Term
|
Definition
| The science of psychological measurement |
|
|
Term
| What are the three defining characteristics of A psychological test? |
|
Definition
1) test is a sample of behavior
2) sample is obtained under standardized conditions
3) established rules for scoring |
|
|
Term
| What are the 3 categories of psychological tests? |
|
Definition
1) tests of performance (well-defined task)
2) behavior observations (response to a context)
3) self-report |
|
|
Term
| What kind of test is a driving test and example of? |
|
Definition
|
|
Term
| What are 2 Concerns over Psychological Tests? |
|
Definition
1) Psychological tests might have an undue impact on an individual
2) Tests might change decisions/actions of individual |
|
|
Term
| What are the 4 scales of measurement? |
|
Definition
-Nominal
-Ordinal
-Interval
-Ratio |
|
|
Term
| What is the mean and how is it calculated? |
|
Definition
|
|
Term
| What is the mode and how is it calculated? |
|
Definition
-most common score
-if more than 1 most common, average or report 2 modes |
|
|
Term
| What is the median and how is it calculated? |
|
Definition
-middle score
-(N+1)/2
-for an even number average the two middle scores |
|
|
Term
| What does A large variance indicate? |
|
Definition
| that individual scores tend to differ substantially from the mean and therefore from each other |
|
|
Term
| What does A small variance indicate? |
|
Definition
that most
individuals received very similar scores and therefore that most people are very close to the mean |
|
|
Term
| what does standard deviation mean? |
|
Definition
the average amount the scores deviated
from the mean |
|
|
Term
| How is standard deviation calculated? |
|
Definition
| Square root of the variance |
|
|
Term
| How is the variance calculated? σ2 |
|
Definition
-for each score: subtract the mean from it and square it
-add up all the new cores
-divide the total by N |
|
|
Term
| What is the difference between a positive Z score and a negative Z score? |
|
Definition
+ above the mean
- below the mean |
|
|
Term
| How is a Z score calculated? |
|
Definition
|
|
Term
| With a perfect correlation, all points in the scattergram will _______? |
|
Definition
|
|
Term
| How is correlation calculated? |
|
Definition
|
|
Term
| What does a regression do? |
|
Definition
it chooses a line called the
Least Squares Line. The line is chosen based on when prediction errors are at a minimum. |
|
|
Term
| What is the mean and standard deviation of a T score? |
|
Definition
|
|
Term
| What is the formula for a T score? |
|
Definition
| T = (new SD/old SD) x (old score - old mean) + new mean |
|
|
Term
| Do linear transformations change the shape of the distribution? |
|
Definition
|
|
Term
|
Definition
The percentile rank represents the percentage of the norm group that earned a raw score less than or
equal to the score of that particular individual |
|
|
Term
| How is percentile rank calculated? |
|
Definition
| Place from the top score / n |
|
|
Term
| What is A norm-based score? |
|
Definition
where an individual stands in
comparison with the particular normative group that defines the
set of standards |
|
|
Term
| What are Criterion-referenced tests? |
|
Definition
| evaluate a person's score with reference to a set standard (e.g., a driving test) |
|
|
Term
What is wrong with this question:
My instructor grades fairly and
quickly. |
|
Definition
| it should only have central thought, more than one makes it double-barreled |
|
|
Term
What is wrong with this question?
For what age group will it not be
the case that people disapprove of graded vehicle licensing? |
|
Definition
|
|
Term
| What is a Thurstone scale? |
|
Definition
-attempt to measure attitudes on an interval scale
-statements are are sorted into categories by judges based on how strong the statements are |
|
|
Term
|
Definition
| All respondents who agree with the stronger statements of the attitude will also agree with milder statements |
|
|
Term
| What is Cumulative scoring? |
|
Definition
| the higher the score on the test, the higher the test taker is on the ability, trait, characteristic |
|
|
Term
| What is Ipsative scoring? |
|
Definition
| the response choices are pitted against one another so that choosing one option, by definition, makes the respondent higher on one scale and lower on the other |
|
|
Term
| What is the Construct, or rational approach Test Development Strategy? |
|
Definition
| Start with psychological theory underlying the construct/trait |
|
|
Term
| What are the two kinds of Empirical Approaches to test development? |
|
Definition
-The contrasted groups approach
-The criterion keyed approach |
|
|
Term
| What is the criterion keyed approach? |
|
Definition
| focuses on examining the correlation between each item and some criterion (e.g., performance in university) |
|
|
Term
| What is the contrasted groups approach? |
|
Definition
| focuses on looking for differences in the way two groups respond to the same item |
|
|
Term
| What are the 5 kinds of response sets? |
|
Definition
-social desirability
-random responding
-dissimulation
-acquiescence
-criticalness |
|
|
Term
| What is social desirability? |
|
Definition
a kind of response set.
