Quiz
Norms, Validity and Reliability
This quiz has question types that open in the usual player.
Questions in this quiz (23)
1A method of evaluation and a way of deriving meaning from test scores by evaluating an individual testtaker's scores and comparing it to scores of a group of testtakers.
- ANorm-referenced testing
- BCriterion-referenced testing
- CReliability
- DValidity
2A method of evaluation and a way of deriving meaning from test scores by evaluating an individual’s score with reference to a set standard. Predetermined standard (pass/fail).
- ANorm-referenced testing
- BCriterion-referenced testing
- CReliability
- DValidity
3The precision with which the tool measures and the extent to which error is present in measurement.
- ANorm-referenced testing
- BCriterion-referenced testing
- CReliability
- DValidity
4Does the measure actually measure what is says it measures?
- ANorm-referenced testing
- BCriterion-referenced testing
- CReliability
- DValidity
5[blank_start]Percentiles[blank_end]: A distribution that is divided into 100 equal parts (not the same as a percentage). An expression of the percentage of people whose score on a test or measure falls below a particular raw score.
[blank_start]Age Norms[blank_end]: The average performance of different samples of testtakers who were at various ages at the time the test was administered. Height is an example. Falls under the broader term Developmental Norms.
[blank_start]Grade norms[blank_end]: Average test performance of testtakers in a given school grade. A grade-based spelling test. Falls under the broader term Developmental norms.
[blank_start]National norms[blank_end]: Norms derived from a normative sample that was nationally representative of the population at the time the norming study was conducted.
[blank_start]National anchor norms[blank_end]: Norms for two equivalent tests are compared and equivalency tables are generated.
[blank_start]Subgroup norms[blank_end]: A normative sample can be segmented by any of the criteria initially used in selecting subjects for the sample.
[blank_start]Local norms[blank_end]: Normative information with respect to the local population’s performance on some test.- APercentiles
- BAge Norms
- CGrade norms
- DNational norms
- ENational anchor norms
- FSubgroup norms
- GLocal norms
6Domain-referenced or content-referenced testing is also known as
- ACriterion-referenced
- BNorm-referenced
7Criterion-referenced testing is a predetermined standard (pass or fail) or a standard on which a judgement or decision may be based.
- ATrue
- BFalse
8Criterion-referenced testing is a method of evaluation and a way of deriving meaning from test scores by evaluating an individual testtaker's score and comparing it to scores of a group of testtakers.
- ATrue
- BFalse
9A good psychological test must have good reliability, but validity is not as important.
- ATrue
- BFalse
10Reliability is about consistency, dependability, and replicability
- ATrue
- BFalse
11• Give test A at time 1, then the same test at time 2 to the same person and correlate the results.
• Scores can be affected by carry over from one test to the next (practice etc.).
• Gives a measure of stability over time.
• May not always be appropriate for psychological characteristics that change with time (e.g. current level of stress).- ATest-retest reliability
- BAlternate or Parallel forms reliability
- CSplit-half reliability
- DInternal-consistency
- EInterscorer reliability
12• Two versions of a test that measure the same construct are compared.
• Give test A and test B at time 1 and correlate the results.
• The tests can be administered close in time if carryover is not a problem.
• Gives a measure of content consistency.
• When delayed, gives a measure of stability over time.
• Not always possible to have two forms of a test.- ATest-retest reliability
- BAlternate or Parallel forms reliability
- CSplit-half reliability
- DInternal-consistency
- EInterscorer reliability
13• Correlate halves of test A such as odd/even given to one group of people.
• Gives a measure of internal consistency.
• Many ways to split a test.
• Problem is the test is then half its length giving smaller scores. Range will be smaller so correlation will be smaller. Can be corrected by using the Spearman-Brown formula.- ATest-retest reliability
- BAlternate or Parallel forms reliability
- CSplit-half reliability
- DInternal-consistency
- EInterscorer reliability
14• Measures of internal consistency include Kuder-Richardson Formula 20 (KR20) and Cronbach’s Alpha.
• Range from 0.00 to 1.00, higher = higher internal consistency.
• Should be around .80 to be considered consistent.
• Assume the items on the measure are testing one construct.
• Is an overall score, no information on individual items.
• Sensitive to test length, longer tests will get higher scores.
• KR20 is for dichotomous items.
• Does not say how well the construct being measured is covered.- ATest-retest reliability
- BAlternate or Parallel forms reliability
- CSplit-half reliability
- DInternal-consistency
- EInterscorer reliability
15• Scores judges/observers/raters.
• Various measures are used, depending on the data set. Includes ordinary correlations, other types of correlations (Spearman’s rho), percentage agreement.- ATest-retest reliability
- BAlternate or Parallel forms reliability
- CSplit-half reliability
- DInternal-consistency
- EInterscorer reliability
16Does the test appear to measure what it is supposed to be measuring? It depends on the test, the reason the person is sitting it, and the person’s past history.
- AFace validity
- BContent validity
- CCriterion-related validity
- DConstruct validity
- EConvergent validity
- FDiscriminant validity
17Does the test cover the appropriate content for its purpose? It is established by showing the behaviours sampled are a representative sample of the attribute being measured.
- AFace validity
- BContent validity
- CCriterion-related validity
- DConstruct validity
- EConvergent validity
- FDiscriminant validity
18How well a measure predicts a desired criterion. These criteria are often related to assist decision-makers.
- AFace validity
- BContent validity
- CCriterion-related validity
- DConstruct validity
- EConvergent validity
- FDiscriminant validity
19The degree to which a study measures the underlying psychological elements that the researcher claims to be measuring.
- AFace validity
- BContent validity
- CCriterion-related validity
- DConstruct validity
- EConvergent validity
- FDiscriminant validity
20When measures are supposed to be related then their scores should correlate.
- AFace validity
- BContent validity
- CCriterion-related validity
- DConstruct validity
- EConvergent validity
- FDiscriminant validity
21When measures are NOT supposed to be related then their scores should NOT correlate.
- AFace validity
- BContent validity
- CCriterion-related validity
- DConstruct validity
- EConvergent validity
- FDiscriminant validity
22A _________ is an abstract summary of regularities in nature connected to concrete observable events. For example, gravity is abstract (a hidden force).
- AConstruct
- BNomological Networks
- CConcept
- DParadigm
23____________________ are a representation of the construct of interest the observable manifestations and the interrelationships between them. They systematically describe a construct. This information can be used as the basis for starting the process of construct validity.
- ANomological networks
- BNeurological networks
- CNetworks
- DIdiographic networks
Information
- Description
- Psychological Measurement Quiz on Norms, Validity and Reliability, created by Ryan Bentham on 19/06/2018.
- Author
- Ryan Bentham
- Language
- English
- Views
- 40
- Tags
- Rating
- No ratings yet Rate this quiz