lecture notes

23 views5 pages
13 Dec 2010
PSY lecture Jan 11
Research methods
How to critically evaluate credibility. How to do simple designs,
Some examples of good psychological research:
A theoretical framework: general hypothesis from the theory.
Explains things simply. Simplest theory is always the best theory.
A theory is good if it generates a lot of hypotheses. By generating
hypotheses from a theory, we can prove theories and test them.
Hypotheses need to be tested. Theory isnt falsifiable. This means
it cant be tested. You have to have evidence. If theres no evidence,
its not science.
A standardized procedure: every subject has to be treated the
same. it shouldnt be based on anything else but the. It should not
be varied from subject to subject. no matter how well the study is
done, there is always a chance that there is a statistic probability.
Have to get the same results from the experiments that have been
done by other researchers. Dont accept other studies. Replication
of studies. If the replication of a study didnt give the same results,
then we need to find what caused to have different results.
Everyone has to be treated the same. the only differences should
be different is the manipulation.
Generalizability: Samples are not representative of the population.
How do we generalize the findings? Use a less biased sample.
Biased sample can be saved when we use random samples.
External validity: is it real? Ex. When drinks and pop corns were
flashed in a movie theater, the desire for drinks and popcorns of
people went up significantly. We have to do the studies over and
over again.
Objective measurement: Try to cross reference. Make sure it
correlates well with other information. You cant fake physiological
measures. Make sure they’re valid. Ex. IQ test is a valid measure
Unlock document

This preview shows pages 1-2 of the document.
Unlock all 5 pages and 3 million more documents.

Already have an account? Log in
of how well you do in school. Its not a valid measure of how smart
you are.
Psychological research:
Naturalistic observation: we observe people, things, animals,
etc. We observe things in their natural environments. We do
not want to affect what we are watching, without altering
their behavior. Try to observe in a way that it doesnt affect
what happens. You can make assumptions but you dont
know why its happening.
Surveys: valuable pieces of information gathering. Has to be
cautious. Questions that people answer. The way you ask a
question has a profound influence on how they answer.
Answers hat are provided are often hard to get what the
person is truly thinking. It might not represent the truth
depending on who watches which tv show, etc. Questions can
be manipulative, even though it can be a fantastic tool.
Dangerous but a very useful research.
Case study: a study of a phenomenon, a single group, a
person, etc. People will get involved. Its like an anecdote. Its
an anecdotal evidence. It can be wrong. It might not apply to
everyone. We assume its valid because were aware of it. It
can be completely wrong but because we see things on tv,
and from around us, we tend to believe them. It can be
extremely misled.
Correlational: It can be either positive or negative. Positive:
one variable goes up the other goes up too. Ex. If we graph
height vs. weight, there is a strong positive correlation. If the
correlation is perfect, there is no exceptions. Its either
negative or positive. Strength: strong, moderate, weak.
Moderately strong: .3 to .5: moderately strong. Problems
with correlation: cannot tell about causation. Its not based
Unlock document

This preview shows pages 1-2 of the document.
Unlock all 5 pages and 3 million more documents.

Already have an account? Log in

Get OneClass Notes+

Unlimited access to class notes and textbook notes.

YearlyBest Value
75% OFF
$8 USD/m
$30 USD/m
You will be charged $96 USD upfront and auto renewed at the end of each cycle. You may cancel anytime under Payment Settings. For more information, see our Terms and Privacy.
Payments are encrypted using 256-bit SSL. Powered by Stripe.