Research methods Flashcards
extraneous variable
Any variable that is not manipulated but still might have an effect on the dependent variable; confounding variable which decreases the validity and realiability of a study.
correlation
Correlation is a statistical technique that can show whether and how strongly pairs of variables are related.
correlation coefficient
A correlation coefficient is a statistical measure of the degree to which changes to the value of one variable predict change to the value of another. Can get the values -1.0 - 1.0.
positive correlation
A positive correlation is a relationship between two variables such that their values increase or decrease together.
negative correlation
A negative correlation is a relationship between two variables such that as the value of one variable increases, the other decreases.
intervening variable
An intervening variable is “the third variable” in correlational studies (the probable reason to cause the change in both measured variables (like the coorrelation between ice cream consumption and drowning fatalities can be explained by summer)
quantitative data
Anything that can be expressed as numbers (data that can be measured in numbers).
qualitative data
Descriptive data (cannot be measured in numbers). Instead os statistical analysis this kind of data is analysed by using content analysis.
overt observation
Researcher reveals that participants know that they are being observed as a part of the study.
covert observation
Researcher does not inform participants that they are observed and what is observed.
naturalistic observation
Observing participants overtly or covertly in their natural environment. Used when lab experiments are unrealistic.
controlled observation
Observational study where the researcher has planned the situation or environment. Control of variables consequently makes establishing a cause and effect easier.
participant observation
Researcher is part of the observed group (like lives in a distant village and makes observations about it)
non-participant observation
The researcher does not take part in the activity observed, the researcher is an outsider
observer bias
observer bias occurs when the observers (or researcher team) know the goals of the study or the hypotheses and allow this knowledge to influence their observations during the study
inter-observer reliability
the extent to which independent observers agree in their observations - is increased for example by defining clearly the behaviour and events recorded (good coding system)
case study
an in-depth and detailed study of an individual or a small group of people, often applied to unusual or valuable examples of behaviour which may provide important insights into psychological function or counterargument of psychological theory (e.g. cases of H.M. and Genie)
key ethical guidelines
informed consent, only justified deception, protection of participants, debriefing, right to withdraw, confidentiality, privacy
informed consent
before the study the researcher must outline to the participants what the research is about and ask their permission to take part (an ethical guideline)
deception
participants are misled or wrongly informed about the aims of the research, necessary to some extent, ethically wrong at some point
debriefing
the act of revealing the details of the experiment for the participant in order to minimize any psychological harm or stress the experiment might have caused
protection of the participants
making sure that the participants in the experiment don’t suffer psychological harm because of the test
confidentiality
Confidentiality is about what is and isn’t allowed to be revealed about the participants of an experiment. There are many laws in place regarding this matter. If the participant doesn’t agree to releasing the information about themselves the researchers are not allowed to.
reliability
Reliability refers to the consistency of results. A highly reliable experiment provides similar results with similar conditions.
test-retest reliability:
If there is no variance in the results collected with the same methods in the same conditions then there is test-retest variability. Test-retest reliability therefore refers to the degree of reliability the test has when repeated under same conditions.
split-half reliability
Split-half reliability means the consistency of a test when the test is split into two parts and the results of the two halves are compared to each other.
Inter-rater reliability
This is the extent to which two raters provide consistent or similar responses. The ratings for each observer are correlated to check for agreement. It is a method of assessing the reliability of a set of measurements or ratings such as in an observation.
Validity
The extent to which results accurately measure what the they claim to measure. There are also several subcategories for validity.
Ecological validity:
How well the study can be related or reflectes to everyday life, real life. So if the study has high ecological validity it can be generalised beyond the setting it was carried out in, but studies with low ecological validity can not be.
Generalisability
whether the findings of the study can be transferred to people or situations other than those in the original study.
Experimenter bias
Errors in the research study due to the predisposed notions and beliefs of the experimenter(s).
Demand characteristics
A research effect where participants form impressions of the research purpose and (un)consciously alter their behavior accordingly.
laboratory experiment
The experment takes place in a highly controlled (often artificial) environment, the reseacher manipulates IV, measures DV and controls all other variables. Cause and effect relationship can be established.
field experiment
The experiment takes place in a natural environment, impossible to obtain total control over all variables so there may be confounding variables and that’s why we cannot be as sure as in lab about the the cause and effect relationship. The researcher manipulates the independent variable (IV)
natural experiment
Iindependent variable (IV) is naturally occuring and not manipulated like in real experiments. The researcher does not use random assignment and manipulate the IV but records possible effects of a variable (like gender, race, previous experiences) on another (DV).
quasi experiment
There is no control over independent variable or possible extraneous variables and/or no possibility of random allocation to conditions: Field experimentts and natural experiments are quasi experiments.
random assignment / allocation
an experimental technique for assigning subjects to different conditions in order to get as similar groups as possible and controlling possible confounding variables that way
independent variable (IV)
An independent variable is the one manipulated by the researcher (“the cause /predictor /exposure variable”)
dependent variable (DV)
DV is the variable which is measured in experimental studies, “the effect”
