Psychology 2030A/B Chapter Notes - Chapter 4: Null Hypothesis, Internal Validity, Statistical Significance

18 views11 pages
Research on Psychological disorders includes:
presenting problem
treatment and outcome
Start with a HYPOTHESIS, about what you expect to find – then
decide how you want to test his hypothesis with RESEARCH DESIGN
RD: includes the aspects you want to measure in the people you are
studying (the dependent variable) and the influences on their
behaviours (the independent variable)
Two forms of validity are specific to research studies: internal and
INTERNAL VALIDITY: is the extent to which we can be confident
that the independent variable is causing the dependent variable to
EXTERNAL VALIDITY: refers to how well the results relate to things
outside your study; in other words, how well your findings describe
similar individuals who were not amount the study subjects
An educated guess or statement to be supported by data
Abnormal behaviour defies the regularity and predictability we desire
Initial phase of a research study – hypothesis formation
Next step put it in unambiguous words and a form that is testable –
the way the question is stated should suggest the researchers
already know the answer to their question – OBVY they don’t but
phrasing it this way makes it testable
Opposite is the NULL HYPOTHESIS
oExample: researchers posed the H that administations of a
mildly intoxicating does of alcohol, relative to adminitation of
a nonalcoholic control beverage, would lead to increases in
several parameters of gambling behaviour
oOpposite: it IS possible that this low does of A might have no
impact on any aspect of gambling behaviour (null hypothesis)
This concept of testability (the ability to support the hypothesis is
important for science because it allows use to search further
Also specify dependent and independent variables
oDependent – is what is expected to change or influenced by the
oIndependent variable – causes or influences behaviour (alcohol)
CHAPTER 4 1/23/11 4:18 PM
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 11 pages and 3 million more documents.

Already have an account? Log in
Confound – relates to INTERNAL validity – any factor occurring in a
study that makes the results uninterprable
oEx. If some people drank coffee before they came into the lab –
affects data – makes the results un-interptrable
oMakes the research internally INVALID
Scientists use many strategies to ensure internal validity to their
oControl group – people are similar to the experimental group
in every way EXCEPT that members of the experimental
group are exposed to the independent variable and those in
the control group are not
oControl groups help rule out alternative explanations for
results, thereby strengthening internal validity
Help rule out alternative explanations for results – aka
strengthening internal validity
Ex. Half the gamblers were assigned alcohol, other half
was not
oRandomization – is the process of assigning people to
different research groups in such a way that each person has
an equal chance of being place in any group
Eliminates any systematic bias
oAnalogue models – create in the controlled conditions of the
lab aspects that are comparable (analogous) to the
phenomena under study
Ex. Bulimia study - could ask volunteers to binge eat in
the lab, quesionoing them before they arte, while they
were eating, and after they finished to learn whether
eating in this way made them feel more or less anxious
– if volunteers are of any age, race, gender,
background, can rule pit influences on the subjects
attitudes – not just have bulimics
Strengthen internal validity
GENERALIZABILITY – the extent to which results apply to everyone
with a particular disorder
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 11 pages and 3 million more documents.

Already have an account? Log in
Statistical significance – probability that obtaining the observed
research findings merely by chance is small – then leads you to
think of the SIZE OF THE EFFECT – ex. People hurting themselves,
is statistically significant but when you look at the people who were
rated as imorved, you find they still hit themselves about six times
per day – even though frequency is lower, they are still hurting
themselves – suggests statistical significance may not be
CLINICALLY significant
Clinical significance - degree to which research findings have
USEFUL and MEANINFUL applications to real problems
Clinically – importance to the people that hurt themselves
Now – concern for the CS of results has led researches to develop
statistical methods that address not just the fact that groups are
different, but how large these differences are, effect size
oInstead of just looking at the results of the group as a whole,
individual differences are considered as well
What is the best way to begin exploring a relatively UNKNOWN
DISORDER? – Case Study Method – intensively investigating one
or more individuals who display the behavioural and physical
DOES NOT USE SCIENTIFIC METHOD (many confounding variables
are present that can interfere with conclusion)
Instead, relies on a clinciian’s observations of differnes between one
person or group with a disorder, people with other disorders, and
people with no psychological disorder
Limitation: sometimes coincidence occurs that are irrelevant to the
condition under study and may lead to mistaken conclusions about
what causes certain conditions or what treatment appears to be
A statistical relationship between two variables is called a correlation
oEx. Is schizophrenia related to the size of ventricles in the
oThe answers depend on determining how one variable is related
to another
oCD are used to study phenomena just as they occur
Correlation does NOT imply causation – two things occurring together
do not imply that one caused the other
oDon’t know whether A caused B or B caused A or if there is
another variable C that is added
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 11 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.