Psych Testing and Assessment-Chapter 6 (Test Construction)

Question 1

5 Steps of The Test Development Process

Answer 1

1) Test Conceptualization
2) Test Construction
3) Test Tryout
4) Analysis
5) Revision

Question 2

Test Construction Guidelines

Answer 2

1) Define clearly what you want to measure (operational definitions)
2) Generate and item pool
3) Avoid exceptionally long items
4) avoid “double-barreled” items
5) Consider mixing positive and negatively worded items

Question 3

Dichotomous Format

Answer 3

-test that offers two alternatives for each item. Usually a point is given for the selection of one of the alternatives (Ie. True/False)

Question 4

Polytomous Format

Answer 4

-Resembles dichotomous format except that each item has more than two alternatives (Multiple Choice)

Question 5

Likert Format

Answer 5

• respondent indicates the degree of agreement with a particular attudinal question
• format is especially popular in measures of attitude/opinion.
• responses in Likert can be subjected to factor analysis
• odd number of options is better as this allows a ‘neutral option’
• even number of options insinuates a forced response

Question 6

Category Format

Answer 6

-technique similar to the Likert format but it uses an even greater number of choices (ie. ten point rating scale)
For example: Doctors often ask patients to rate their pain on a ten point scale

Question 7

Checklist

Answer 7

adjective checklist format is most common in personality measurement
-subject recieves a long list of adjectives and indicates whether each one is a characteristic of themselves

Question 8

Q sorts

Answer 8

• can be used to describe oneself or to provide ratings of others
• subject is given statements and asked to sort them into nine piles
  
  • ->items that end up in extreme categories usually say something interesting about the person

Question 9

Item Analysis

Answer 9

general term for a set of methods used to evaluate test items, is one of the most important aspects of test construction.

• increasing the number of items makes a test more reliable.
• ranges from .30-.70
  
  • ->.30= 30% will get it correct (this is a hard question as only 30% will get it right)
  • ->.70=70% will get it correct (easy question)

Question 10

Item Difficulty

Answer 10

defined as the number of people who get a particular item correct.

Question 11

Item Discriminability

Answer 11

determine whether the people who have done well on particular items have also done well on the whole test.

Question 12

Extreme Group Method

Answer 12

method compares people who have done well with those who have done poorly on a test.
–>difference between these proportions=discrimination index

Question 13

Point Biserial Method

Answer 13

Examine the correlation between performance on an item and performance on a total test.
-can be problematic on tests with few items since performance on the item contributes to total test score.

Question 14

Item Characteristic Curve

Answer 14

Graph of test items.

• ->x axis = total test score
• –>y axis= proportion of examinees who get the item correct.
• Ranges in the curve suggest that the item is sensitive; flat ranges suggest areas of low sensitivity
• item characteristic curve gradually rises showing that the item is sensitive to most levels of performance

Question 15

Item Response Theory (IRT)

Answer 15

• each item on a test has its own item characteristic curve that describes the probability of getting each particular item right or wrong given the ability level of each test taker.
  
  • ->testers can then make an ability judgement without subjecting the test taker to all of the test items. (the level of difficulty for each test item that is answered correctly becomes the test takers score; not the number answered correctly)

Question 16

Criterion referenced test

Answer 16

compares performance with some clearly defined criterion for learning.
–>often educators use criterion-referenced tests as a diagnostic instruments.

Question 17

Antimode

Answer 17

• bottom of the “V”
• least frequent score
• this point divides those who have been exposed to the unit from those who have not been exposed; usually taken as the cutting score or point that marks the point of decision
• left of V=scores on the left side of the V are probably those from students who have not experienced the unit; scores on the right mark those who have been exposed.