsible for the change in the outcome variable.
Confounds = possible alternative explanations or potential threats to internal validity
- Design confound = an experimenter’s mistake in designing the independent variable. It is a
second variable that happens to vary systematically along with the intended independent
variable and therefore is an alternative explanation for the results.
o Systematic variability = when there is only a design confound in one part of the
group
o Unsystematic variability = when both groups experience the same design confound
- Selection effects = when the kinds of participants in one level of the independent variable
are systematically different from those in the other.
o Random assignment = randomly decided who belongs to which group
Contaminatie = deelnemers in de experimentele groep vertellen de deelnemers in de
controle groep over de deelname / deelnemers houden zich niet aan de
handelingen / beïnvloeding door de onderzoeker
o Matched groups = the experimental groups are as equal as possible before they
administer the independent variable. (GPA lowest to highest, randomly assign the
two highest GPA scores and so on)
, Interrogating causal claims with the four validities:
Construct validity how well were the dependent variables measured and the independent
variables manipulated?
- Manipulation check = an extra dependent variable that researchers can insert into an
experiment to convince them that their experimental manipulation worked.
- Pilot study = a simple study that is completed before conducting the study of primary
interest.
External validity whether the causal relationship can generalize to other people, places, and times
Statistical validity is the difference statistically significant? How large is the effect?
- r can help researchers evaluate the effect size of an association
- d (the standardized effect size) represents how far apart two experimental groups are on the
dependent variable. It indicates not only the distance between the means, but also how
much the scores within the groups overlap.
When d is larger, it usually means the independent variable caused the dependent variable
to change for more of the participants in the study
When d is smaller, it usually means the scores of participants in the two experimental groups
overlap more
Internal validity are there alternative explanations for the results?
- Design confounds
- Selection effect
Onderzoeksvraag:
- bevat constructen
Hypothese:
- Bevat geoperationaliseerde termen
- Gaat over een populatie
- Bevat symbolen (Griekse letters) Griekse letter delta Δ voor populatie
Griekse letter mu μ voor populatie gemiddelde
Griekse letter ρ voor correlatie in populatie
Steekproef:
- Bevat letters (Romeinse letters)Romeinse letter d voor steekproef
Onderzoeksvraag experimenteel onderzoek:
P - population
I - intervention
C - comparison
O - outcome
Operationele hypothese = in woorden
Statistische hypothese = H0: μ revisie = μ geen revisie
HA: μ revisie ≠ μ geen revisie
Betrouwbaarheidsinterval (BI) / confidence interval (CI)
Breedte hangt af van:
- Steekproefgrootte meer info, dus meer zekerheid, kleinere standaardfout, smaller interval
- Spreiding scores meer spreiding, meer standaardfouten, breder interval
- Betrouwbaarheidsniveau hoger niveau, meer zekerheid, maar breder interval
Chapter 10 introduction to simple experiments
Experiment = the researchers manipulated at least one variable and measured another.
Manipulated variable / causal variable / independent variable = controlled/ participants can’t choose
Conditions = the levels in the manipulated variable
Measured variables / outcome variable / dependent variable = form of record of behaviour or
attitudes
The independent variable is almost always on the x-axis, and the dependent variable is almost always
on the y-axis
Control variable = any variable that an experimenter holds constant on purpose. They are important
for establishing internal validity, because they eliminate alternative explanations for results.
Causal claims:
1. Covariance
2. Temporal precedence
3. Internal validity
Experiments establish covariance between the causal variable and the outcome variable.
Comparison group / comparison condition = you can compare two groups, instead of your own
experience “compared to what?”
Treatment group = the other level or levels of the independent variable
Control group = a level of an independent variable that is intended to represent “no treatment” or a
neutral condition.
Placebo group = when the control group is exposed to an inert treatment such as a sugar pill
Experiments establish temporal precedence by manipulating the causal (independent) variable to
ensure that it came first in time.
Well-designed experiments establish internal validity
To be internally valid, a study must ensure that the causal variable (the active ingredient) (and not
other factors) is responsible for the change in the outcome variable.
Confounds = possible alternative explanations or potential threats to internal validity
- Design confound = an experimenter’s mistake in designing the independent variable. It is a
second variable that happens to vary systematically along with the intended independent
variable and therefore is an alternative explanation for the results.
o Systematic variability = when there is only a design confound in one part of the
group
o Unsystematic variability = when both groups experience the same design confound
- Selection effects = when the kinds of participants in one level of the independent variable
are systematically different from those in the other.
o Random assignment = randomly decided who belongs to which group
Contaminatie = deelnemers in de experimentele groep vertellen de deelnemers in de
controle groep over de deelname / deelnemers houden zich niet aan de
handelingen / beïnvloeding door de onderzoeker
o Matched groups = the experimental groups are as equal as possible before they
administer the independent variable. (GPA lowest to highest, randomly assign the
two highest GPA scores and so on)
, Interrogating causal claims with the four validities:
Construct validity how well were the dependent variables measured and the independent
variables manipulated?
- Manipulation check = an extra dependent variable that researchers can insert into an
experiment to convince them that their experimental manipulation worked.
- Pilot study = a simple study that is completed before conducting the study of primary
interest.
External validity whether the causal relationship can generalize to other people, places, and times
Statistical validity is the difference statistically significant? How large is the effect?
- r can help researchers evaluate the effect size of an association
- d (the standardized effect size) represents how far apart two experimental groups are on the
dependent variable. It indicates not only the distance between the means, but also how
much the scores within the groups overlap.
When d is larger, it usually means the independent variable caused the dependent variable
to change for more of the participants in the study
When d is smaller, it usually means the scores of participants in the two experimental groups
overlap more
Internal validity are there alternative explanations for the results?
- Design confounds
- Selection effect
Onderzoeksvraag:
- bevat constructen
Hypothese:
- Bevat geoperationaliseerde termen
- Gaat over een populatie
- Bevat symbolen (Griekse letters) Griekse letter delta Δ voor populatie
Griekse letter mu μ voor populatie gemiddelde
Griekse letter ρ voor correlatie in populatie
Steekproef:
- Bevat letters (Romeinse letters)Romeinse letter d voor steekproef
Onderzoeksvraag experimenteel onderzoek:
P - population
I - intervention
C - comparison
O - outcome
Operationele hypothese = in woorden
Statistische hypothese = H0: μ revisie = μ geen revisie
HA: μ revisie ≠ μ geen revisie
Betrouwbaarheidsinterval (BI) / confidence interval (CI)
Breedte hangt af van:
- Steekproefgrootte meer info, dus meer zekerheid, kleinere standaardfout, smaller interval
- Spreiding scores meer spreiding, meer standaardfouten, breder interval
- Betrouwbaarheidsniveau hoger niveau, meer zekerheid, maar breder interval