A propensity for giving a socially approved response (rather than the true response) |
|
|
Term
| What is random responding? |
|
Definition
a kind of response set.
when examinees fail to attend to the
content of test items, and respond randomly Due to:
-lack of motivation
-Inability to complete task accurately |
|
|
Term
|
Definition
a kind of response set.
Refers to completing an inventory so as to “fake good” or “fake bad” |
|
|
Term
|
Definition
a kind of response set.
Tendency to generally agree |
|
|
Term
|
Definition
a kind of response set.
Tendency to disagree. |
|
|
Term
|
Definition
| the expected value (long term average) of the variable |
|
|
Term
| What is the difference between random and systematic error? |
|
Definition
Systematic: errors that are consistently in the same direction
Random: average out to zero over an infinite number of measurements |
|
|
Term
| What are the assumptions of classical test theory? |
|
Definition
X = T + E
Error is random (+ve or ‐ve) |
|
|
Term
| What is The correlation between true score and error according to classical test theory? |
|
Definition
|
|
Term
| What is the reliability coefficient rxx? |
|
Definition
| the ratio of true score variance to the total variance of test scores |
|
|
Term
A test with _____ measurement error is a
reliable test |
|
Definition
|
|
Term
| Reliability indicates the proportion of variance in test scores that is due to or accounted by variability in ______ |
|
Definition
|
|
Term
| What is Parallel Test Model? |
|
Definition
way of thinking about Reliability: the correlation between any two random parallel tests
- a high correlation means a high reliability |
|
|
Term
Smaller error scores will __________
reliabilities |
|
Definition
|
|
Term
| What are the 4 ways to assess reliability? |
|
Definition
-test-retest reliability
-parallel forms reliability
-split-half reliability
-internal consistency (alpha) |
|
|
Term
| What is Test‐Retest Reliability? |
|
Definition
This is an estimate of stability
-a test is taken and then retaken later
-Practice & carryover effects can
spuriously increase reliability |
|
|
Term
| What is Parallel Forms Reliability? |
|
Definition
This is an estimate of equivalence
-take a test and then take a similar test again later |
|
|
Term
| What is Split‐Half Reliability? |
|
Definition
This is an estimate of internal consistency
-correlate two halves of the test
-each different split ½ will yield a different reliability coefficient |
|
|
Term
| What is Cronbach’s Alpha? |
|
Definition
| a measure of internal consistency |
|
|
Term
In the Cronbach’s Alpha formula, what do these mean?
K
σ2i
σ2x |
|
Definition
K: number of test items
σ2i: variance of the test item
σ2x: variance of the test total scores |
|
|
Term
for the Standardized Alpha formula, what do these mean?
k
rij |
|
Definition
k: number of test items
rij: average inter-correlation among test items |
|
|
Term
| How does the length of the test (k) influence reliability? |
|
Definition
| The more items you have, the more the random errors cancel each other out. This is because errors are sometimes +ve and sometimes –ve |
|
|
Term
| How can you see how the mean inter‐item correlation of the test (r) is influencing your reliability? |
|
Definition
| use the standardized alpha formula |
|
|
Term
| How does The variance of the true scores in the sample (σ2T) influence reliability? |
|
Definition
| if there is no variance, the reliability is lowered |
|
|
Term
What formula can be used to
predict the effect of lengthening a test? |
|
Definition
| The Spearman Brown formula |
|
|
Term
In the The Spearman Brown formula, what do these terms mean?
newrx
oldrxx
n |
|
Definition
newrx : Reliability of lengthened/shortened test
oldrxx : Reliability of original test
n : Ratio of new to old test length of the form |
|
|
Term
| What is The Standard Error of Measurement (SEM)? |
|
Definition
| how much observed scores deviate from the true score |
|
|
Term
| The higher the reliability of a test, the _____ the SEM |
|
Definition
|
|
Term
In the Standard Error of Measurement (SEM) formula, what do these mean?
σx
rxx |
|
Definition
σx : standard deviation of test scores
rxx : reliability of the test |
|
|
Term
| What is Correction for attenuation? |
|
Definition
| estimate of the correlation you would expect between two imperfect measures if the effects of measurement error could be removed |
|
|
