Research Methods in Psychology Investigating Human Behavior 2nd Edition Test Bank
Follow Below Link to
Download File
Email us for original and Plagiarism Free
Work At ( info.homeworklance@gmail.com ) or order us at
View Sample Chapter Below:
1. A construct is best described as a
1. Directly observable entity
2. Concrete entity
*c. Theoretical entity
1.
Hypothesized entity
2. Meredith can measure happiness by counting
participants’ smiles, by having peers fill out reports about participants, or
by asking participants to complete self-reports. These options are _______ of
the _______of happiness.
1. conceptual definitions; construct
*b. operational
definitions; construct
1. conceptual definitions; variable
2. operational definitions; variable
3. Kimi operationalizes aggression as
participants’ scores on a self-report scale. Candice operationalizes aggression
as increases in blood pressure. Candice’s operationalization has
1. Fewer variables
2. More variables
3. Less ecological validity
*d. Greater ecological
validity
4.
Josh is studying how
options affect satisfaction. He presents participants with either ten different
cookies or two different cookies. Participants choose a cookie and then rate
how satisfied they are with their selection on a scale from one to ten. In this
example, the independent variable is
*a. The number of
cookies
1. Options
2. Satisfaction scores
3. The taste of the cookie
5. Josh is studying how options affect
satisfaction. He presents participants with either ten different cookies or two
different cookies. Participants choose a cookie and then rate how satisfied
they are with their selection on a scale from one to ten. In this example, the
dependent variable is
1. The number of cookies
2. Options
*c. Satisfaction
scores
1. The taste of the cookies
6. Ava discovers that the effect of personality
type on stress depends on whether individuals meditate. In other words, having
a Type A personality predicts high stress for those individuals who do not
meditate. At the same time, Type A personality is not related to stress for
those individuals who engage in regular meditation. In this example, meditation
is
1. An independent variable
2. An dependent variable
*c. An intervening
variable
1. A confound
7. When using different measures to measure the
same construct, researchers want these different measures to produce
*a. Convergent results
1. Divergent results
2. Inverse results
3. Intervening results
8. This is the quantification of an object or
event according to a specific rule.
*a. Measurement
1. Analysis
2. Theory development
3. Objectivity
9. As part of her survey, Lauren asks
participants to indicate their gender (male or female). She collects this data
on which type of measurement scale?
*a. Nominal
1. Ordinal
2. Interval
3. Ratio
10. Time on a stop watch is an example of which
type of measurement scale?
1. Nominal
2. Ordinal
3. Interval
*d. Ratio
11. Jackson has people rate their parents’
physical attractiveness on a scale of 1 to 7. This measurement scale is best
described as
1. Nominal
*b. Ordinal
1. Interval
2. Ratio
12. Bethany measures participants’ body
temperature (using Fahrenheit) before and after exercise. She is using which
scale of measurement?
1. Nominal
2. Ordinal
*c. Interval
1. Ratio
13. The attributes of nominal variables must be
1. Numerical
2. Dichotomous
3. Additive
*d. Exhaustive
14. Age is an example of the ____ level of
measurement.
1. Nominal
2. Ordinal
3. Interval
*d. Ratio
15. This is a school of psychology that uses tests
as objective measures of the mind and mental processes.
1. Nonparametrics
2. Parametrics
*c. Psychometrics
1. Psychophysics
16. In a set of normally-distributed scores,
approximately 95% of the population falls within
1. One standard deviation above and below the
mean
*b. Two standard
deviations above and below the mean
1. Three standard deviations above and below the
mean
2. Four standard deviations above and below the
mean
17. Compared to unreliable measures, reliable
measures are affected
1. more by chance
2. more by measurement error
3. less by changes in the construct
*d. less by
measurement error
18. To establish this type of reliability, researchers measure
a construct using a specific method and then, after a certain period of time
has passed, measure this construct again using the same method.
