You are on page 1of 36

Data Collection Forms

Primary Data

Primary Data : information obtained exclusively for current research Personal Interview Telephone survey Mail survey Telephone Interview Computer assisted telephone interviewing and Computer administered telephone survey Self-Administered Surveys

Secondary Data

Secondary Data archival or previously recorded information

Procedure for Developing a Questionnaire

Specify what information will be sought Determine type of questionnaire and method of administration Determine content of individual questions Determine form of response to each question Determine wording of each question Determine question sequence Determine physical characteristics of questionnaire Reexamine steps 1-7 and revise if necessary

Step 1

Step 2 Step 3
Step 4 Step 5 Step 6 Step 7 Step 8 Step 9

Pretest questionnaire and revise if necessary

Guidelines for Question Wording


1. Use simple words and questions 2. Avoid ambiguous words and questions 3. Avoid implicit alternatives 4. Avoid implicit assumptions 5. Avoid generalizations

Guidelines for Question Sequencing

Use simple, interesting opening questions

Carefully design branching questions


Ask for classification information last Place difficult or sensitive questions near the end

Requirements for a Good Questionnaire


1. 2.

3. 4.

You must ask the right questions Respondents must properly understand your questions Respondents must know the answers Respondents must be willing and able to tell you those answers

1. Rules for asking the right questions

Ask whether the question fits the way the market works. Ask whether the question addresses the research objectives

2. Do Respondents Understand the Question?

Q: Does your home have power conditioning equipment to protect your critical equipment against power fluctuations?

2a. Do Respondents Understand the Words in the Question?

Q : I am going to read you a short list of words that could be used to describe TV programs, movies, products, or almost anything else. If "soso" is worth 50 points, please tell me what number you would assign to each of these other words. You can give each word any number above zero, no matter how large it is. Let's start with bad. If so-so is worth 50 points, what number would you assign to bad?

2b. Do All Respondents Understand it in the Same Way?

Q: What is your income?

2c. Do Respondents Understand in the Way You Intended?

Q: What are all the reasons why you bought your groceries at Publix rather than some other store?

2c. Do Respondents Understand in the Way You Intended? (contd.,)

"Why do you shop at Publix rather than another store close to you?"

How do you Minimize Problems of Misunderstanding?


Rule # 1: Be Specific Q: In the past six months, has your household purchased any major appliances new from the store?

How do you Minimize Problems of Misunderstanding? Another Version

Q: We consider the following items to be major appliances: refrigerators, kitchen ranges or ovens, microwave ovens, freezers, washing machines, dryers, room air conditioners, television sets, VCRs, and camcorders. In the past six months, has your household purchased any major appliances new from the store?

Example

Q: I have a list of household appliances. As I read each one, please tell me whether or not your household has purchased this type of appliance new from the store during the past six months. How about. . . Yes No A refrigerator? . . . . . . . . . 1 . . . 2 Etc... . . . . . . . . . . . . . . . . . 1 . . . 2

How do you Minimize Problems of Misunderstanding?

Rule # 2: Specify who, what, where, when and how? Q: What is your income?

How do you Minimize Problems of Misunderstanding?

In 2001, about what was your total family income before taxes? Please count income from all members of your household, and from all sources including sources such as interest and dividends.

How do you Minimize Problems of Misunderstanding?

Rule # 3: Specify how the answer should be given Q: Overall, how satisfied were you with the care you received at our hospital?

How do you Minimize Problems of Misunderstanding?

Q: Overall, how satisfied were you with the care you received at our hospital? very satisfied, moderately satisfied, slightly satisfied, or not at all satisfied?

Q: What are the two most important reasons


you buy your groceries at Publix rather than some other store?

How do you Minimize Problems of Misunderstanding?

Rule # 4: Use simple language Rule # 5: Use words with only one meaning Rule # 6: Use numbers rather than indefinite adjectives to measure magnitudes.

How do you Minimize Problems of Misunderstanding?


Rule # 7: Ask questions one at a time In the past six months, have you bought a Television or a VCR? In the past six months, have you bought a Television? In the past six months, have you bought a VCR?

3. Do the respondents know the answer?

Rule # 1: Were they there?

Proxy respondents

Rule # 2: Can they remember?

Memory issues

Rule # 3: Do they have Opinions?

Rule # 4: Are intentions meaningful?

Social desirability

Q: I have a list of hospitals in our area. As I read each one, please tell me how you would rate that hospital as a place to receive care: excellent, good, fair, or poor. How about . . .
Excellent Good Fair Poor

Eastside Hospital? . . . 4 . . . . 3 . . . . 2 . . . . 1 Lakeview Hospital? . 4 . . . . 3 . . . . 2 . . . . 1

Presbyterian Hospital? . 4 . . . 3 . . 2 . . . 1
St. Peter's Hospital? . 4 . . . . 3 . . . . 2 . . . . 1

Q: If there was a local magazine like Consumer Reports that evaluated restaurants, auto repair shops, plumbers, stores, and other local businesses, what is the likelihood that your family would subscribe to this magazine? Would you say your family definitely would subscribe, probably would subscribe, might or might not subscribe, probably would not subscribe, or definitely would not subscribe?

How do you minimize problems from respondents not knowing the answers
1. 2. 3.

Qualify respondents for knowledge Use the right time frame Consider providing cues to aid memory

BOUNDED RECALL

4.

Use multiple measures for imprecise concepts

4. Willingness to Respond

The problem of social desirability Q: During the past month, since (DATE) , did you drink milk even once? Yes . . . . 1 (ASK A) No . . . . 2 (GO TO X)

(IF YES) A. About how often did you drink milk during the past month? Once . . . . . . . . . . . . ...1 2-3 times . . . . . . . . . .2 About once a week . .. . .. 3 2-3 times a week . . . . .. 4 4-6 times a week . . . . . . 5 About once a day . . . . . 6
More than once a day . . . ..7

Willingness to Respond

Q: During the past month, have you read any books other than for work or school?

How do you Minimize the Problem


Train interviewers Use comparative choice Check questions for social loading Do not reveal the identity of the sponsor Use open questions

Closed vs. Open Questions


Easy. Cost of coding is reduced. Quicker, standardized interviews. Can be answered without thinking. Pre-testing is a must. Limit the richness of data.

Principles of Response Category Design


Categories must be exhaustive Mutually exclusive Do not list Dont know or No answer options Presented in order Counterbalancing issues Relate to ONE underlying dimension

Principles of Response Category Design

"excellent-good-average-fair-poor" How would you rate the taste of Eagle Brand Honey Roast Peanuts? Would you say they are very sweet, sweet, bland, salty, or very salty?

Principles of Response Category Design


How many categories? Should we have a neutral category? How many questions should be used to measure a phenomenon?

Single vs. Multi-item?

Q: How often are your buying decisions influenced by the availability of coupons, rebates, or sales? Would you say very often, pretty often, not too often, or never?

Single vs. Multi-item?


SA
I usually check the newspaper for coupons . . . . . . . . . . . . I will buy a product I don't usually buy if I have a coupon for it . I'm much more likely to go into a store if it is having a sale . .

SD