Quiz
Test Construction
This quiz has question types that open in the usual player.
Questions in this quiz (13)
1Before developing a test, there are a number of questions that should be asked such as the objective, need, and usage.
- ATrue
- BFalse
2Item analysis is NOT necessary for test construction.
- ATrue
- BFalse
3This is not related to the complexity or obscurity of the item. It can be hard to say why one item is more difficult than another. This is actually the proportion of testtakers who answered the item correctly.
- AItem-difficulty index
- BItem-reliability index
- CItem-validity index
- DItem-discrimination index
4The index is calculated by taking the total number of testtakers who answered an item correctly and dividing by the total number of testtakers.
- AItem-difficulty index
- BItem-reliability index
- CItem-validity index
- DItem-discrimination index
5This index provides an indication of the internal consistency of a test. The higher the index, the higher the internal consistency.
- AItem-difficulty index
- BItem-reliability index
- CItem-validity index
- DItem-discrimination index
6What index measures the degree to which a test measures what it purports to measure.
- AItem-difficulty index
- BItem-reliability index
- CItem-validity index
- DItem-discrimination index
7Which index indicates how adequately an item separates between high test scores and low test scores on an entire test. Each item can be thought of as a separate test.
- AItem-difficulty index
- BItem-reliability index
- CItem-validity index
- DItem-discrimination index
8The correlation between the score on an item and the total test score. A positive correlation indicates that the item measures the same thing as the overall test. Directly related to the reliability of a test.
- AItem-total correlation
- BInter-item correlation
9This index can tell us why some items fail to discriminate between subjects. If the correlation is low there are two possibilities. The item is not related to other items. The item varies in relatedness across other items.
- AItem-total correlation
- BInter-item correlation
10Items cannot be analysed in a qualitative manner.
- ATrue
- BFalse
11[blank_start]Levels of measurement[blank_end] (nominal, ordinal, interval, and ratio).
[blank_start]Age-based scales[blank_end] – testtaker performance as a function of age is of interest.
[blank_start]Grade-based scales[blank_end] – testtaker performance as a function of grade is of interest.
[blank_start]Stanine scale[blank_end] – All raw scores are transformed into scores that can range from 1-9.- ALevels of measurement
- BAge-based scales
- CGrade-based scales
- DStanine scale
- EPercentile scale
- FPercentage scale
12[blank_start]Rating Scale[blank_end]: A grouping of words, statements, or symbols on which judgements of the strength of a particular trait, attitude, or emotion are indicated. Smile face to sad face. Mild, moderate, severe. Not helpful to helpful.
[blank_start]Likert Scale[blank_end]: Widely used. 5-7 alternate responses on an agree-disagree / approve-disapprove continuum. Usually reliable, return ordinal data.
[blank_start]Paired comparisons[blank_end]: Testtakers are asked to choose between two items (pictures, objects, statements).
[blank_start]Guttman scale[blank_end]: A variation on the Likert scale, testtakers have to select which statement they agree with. Statements are arranged in order from a weaker to stronger position about an attitude or belief.- ARating Scale
- BLikert Scale
- CPaired comparisons
- DGuttman scale
- EGunther scale
- FLike Scale
13A good test item should
- Abe reliable
- Bdiscriminate testtakers
- Cbe answered correctly by high scorers
- Dbe answered incorrectly by low scorers
- Ebe easy to answer
Information
- Description
- Psychological Measurement Quiz on Test Construction, created by Ryan Bentham on 20/06/2018.
- Author
- Ryan Bentham
- Language
- English
- Views
- 4
- Tags
- Rating
- No ratings yet Rate this quiz