EPPP Flashcards
What is negative predictive value
A test says the person does not have a disease and they actually do not have a disease
What is positive predictive value
A test says the person has a disease and they actually do have the disease
What is specificity
The probability that a test will correctly identify people without the disease from the pool of people without the disease
What is sensitivity
The probability that a test will correctly identify people with the disease from the pool of people with the disease
Are Z scores a standard score yes or no
Yes
Are T scores standard score yes or no
Yes
Is a percentage score a standard score yes or no
No
Is a Wechsler IQ score a standard score yes or no
Yes
The item difficulty index ranges from
0-1.0
Item difficulty - 0 =
No one answers the item correctly
Item difficulty - 1.0 =
Everyone answers the item correctly
If a test developer wants to add more difficult items to her test, she will include items that I have an item difficulty index of? .90, .10, .50 or 0
.10; not 0- it’s not useful to have items that nobody can answer
Divergent validity
Scores on a measure do not correlate with scores on measures of unrelated traits
Item response theory
Scores are reported in terms of the examinees level on a trait or ability measured by the test instead of in terms of a total score
What kind of validity Does a measure have when it correlates highly with other measures of the same trait
Convergent validity
Attest has divergent or discriminant validity when
When a measure has a little correlation with measures of different traits
The multitrait multi method matrix contains correlation coefficients that provide information about
Convergent and discriminant validity
Kappa statistic provides a more accurate estimate of reliability than percent agreement as far as interrater because
It’s calculation includes removing the effects of chance agreement
Which type of reliability is most appropriate for estimating the reliability of a multiple choice speed test
Alternate forms reliability
A coefficient of stability is obtained by
Administering the same test twice to the same group of people on two different occasions and then correlate the two sets of scores
Consensual observer drift occurs when observers ratings become
Increasingly less accurate overtime in a systematic way
What’s the best way to control consensual observer drift
Alternate raters. This occurs when the Raiders were working together influence each other‘s rating so that they assigned readings and increasingly similar ways
The reliability coefficient just like any other correlation coefficient is larger when
There is an unrestricted range of scores, so when the tryout sample contains examinees were heterogenous with regard to the attribute measured by the test. Homogenous sample would restrict the score range thereby impacting reliability.
The very best way to demonstrate that it has has adequate reliability is by using what method that is fairly costly time consuming and difficult
Alternate forms or equivalent forms
In the factor analysis when 2 factors are orthogonal this means that
They are not correlated
The monotrait heteromethod coefficient is a measure of what kind of validity
Convergent
Heterotrait monomethod coefficient is a measure of
Divergent validity
Monotrait and monomethod coefficient indicates
Reliability
Heterotrait-heteromethod is a measure of
Divergent validity
Cronbachs alpha is an appropriate method for evaluating reliability when
All test items are designed to measure the same underlying characteristic
Cronbachs alpha is another name for
Coefficient alpha and it’s used to assess internal consistency reliability
Incremental validity is a measure of
Decision making accuracy. It refers to the increase or increment in decision-making accuracy that results from the use of a new predictor for example the increase in accurate hiring decisions
Attest developer would use the Kuder Richardson formula KR20 in order to
Evaluate a tests internal consistency reliability
The optimal item difficulty level for a true false test is
.75 which is half way between 100%. .75 is half way between 100% and 50%
According to classical test theory total variability in test scores is due to
True score variability plus random error
Which formula estimates the effects of shortening or lengthening a test on the test reliability coefficient
Spearman Brown
Cross validation refers to
Reassessing a tests criterion related validity with a new sample
