Chapter 14 Flashcards
A study must be ____ to be ____, but may not need to be ____ or have ____ to have importance.
replicated to be credible
may not need generalizable or have applicability to have important
direct replication
replicates original study exactly
conceptual replication
uses same conceptual variables as original but operationalizes them differently
replication plus extension study
repeats original and introduces new participant variables, situations, or IV levels
meta analysis
collects and averages effect sizes from all studies that have tested the same variables
What do psychological scientists now do to strengthen the verifiability and replicability of studies?
Promote open data, open materials, and preregistration
what are some questionable practices that may produce findings that cant be replicated
underreporting null results, p hacking, hypothesizing after results are known (HARKing)
Importance of external validity depends on ..
whether researchers are operating in generalization mode or theory testing mode
theory testing mode
Researchers design studies that test a theory, leaving generalization for future studies
In this case external validity less important than internal validity
Lab studies conducted in this mode may have strong experimental realism
generalization mode
researchers focus on whether their samples are representative, whether the data from sample apply to population of interest, and if data may apply to new population of interest
what mode are researchers in who make frequency claims
generalization mode
true or false; Research does not need to be conducted in a field setting to have ecological validity
true
p hacking
A family of questionable data analysis techniques, such as adding
participants after the results are initially analyzed, looking for
outliers, or trying new analyses in order to obtain a p value of just
under .05, which can lead to nonreplicable results.
what does HARKing stand for?
(hypothesizing after results are known)
what is HARKing
A questionable research practice in which researchers create an afterthe-
fact hypothesis about an unexpected research result, making it
appear as if they predicted it all along.