Research Exam #2 Flashcards
Types of Qualitative Research Designs
Phenomenology Grounded Theory Ethnography Autoethongraphy Participatory Action Research
Phenomenology
qualitative research about people’s lived experiences
Grounded Theory
(sociology) Collecting/analyzing data with the goal of creating theories that explain observations and experiences
Ethnography
(anthropology) experience of a specific cultural group
- autoethnography: experience of a person
- institutional ethnography: experience of an institution
Participatory action research
(politics) asks individuals what Q’s to ask to learn about xyz, then uses their answers as the questions they ask
qualitative terms relating to VALIDITY/RELIABILITY
- trustworthiness
- authenticity
- transferability
- credibility
- dependability
- confirmability
trustworthiness
(qualitative, validity)
how well the results can be trusted
transferability
(qualitative, validity)
=quantitative external validity
can the data apply to other circumstances?
enhanced by: thick description
credibility
(qualitative, validity)
=quantitative internal validity
how confident are we in the truth of the data?
enhanced by:prolonged engagement, persistent observation, peer-debriefing, member checking, triangulation (multiple methods to document 1 phenomenon)
dependability
(qualitative, validity)
=quantitative reliability
stability of data over time and space
enhanced by: step-wise replication (multi
validity
how well can the data be trusted?
reliability
was it measured correctly?
Types of Quantitative Validity
statistical conclusion validity
internal validity
construct validity
external validity
statistical conclusion validity
is there a relationship between the independent and the dependent variables? (did we use the right stats?)
internal validity
is there evidence of a causal relationship between the independent and dependent variables? (did the intervention actually cause the dep. variables change? were all others rules out?)
construct validity
to what theoretical constructs can the results be generalized?
External validity
can the results be generalized to other persons, settings or times?
Pyramid of Quantitative types of validity
statistical conclusion
internal
construct
external
Threats to Internal Validity
iMulti-group threats:
1.selection history (something different happened to group 1 than group 2 between pre and posttests) ,
2. selection maturation: when geoups experience different maturational changes (5mos-10mos olds vs 10yr-10.5 yr olds)
3. selection attrition,
4. selection testing: when pretests effect groups differently
5. selection instrumentation: test is not consistent across groups (due to variance in reliability)
6.selection regression to the mean: interaction is of concern if the groups are specifically divided based on higher and lower pretest scores
Single group threats:
1. history (something may have happened to have an effect on the dependent variable),
2. maturation: changes occur to dep. variable due to passing time
3. attrition: potential loss of participants during the data collection
4. testing threat: the mere act of collecting data changes the response being measured (potential effect of pretesting or repeated testing on the dep. variable
5. instrumentation: bias due to an unreliable/ inaccurate measuring system
6. regression to the mean: statistical phenomenon where scores on pretests are inherently likely to move towards the group mean in the post-tests
Threats to Statistical Conclusion Validity
wrong stats
ow statistical power (number of ppl to make it valid),
type I/type II errors,
variance
Threats to Construct Validity
Reactivity: participants reacting to being in a study
1. Hawthorne effect: performance is effected (better) because they know they are in a study
2. Novelty effect: react because its new
Realism:________
Threats to External Validity
if anything above is invalid it can not have external validity.
i. social threat: group a talks to group b
ii. compensatory equalization of treatment: treat the control group extra well to compensate for the fact that they are not getting the “better” treatment
population:
the entire set of individuals or units to which your data will be generalized
Target population
the larger population to which results of a study will be generalized (: the people with the condition your are focusing on, but not in your study)
accessible population
¬¬¬¬¬¬The actual population of subjects available to be chosen for a study, usually a non random subset of the target population
representative sample
a small groups whose characteristics are of equal proportions to those of a larger group
sampling bias
bias that occurs when individuals who are selected for a sample overrepresent or underrepresent the underlying population characteristics
sampling error
the difference between an observed statistic from a sample and the population parameters
non-probability sampling
a sample that was not selected using random selection (weaker, but easier)
probability sample
a sample chosen using randomized methods
non-probability sampling
convenience: ppl at DU
snowballing: you’re in, get 3 fiends too!
quota
Probability sampling (quantitative)
a sample chosen using randomized methods
random sampling
probability method of selecting subjects for a sample, where every subject in the population has an equal chance of being chosen
stratified random sampling
the grouping of individuals in a population into homogeneous groups on some characteristic prior to sampling (study on elementary school kids—take 1st , 2nd & 3rd graders and randomly split 1st in to a/b, randomly out 2nd in group a/b, randomly take 3rd split into a/b)
cluster sampling
probability sampling in which large subgroups (clusters) are randomly selected, and then smaller units from those clusters are successively chosen
