Question 1

In order to investigate potential sex bias in a test item, we would examine an)

Accepted Answer

An item-characteristic curve (ICC) is used in item response theory to show how the probability of a correct response to a test item varies with the trait level of the respondent. It can be used to investigate potential sex bias by comparing the curves for different groups (e.g., males vs. females) to see if there is a systematic difference in how they respond to the item, indicating potential bias.

Question 2

_________________is a statistical index of how efficiently an item discriminates between persons who obtain high and low scores on the entire test.

Accepted Answer

The item-discrimination index is a statistical measure used to determine how well an item on a test distinguishes between individuals who score high overall on the test and those who score low. It indicates the effectiveness of an item in differentiating between higher and lower ability examinees.

Question 3

The item-discrimination index can vary from

Accepted Answer

The item-discrimination index measures how well an item distinguishes between high-performing and low-performing examinees. It can range from -1.0 (all low-performing examinees answer correctly and all high-performing examinees answer incorrectly) to +1.0 (all high-performing examinees answer correctly and all low-performing examinees answer incorrectly), with 0 indicating no discrimination.

Question 4

Suppose we obtain the following response patterns on a multiple choice question with correct answer "c": a b c d e
High-scorers 5 6 80 5 4
Low-scorers 15 14 40 16 15
What needs to be done to improve this test item?

Accepted Answer

This test item shows a clear distinction between high-scorers and low-scorers, with the majority of high-scorers selecting the correct answer (c) and a more distributed response among low-scorers. This indicates the item effectively differentiates between levels of understanding or preparation, which is a characteristic of a good test item.

Question 5

A graphical display of the relationship between the probability of a correct response and the examinee's position on the underlying trait measured by the test is called

Accepted Answer

The item-characteristic curve (ICC) graphically represents the relationship between the probability of a correct response on a test item and the examinee's ability level or position on the trait that the test is measuring.

Question 6

Which of the following is a desirable feature for an individually administered test?

Accepted Answer

All of the options listed are desirable features for an individually administered test as they contribute to clarity, ease of administration, and accessibility.

Question 7

The purpose of the Examinee Feedback Questionnaire is to

Accepted Answer

The Examinee Feedback Questionnaire is designed to collect feedback from examinees about their experience and response to the test, which helps test developers understand and improve the test experience.

Question 8

The expression_________ refers to the phenomenon in which a test predicts a criterion less well when used on a new sample of subjects.

Accepted Answer

Validity shrinkage refers to the decrease in predictive validity of a test when it is applied to a new sample, compared to the original sample on which it was validated.

Question 9

A key step in using the Method of Equal-Appearing Intervals would be to:

Accepted Answer

The Method of Equal-Appearing Intervals is a scaling technique that involves creating a series of items that reflect opinions in both directions while eliminating more extreme ones. This ensures that the items are evenly spaced along the continuum of opinion and that respondents can easily identify the item that best represents their own opinion.

Question 10

The simplest item-characteristic curve ICC) model is the____ , based upon item-response theory.

Accepted Answer

The Rasch model is the simplest item-characteristic curve (ICC) model based on item-response theory, focusing on the probability of a specific response to an item as a function of the difference between the person ability and item difficulty.

Question 11

To know how well each preliminary test item contributes to accurate prediction of the criterion, we would use

Accepted Answer

Item-validity index is used to determine how well a test item predicts a criterion or outcome, indicating the relevance and effectiveness of the item in measuring what it is supposed to measure.

Question 12

According to Arthur Jensen, the principal hindrances to psychometrically superior tests are

Accepted Answer

Arthur Jensen argued that copyright laws, vested interests of test publishers, and the market economy for tests are all principal hindrances to the development of psychometrically superior tests.

Question 13

The point-biserial correlation between the item score and the score on the criterion variable is needed to compute the

Accepted Answer

The item-validity index is computed using the point-biserial correlation between the item score and the criterion variable score, as it measures how well the item predicts the criterion.

Question 14

The expression___________ refers to the practice of using the original regression equation in a new sample to determine if the test predicts the criterion as well as it did in the original sample.

Accepted Answer

Cross-validation is the process of testing the effectiveness of a predictive model on a new sample to see if it performs as well as it did on the original sample.

Question 15

The expression U - L)/N defines the

Accepted Answer

The expression (U - L)/N is used to calculate the item-discrimination index, which measures how well an item differentiates between high and low scorers on a test.

Question 16

The scaling method that utilizes a rating from "Strongly Agree" to "Strongly Disagree" is called ________scaling.

Accepted Answer

The Likert scale is the scaling method that uses a range of responses from "Strongly Agree" to "Strongly Disagree," allowing respondents to express their level of agreement with a statement.

Question 17

The optimal value for the item-discrimination index is

Accepted Answer

The optimal value for the item-discrimination index is 1.0, indicating that the item perfectly discriminates between high and low scorers.

Question 18

A dichotomously scored test item with good item reliability must

Accepted Answer

A dichotomously scored test item with good item reliability should have strong internal consistency, meaning it consistently measures what it's supposed to across different instances, and it should produce a good dispersion of scores between its two alternatives, ensuring that it can differentiate between different levels of ability or understanding among test-takers.

Question 19

Examinees used in a "tryout" sample should be________ those for whom the test is ultimately intended.

Accepted Answer

Examinees in a "tryout" sample should be highly similar to those for whom the test is ultimately intended to ensure that the test results are valid and reliable for the target population.

Question 20

The _______is simply the normal distribution graphed in cumulative form.

Accepted Answer

The correct term for the normal distribution graphed in cumulative form is the "normal ogive." This graph represents the cumulative probabilities of a normal distribution, showing the proportion of observations that fall below or at each value.

Quiz 4: Validity and Test Development