Textbook Notes (280,000)
CA (170,000)
U of G (10,000)
PSYC (3,000)
PSYC 2360 (100)
Chapter

PSYC 2360 Chapter Notes -Statistical Conclusion Validity, Null Hypothesis, Internal Validity


Department
Psychology
Course Code
PSYC 2360
Professor
Naseem Al- Aidroos

This preview shows page 1. to view the full 5 pages of the document.
Research Methods - External Validity
Validity Threats
Construct validity - measuring thing you think you are measuring
Statistical conclusion validity - whether or not you are rejecting null
hypothesis and how often you are incorrect in doing so
Internal validity - to what extent you can conclude independent variable is
causing dependent variable
External validity - extent to which results can be generalized beyond the
specific way of the original experiment
When can we generalize to other people?
True generalization is not possible because it is impossible to draw a truly
representative sample of all human beings
o Frequently assume that unless there is a reason to believe otherwise,
relationships between conceptual variables found in one group tends
to also appear in other groups too
o Burden of proof rests on those who claim that a result will not
generalize to demonstrate that this is indeed the case
Tough question
o Theoretical question
Phenomenon (but be careful here)
Can reason about it, things that tend to have better
external validity…
o Large sample sizes that characterize the
population at large
o Evolutionary psychology - we have faster
perception of colour red
Things that vary between cultures are hard to
generalize and say it has high external validity
Characteristics of population under study
What is different about this population compared to
other populations
Problem with using college students - might be
cognitively different, have a higher need for approval
You're Reading a Preview

Unlock to view full version

Only page 1 are available for preview. Some parts have been intentionally blurred.

o Empirical question
Go and find out - much easier to do
To make strong claim that you expect to find something in one
population and not in another you are going to have to go out
and do it
Have to make sure it is worth it, does it matter to you?
When can we generalize to other settings?
Extent to which research will generalize beyond specific settings and
techniques used in original study
o Uniqueness of one experiment makes it possible that findings are
limited in some way to the specific settings, experimenters,
manipulations or measured variables used in the research
Tough question
o Repetition with variation in study
Does it generalize across psychological conditions
o Focus on ecological validity (make sure that various settings you have
tend to occur in everyday social / psychological world)
o Field experiments - experimental designs conducted in natural
settings
Possibility of more ecological and consequently, more external
validity
Influence of extraneous variables can noise the data
Greater potential for random error and systematic error that
would not happen in a lab
Practicality?
Sometimes hard for research to go into the field and
think of strong manipulation that you can actually get
away with
Cannot always get permission to conduct them and
even if access is gained it may not be feasible to use
random assignment
Natural?
How can you do something that will still appear natural
after the experimental manipulation?
Importance of Replication
Necessary in order to conclude external validity
You're Reading a Preview

Unlock to view full version