1. Interobserver reliability
2. Interitem reliability
*c. Test-retest
reliability
1. Split-half reliability
19. Having two researchers observe a behavior,
code it separately, and then compare how they rated the behavior is an example
of
1. Test-retest reliability
2. Interitem reliability
*c. Interobserver
reliability
1. Split-half reliability
20. All of the following tell us about a measure’s
internal consistency, EXCEPT
1. Split-half reliability
2. Interitem reliability
3. Cronbach’s alpha
*d. Test-retest
reliability
21. Alan reads through the statements of his new
measure on sociality and believes that it appears valid. This suggests the
measure has
*a. Face validity
1. Content validity
2. Criterion validity
3. Construct validity
22. Nora asks participants fill out a self-report
survey on their current feelings of stress. At the same time, in order to
validate her survey, she also samples participants’ saliva and measures levels
of stress hormones. Nora compares her scale to the stress to establish
1. Face validity
*b. Criterion validity
1. Predictive validity
2. Divergent validity
23. Gabriella develops a set of questions designed
to measure work place motivation. She distributes the survey. Six months from
now, to validate her measure, she will see how well scores from her scale
predict the number of voluntary overtime hours people work. This will help
establish
1. Face validity
2. Concurrent validity
*c. Predictive
validity
1. Construct validity
24. To establish discriminant validity,
researchers must show
1. That similar traits measured in the same way
are highly correlated
2. That different traits measured in the same way
are highly correlated
3. That similar traits measured in the same way
are unrelated
*d. That different
traits measured in the same way are unrelated
25. More than other types of validity, social
desirability is often a concern if a study has obvious ___ validity.
*a. Face
1. Predictive
2. Concurrent
3. Convergent
26. Constructs are useful in scientific research
because they can be directly observed.
1. True
*b. False
27. A scientific theory is valid to the extent
that it predicts, explains, and describes the relations between relevant
independent and dependent variables.
*a. True
1. False
28. Dichotomous variables are variables that have
two or more values, such as ethnicity.
1. True
*b. False
29. Ordinal, interval, and ratio scales are
quantitative, whereas the nominal level of measurement is qualitative.
*a. True
1. False
30. Nonparametric statistics are primarily used
with variables measured on an interval or ratio scale.
1. True
*b. False
31. The shape of a normal curve is bilaterally
symmetric with one peak in the middle.
*a. True
1. False
32. In measurement, validity is a prerequisite for
reliability.
1. True
*b. False
33. Factor analysis is a “top-down” deductive
procedure that enables research to identify distinct dimensions of a construct.
1. True
*b. False
34. Convergent validity and discriminant validity
are two types of criterion validity.
1. True
*b. False
35. In order to establish construct validity,
researchers must demonstrate both convergent and discriminant validity.
*a. True
1. False
36. Consider the construct “hungry.” Identify
three operational definitions for hungry. Why is it appropriate to use multiple
methods of measurement?
Correct Answer:
Hungry could be
operationally defined as the number of cookies participants eat; the
self-report of hunger on a scale of 1-10; the time since a participant last ate
(answers will vary). It is important to use multiple measures because it is the
only way to understand the true nature of a construct (p. 95). As a theoretical
concept, hunger cannot be directly measured (p. 84) and therefore using only
one operational definition limits understanding.
37. Compare and contrast the four levels of
measurement and provide an example of each.
Correct Answer:
The nominal level of
measurement is the only qualitative level. Nominal variables have attributes
that have no mathematical interpretation (p. 87). Gender or ethnicity, for
example, are examples of nominal variables. Ordinal scales assign numbers to
responses; higher or lower numbers mean more or less of the variable they
represent (p. 88). Measuring optimism on a scale of 1-5 is an example of an
ordinal scale. Interval scales also use numbers to represent responses and
these numbers also represent “greater than” or “less than.” However, instead of
simply showing the relative rank of responses, interval scales include an
additional feature. The distance between any two points is a known size (p.
90); Fahrenheit temperature is an example of an interval scale. Finally, the
ratio scale includes all of the features of an interval scale, but also has a
real zero. Age, height, and weight are all examples of the ratio level of
measurement (p. 91). (Student examples will vary).
38. What is random error of measurement, why is it
a problem, and how can researchers combat it?
Correct Answer:
Random error of
measurement refers to the variation in any response that is not reflecting the
construct of interest. This variation can be the result of any other influence
or factor. Random error of measurement is a problem in any given response (p.
97). If the goal of a measure is to accurately reflect a construct of interest,
then the goal is to minimize error. High random error means low internal
consistency. In developing a measure, researchers can add questions to increase
the internal consistency of their measure and combat the problem of random
error. Adding more questions effectively allows the random error associated
with a particular question to be cancelled out by the random error associated
with responses to the other questions (p. 97).
