RESEARCH Flashcards
what does Regression mean?
All Variables examined are continuous( makes assumption of which variable is influencing other)
(think one variable causes the other to regress)
what does Linear Regression mean?
Degree of dependence between one variable on another
when all variables are categorical, looks at if 2 distributions differ from each other
Chi-square
compares mean values of continuous variable between 2 groups
T-test
compares mean values of continuous variable between 3+ groups
ANOVA
think: A nova comet hits 3 mean(angry) groups
this study type looks at a group of different people at one moment in time
cross-sectional study
this study follows a subset of the population over a lifetime
cohort study
lifetime COuples HORT “hurt”
group of people that share a commone characteristic (example: people born and exposed to same polutant)
cohort
think COuples have somethinig in common
cohort that looks back at events that have already taken place
retrospective cohort design
cohort that follows a group of individuals over a period of time
Prospective cohort design
type of study in which, data is gathered for the same subjects repeatedly over a period of time
longitudinal study
type of observational study in which 2 groups differ in outcome and are compared to find causal factor
(Ex. comparing
people with the disease
with those who don’t but are otherwise similar)
Case-Control study
Highly controlled interventional study
Clinical trial
people studied randomly given one of treatments under study, used to test efficacy/side effects of medical interventions like drugs. Gold
standard for a clinical trial
Randomized controlled trial
Type of study that involves the manipulation of variables (independent and dependent)
Experimental study
is similar to an experimental
design but lacks random assignment.
Quasi-Experimental design
in this type of study there is no interference or manipulation of variables
Observational
what dos a correlation coefficient that is below -1 mean?
Likely the result of an error
what does “regression to the mean” mean?
phenomenon in which scores become more average overtime
(type of validity) Whether results of the study can be generalized to other situations
external validity
(type of validity)extent to which a causal conclusion based on a study is warranted
internal validity
type of external validity which describes how well the sample used can be extrapolated to a population as a whole. “Generalizability”
Population validity
type of external validity which looks at the testing environment and determines how much it influences behavior
Ecological validity
measures how
well a test matches up with a
benchmark test, which is usually another valid measure of the same
construct
Concurrent Validity
tests that constructs that are expected to be related
are, in fact, related
Convergent Validity
is a third variable in an experiment that could provide an alternative explanation to the relationship between the variables of interest
confounding variable
variable that is measured but independently manipulated
Dependent variable
variable that is directly manipulated by researcher
Independent variable
identify the Independent and dependent variable: “children with parents who smoke are more likely to smoke”
Independent: Children w/ smoking parents and Children w/ non-smoking parents
Dependent: Children smoking
is the degree to which
an assessment tool produces stable and consistent
results. CONSISTENT RESULTS WITH REPEATED EXPERIMENT
reliabilty
time related confounding variables
Temporal Confounds
consistency when two
different people measure the same thing,
Inter-rater reliability
what are the non-experimental study designs?
Phenomenological Observational Longitudinal Ethnographic Case study Archival(biographical) Twin
“POLECAT”
what are the 4 things that make a study an experimental design?
1) experimental and control group
2) Random sampling
3) Random group assignment
4) Control extraneous variables
Non experimental design: observational cultural study
Ethnographic
Non experimental design: uses historical records to understand events
Archival(biographical)
Non experimental design: Understand conscious experience from first person perspective
Phenominological
Non experimental design: long term study, that takes measurements at different time intervals
Longitudinal
what does a positive (R value) correlation mean?
one variable(increases while other increases)
what does a negative (R value) correlation mean?
one variable increases while other decreases
This value tells us the odds of correlation happening by chance
P-test
what p value tells us that our data is valid and the odds of a correlation happening by chance are really low.
less than .05
