Psychological Measurement
Midterm/Exam
three characteristics of a psychological test ANS:-sample of behaviour
-standardized conditions
-established rules for scoring
scoring rules ANS:some set of rules or procedures for describing in quanitiative terms the subject's
behaviour in response to the test
3 types of tests ANS:-people perform a task
-observation of subject in a particular context
-self-report measures
what are tests used for ANS:-educational testing
-personnel testing
-clinical testing
individual decisions ANS:tests can be used to counsel or advise the examinee; these tests have some
influence on the actions of the examinee
two societal concerns aobut individual decisions ANS:-people believe that results are more valuable than
they are
-tests might change the decisions or actions of individuals
important feature of comparative decisions ANS:require less information than absolute decisions
absolute decisions ANS:-involve a decision about a single person, option, object
-more precise measurement
4 issues with ability testing ANS:-do they reflect real ability differences
-are the differences big enough to matter
-do they help or hurt minorities
-should we emphasize equity or efficiency
,do ability tests reflect real ability differences? ANS:-differences may be due to bias in test but may also
reflect differences in ability
affirmative action ANS:refers to a wide variety of efforts to attract, recruit, and hire members of
underrepresented groups
informed consent ANS:participants must be informed of the general purpose and anture of the research,
as well as possible dangers and threats involved
tests might be deemed unfair if: ANS:-it leads to adverse decisions for some groups in the population
-it is the sole basis for decisions
-the consequences of doing poorly on the test are harsh
how to reduce test unfairness ANS:-multiple assessment procedures
-use more intensive screening procedures
efficiency versus equity ANS:trade-off often encountered in testing between doing what is most
beneficial for the institution versus doing what is most beneficial for some or all examinees
institutional decision ANS:decision in which an institution must make a choice about how to treat an
individual
stakeholders ANS:individuals or groups who have valid concerns aobut the development and use of
psychological tests
measurement ANS:the process of assigning numbers to objects in such a way that specific properties of
objects are faithfully represented by properties of numbers
psychologicla measurement ANS:attempts to represent some attributes of persons in terms of some
properties of numbers
nominal scales ANS:numbers are used to classify and identify persons (jersey number)
ordinal scales ANS:assigns numbers to individuals so that the rank order of the numbers corresponds
with the rank order of the individual in terms of the attribute being measured (place in a race)
interval scales ANS:-scale should indicate relative sizes of the differences between intervals
-unit of measurement and zero point are both arbitrary
(temperature)
ratio scale ANS:-ratios between the numbers assigned to persons or objects correspond to ratios
between the attributes measured in these persons or objects
, -meaningful zero point
-height (can't have negative height)
evaluation of tests is based on ANS:-reliability of scores
-validity of scores
reliability ANS:a reliable test is one that yields consistent scores when a person takes two alternate
forms of the test or when they take the same test more than once (weight scale)
vlaidity ANS:whether the test adequately measures what it is supposed to measure
statistical concepts central to psychological measurement ANS:-variability
-correlation
-prediction
variability ANS:the deviation score meausres the extent to which each individual differs from the mean
positive correlation ANS:an increase in one variable is associeted with increase in the other variable
ngative correlation ANS:an increase in one variable is associated with a decrease in the other variable
correlation coefficient ANS:statistical measure of the association between two sets of scores
linear regression ANS:method for predicting scores on one measure on the basis of scores on some
other measure
scale ANS:refers to the set of scores that might be reported for a test
z-score transformations ANS:indicate a person's standing as compared with the group mean
percentile transformaiton ANS:magnifies differences between individuals at the midle of the distribution
and compresses the differences between individuals at the extremes
anchor test ANS:the mechanism for equating the new test form to the old form through the collection of
items from the old test and the new test
norm-based interpretation ANS:when a person's test score is interpreted by comparing that score with
the scores of several other people
types of norms ANS:-local norms
-percentile ranks