39. What is split-half reliability and what is
gained by establishing this type of reliability?
Correct Answer:
Split-half reliability
is a used to establish the internal consistency of a measure. The process involves dividing
all of the items of a measure into two groups (e.g., first half and second
half). For each participant, the research computes the score separately for
each half of the items. Scores can then be correlated across all participants;
scores that are highly correlated would suggest an internally consistent or
internally reliable measure (p. 96).
40. Compare and contrast concurrent and convergent
validity and give an example of each.
Correct Answer:
Both concurrent validity
and convergent validity are tools researchers can use to show that a measure is
really measuring what it is intended to measure. Concurrent validity is a type
of criterion validity. It is established when researchers show that a measure
produces scores that correspond highly with scores on a criterion that is
measured at the same time (p. 101). For example, researchers might validate a
self-report scale of impulsivity by administering it to a group of adolescents
and then comparing the scores to records on classroom misconduct. Unlike
concurrent validity, convergent validity helps establishes construct validity.
Convergent validity is established when two different methods are used to
measure one construct and these two different methods “converge” or correlate
with each other (p. 101). If a researcher is attempting to validate a new
self-report measure of aggression, she might compare scores on her scale with
behavioral observations of aggression. This would provide empirical evidence
for convergent validity.
41. Suppose women score, on average, 15 points
below men on a certain intelligence test. Define psychometrics and explain how
these results should be interpreted in terms of biological and/or cultural and
environmental influences.
Correct Answer:
Psychometrics is a
school of psychology that uses tests as objective measures of the mind and
mental processes (p. 92). Too much meaning should not be attributed to the
differences in scores derived from psychometric tests of intelligence; they
should be interpreted with respect to culture and context. In the example
above, the results do not mean that men are biologically or genetically more
intelligent than women. First, intelligence is a multi-faceted construct and
can be defined and measured in many ways. This test may aim to measure IQ,
social intelligence, or scholastic aptitude; because there are many types of
intelligence, results should be interpreted specifically for the type of
intelligence that researchers intended to measure. More importantly, in
contrast to the hereditarian view of intelligence, environment matters the most
when looking at differences between groups of people. Genes together with the
environment will influence individual differences, but only culture and
environmental influences can explain between-group differences (p. 103). This
means that men and women may be similar in their biologically-based
intelligence, but that certain environmental or social factors have limited
women and created the difference in scores.
42. What is reliability and validity? Why are
tests for reliability and validity necessary? What is the relation between
reliability and validity?
Correct Answer:
Reliability is the
consistency of a measure (p. 101). Assuming that the construct is not rapidly
changing, reliability is expected for successful measurement of a given
construct. We need to test for reliability in order to show that our measure
provides consistent results; highly inconsistent results would suggest that we
are not effectively measuring the construct, rather, the scores are being
affected by error. Measurement validity is how well a measure is measuring what
it is intended to measure (p. 106). Without establishing measurement validity,
we cannot assume that scores relate to our construct of interest. Reliability
is a prerequisite for validity; a measure cannot be measuring what it intends
to unless it also produces consistent results (assuming the construct is not
rapidly changing). At the same time, a measure can be reliable without being valid.
Effective measures are both reliable and valid.
43. Many psychology students become frustrated
when they are trying to think of new research questions; they bemoan that “all
the good questions are taken!” Using an example to support your discussion, explain
the relation between theoretical constructs and experimentation and describe
how you might respond to such a statement.
Correct Answer:
Theoretical constructs
are abstract entities intimately connected to theories. They are used to help
describe, explain, and predict different findings (p. 105). Constructs are not
directly measurable and they cannot be fully captured by any one measurement.
The construct of self-esteem, for example, is not completely understood through
a self-report scale. Constructs include many different dimensions, any one of
which can be translated into a useful, measurable variable that can be studied.
New operational definitions of a construct add to our understanding of that
construct. Indeed, because constructs cannot be measured directly, they requireexperimentation that includes operational
definitions that are thought to create the conditions that reveal and reflect
the construct (p. 92). Essentially, experimentation is necessary to empirically
validate a construct. At the same time, there is not one experiment that can
fully describe a construct. To the student who believes all questions are
taken, it might be useful to explain how through creativity and thoughtful
reflection, new operational definitions of a construct can be generated and
used to explore the construct.
Comments
Post a Comment