Scribd
Upload
76 views1 page

Writing and Evaluating Test Items

This document provides guidelines for writing effective test items in a psychological assessment. It discusses defining the construct being measured, generating an item pool, avoiding long or double-barreled items, and mixing positively and negatively worded items. Common problems in item writing like unfocused stems, negative wording, window dressing, and unequal option lengths are also outlined. Finally, the document describes three common item formats: dichotomous true/false, polytomous multiple choice, and Likert scales, noting advantages and considerations for each.

Uploaded by

John Andrew Evia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
76 views1 page

Writing and Evaluating Test Items

This document provides guidelines for writing effective test items in a psychological assessment. It discusses defining the construct being measured, generating an item pool, avoiding long or double-barreled items, and mixing positively and negatively worded items. Common problems in item writing like unfocused stems, negative wording, window dressing, and unequal option lengths are also outlined. Finally, the document describes three common item formats: dichotomous true/false, polytomous multiple choice, and Likert scales, noting advantages and considerations for each.

Uploaded by

John Andrew Evia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

PSYCHOLOGICAL ASSESSMENT | L6 – WRITING AND EVALUATING TEST ITEMS

GUIDELINES FOR ITEM WRITING best to develop three or four good


 Define clearly what you want to measure. To do distractors for each item.
this, use substantive theory as a guide and try to - Guessing – another issue concerns the scoring
make items as specific as possible. of multiple-choice examinations.
 Generate item pool. Theoretically, all items are
COMMON PROBLEMS IN MULTIPLE-CHOICE ITEM WRITING
randomly chosen from a universe of item content.
In practice, however, care in selecting and  Unfocused stem – the stem should include the
developing items is valuable. Avoid redundant information necessary to answer the question. Test
items, in the initial phases, you mat want to write takers should not need to read options to figure out
three or four items for each one that will eventually what question is being asked.
be used on the test or scale.  Negative stem – whenever possible, the stem
 Avoid exceptionally long items. Long items are should exclude negative terms such as not and
often confusing or misleading, except.
 Keep the level of reading difficulty appropriate  Window dressing – information in the stem that is
for those who will complete the scale. irrelevant to the question or concept being assessed
 Avoid “double barreled” items that convey two is considered “window dressing” and should be
or more ideas at the same time. For example, avoided.
consider an item that asks the respondent to agree  Unequal option length – the correct answer and
or disagree with the statement, “I vote Democratic the distractors should be about the same length.
because I support social programs.” There are two  Negative options – whenever possible, response
different statements with which the person could options should exclude negatives such as “not”
agree: “I vote Democratic” and “I support social  Clues to the correct answer – test writers
programs.” sometimes inadvertently provide clues by using
 Consider mixing positively and negatively vague terms such as might, may, and can.
worded items. Sometimes, respondents develop the Particularly in the social sciences where certainly is
“acquiescence response set.” This means that the rare, vague terms may signal that the option is
respondent will tend to agree with most items. To correct.
avoid bias, you can include items that are worded in  Heterogeneous options – the correct option and all
the opposite direction. of the distractors should be in the same general
category
ITEM FORMATS
1. The Dichotomous Format 3. The Likert Format
- offers two alternative for each item - One popular format for attitude and personality
- usually, a point is given for the selection of one scale requires that a respondent indicate the
of the alternatives degree of agreement with a particular
- the most common example is the true-false attitudinal question
examination - Five alternatives; strongly disagree, disagree,
- overall, dichotomous items tend to be less neutral, agree, and strongly agree
reliable, and therefore less precise than some - In some applications, six options are used to
of the other item formats. avoid allowing the respondent to be neutral.
- Personality test constructors often prefer this The six options are: strongly disagree,
type of format because it requires absolute moderately disagree, mildly disagree, mildly
judgment. agree, moderately agree, and strongly agree.
- Dichotomous items have many advantages for - The Likert Format is familiar and easy to use.
personality tests with may subscales. One is It is likely to remain popular in personality
that they make the scoring of the subscales and attitude tests.
easy.
2. The Polytomous Format
- Sometime called polychotomous
- Resembles the dichotomous format expect that
each item has more than two alternative
- a point is given for the selection of one of the
alternatives, and no point is given for electing
any other choice.
- The multiple-choice tests are easy to score,
and the probability of obtaining a correct
response by chance is lower than it is or true-
false items
- Incorrect choices are called distractors
- A review of the problems associated with
selecting distractors suggests that it is usually

You might also like