RM lecture 1 Flashcards
Methodological triangulation
convergence of the findings of methodologically different studeis can lend credence to the theory pattern
The principle of
______
is the process of testing a theory on the basis of multiple observations, and then drawing a general conclusion for all future observations
Induction
on the other hand, _______ proposes that we should start out with theories that are able to be disproven.
Falsifiability
The belief that beliefs come in degrees, and we can express the likelihood of future events on the basis of past knowledge is known as
_____
.
Bayesianism
When we say that variables must be operational, what do we mean?
That they are defined explicitly so that they can be measured and expressed quantitatively or qualitatively
A set of proposals that define, explain, organise and interrelate can be referred to as…
theory
This word describes theoretical concepts which are constructed to express ideas or provide definitions for a phenomena…
construct
A clear but tentative explanation for an observed phenomenon.
Hypothesis
what is a confounding variable
A confounding variable is a specific type of extraneous variable that is related to both of the main variables that we are interested in.
Content Validity
Does our test measure all aspects of the construct?
Face Validity
Does it look like a good measure?
Convergent Validity
Does the test correlate with measures of the same and related constructs?
Criterion Validity
Is it in agreement with other measures of the same thing?
Concurrent Validity
There is a high correlation between two measures of the same thing
Predictive Validity
The scale has the ability to predict some other variable measuring a different construct
Convergent Validity
Does the test correlate with measures of the same and related constructs?
Divergent Validity
Is there a lack of correlation with measures of different and unrelated constructs?
Over time the researcher becomes concerned that the judges are getting better at differentiating aggressive and non-aggressive behaviours. What threat to internal validity does this pose?
Instrumentation
The researcher becomes concerned that the influence of the judges presence on the children’s behaviours changes over time (e.g. the children were more aware of the judges at the start of the 10 weeks than toward the end of the 10 weeks). What threat to internal validity does this pose?
Reactivity
. Using previously reported methods, you collect a new dataset, but recruit a younger sample, and check that you reach the same conclusions as those reported previously.
what type of replication is this
conceptual replication
Brad has designed a test to measure intelligence, however, he is concerned that scores on the test simply reflect the participant’s motivation. In other words, Brad is concerned about the instrument’s:
Answers:
a. accuracy
b. precision
c. validity
d. reliability
accuracy
validity
He compares the results obtained using his questionnaire with results obtained using an established questionnaire of anxiety.
wahat type of validity
criterion
He checks that his questionnaire asks about anxiety related to feeding issues AND sleeping issues.
what type of validity
Content
Generally speaking, which broad research approach is likely to result in good external validity at the expense of internal validity?
qualitative
You want to obtain a sample with an equal proportion of home and international students even though there are fewer international than home students in the population
stratified
You have access to all members of the population of interest and you want to ensure that the results have population validity
random
You need 200 participants and had hoped to recruit patients from a number of GP surgery’s, but have only received ethical approval to recruit from a single GP surgery with a patient list of 200
cluster
instrumentation
changes in sensitivity or reliability of measurement insttruments during study
parallel forms reliability
if we administer different forma of the same measure to pp, would we obtain the same results
diff versions helpful to eliminate memory effects as the qs are different
replication research
research that checks whether using the same experimental methods produces the same results
Reproduction research
research that checks whether using the same analyses and the same data produces the same results
interval vs ratio data
both have equal increments but ratio data has a real zero point
