THE QUESTIONNAIRE

(cont.)

Format

 

• Include a brief introduction.
• Take note of the order of your questions.
• Group questions that rely on the same response mode.
• Place scale items in random order.
• Determining the appropriate length of the questionnaire.
• Use at least three items to measure a concept.

 

Determining Validity and Reliability

 

Validity

            The degree to which a measure actually measures what is claimed

 

Reliability

            The consistency of the measure with itself.

 

Additional Controls:

1. Check questions
2. Measures of test-taking behavior
3. Polarity rotation and control for response set

 

Sampling Subjects

 

*Samples must be representative of the whole population.

 

Administering the Questionnaire

 

-         experimental studies and questionnaire studies

-         through the mail, by fax, or in classrooms

-         limits of subject willingness

-         response rates

            “A response of at least 50 percent is adequate for analysis and reporting. A response of at least 60 percent is good. And a response rate of 70 percent is very good.”

-         “debriefing”

 

Analyzing and Interpreting Results

 

            *Surveys cannot establish causal relationship directly. In any case, the focus is on describing patterns, rather than asserting cause-and-effect relations.

 

^top^

---

Previous - Next