-age norms
Midterm/Exam
three characteristics of a psychological test ANS:-sample of behaviour
-standardized conditions
-established rules for scoring
scoring rules ANS:some set of rules or procedures for describing in quanitiative terms the subject's
behaviour in response to the test
3 types of tests ANS:-people perform a task
-observation of subject in a particular context
-self-report measures
what are tests used for ANS:-educational testing
-personnel testing
-clinical testing
individual decisions ANS:tests can be used to counsel or advise the examinee; these tests have some
influence on the actions of the examinee
two societal concerns aobut individual decisions ANS:-people believe that results are more valuable than
they are
-tests might change the decisions or actions of individuals
important feature of comparative decisions ANS:require less information than absolute decisions
absolute decisions ANS:-involve a decision about a single person, option, object
-more precise measurement
4 issues with ability testing ANS:-do they reflect real ability differences
-are the differences big enough to matter
-do they help or hurt minorities
-should we emphasize equity or efficiency
,do ability tests reflect real ability differences? ANS:-differences may be due to bias in test but may also
reflect differences in ability
affirmative action ANS:refers to a wide variety of efforts to attract, recruit, and hire members of
underrepresented groups
informed consent ANS:participants must be informed of the general purpose and anture of the research,
as well as possible dangers and threats involved
tests might be deemed unfair if: ANS:-it leads to adverse decisions for some groups in the population
-it is the sole basis for decisions
-the consequences of doing poorly on the test are harsh
how to reduce test unfairness ANS:-multiple assessment procedures
-use more intensive screening procedures
efficiency versus equity ANS:trade-off often encountered in testing between doing what is most
beneficial for the institution versus doing what is most beneficial for some or all examinees
institutional decision ANS:decision in which an institution must make a choice about how to treat an
individual
stakeholders ANS:individuals or groups who have valid concerns aobut the development and use of
psychological tests
measurement ANS:the process of assigning numbers to objects in such a way that specific properties of
objects are faithfully represented by properties of numbers
psychologicla measurement ANS:attempts to represent some attributes of persons in terms of some
properties of numbers
nominal scales ANS:numbers are used to classify and identify persons (jersey number)
ordinal scales ANS:assigns numbers to individuals so that the rank order of the numbers corresponds
with the rank order of the individual in terms of the attribute being measured (place in a race)
interval scales ANS:-scale should indicate relative sizes of the differences between intervals
-unit of measurement and zero point are both arbitrary
(temperature)
ratio scale ANS:-ratios between the numbers assigned to persons or objects correspond to ratios
between the attributes measured in these persons or objects
, -meaningful zero point
-height (can't have negative height)
evaluation of tests is based on ANS:-reliability of scores
-validity of scores
reliability ANS:a reliable test is one that yields consistent scores when a person takes two alternate
forms of the test or when they take the same test more than once (weight scale)
vlaidity ANS:whether the test adequately measures what it is supposed to measure
statistical concepts central to psychological measurement ANS:-variability
-correlation
-prediction
variability ANS:the deviation score meausres the extent to which each individual differs from the mean
positive correlation ANS:an increase in one variable is associeted with increase in the other variable
ngative correlation ANS:an increase in one variable is associated with a decrease in the other variable
correlation coefficient ANS:statistical measure of the association between two sets of scores
linear regression ANS:method for predicting scores on one measure on the basis of scores on some
other measure
scale ANS:refers to the set of scores that might be reported for a test
z-score transformations ANS:indicate a person's standing as compared with the group mean
percentile transformaiton ANS:magnifies differences between individuals at the midle of the distribution
and compresses the differences between individuals at the extremes
anchor test ANS:the mechanism for equating the new test form to the old form through the collection of
items from the old test and the new test
norm-based interpretation ANS:when a person's test score is interpreted by comparing that score with
the scores of several other people
types of norms ANS:-local norms
-percentile ranks
-age norms
