MN 400: Research Methods CHAPTER 8 Survey Methods: Communication with Participants 1
Interviewing for Statistical Production What is an Interview? Interviewing can mean a lot What do people think about when they hear the word interviewing? What people generally think about is interviews they hear on the radio or on TV. They think of interviews with mixed feelings. Newspaper journalists are interviewing people in their daily work for their job. Then you have doctors, social workers and policemen who also have to ask questions in their job. In our profession we talk about recruiting interviews when we want to employ people. 2
Interviewing for Statistical Production History of Interviewing During the 1930s they began to use the statistical interview in USA. George Gallup started an organisation for polls - The American Institute of Public Opinion. His name has more or less become a synonym for statistical surveys. Statistics Sweden has had an interviewers organisation since 1954. 3
Difference Between Interview and Interview What is then the difference between an interview for statistical production and interviewing for other purposes. When you are interviewing for statistical production, you have questions and answers in a questionnaire (=a standardised interview). When you are performing recruiting interviews you often use an interview guide or a checklist, which is your support during the interview. You need something to follow, in order to remember important parts for the final summary. 4
Interviewing for Statistical Production A third way to interview is when you just have a rough plan for the interview with different subjects with which you shall deal. That is what you use for depth interviews in research studies. Two interviews can differ a lot depending on the respondent. And this is actually the purpose, to investigate an area and to follow associations. The interviewer must be very well informed of the topic to be able to handle a depth interview. This is quite another matter than to perform a standardised interview. 5
Purpose with the Interview When you are working with standardised interviews you want to accumulate the answers. The answers from one single person are not at all very interesting. It is first when we have many answers that it is getting exciting. The respondent herself/himself decide if she/he wants to participate or not. The interview which is more like a conversation will very often form the basis of a decision about that person. Sometimes it can be of interest for the person him/herself. You want to be healthy when you see a doctor and have a great interest that all the questions will be answered properly. If you will be interviewed by the police it will be more like an examination. If you are guilty of a crime you do not want to answer the questions. 6
Interviewing for Statistical Production The purpose of having an interview is very obvious for us who are working with statistics. It is not the same situation for the respondent. The public welfare or some other person who wants to know what you think is perhaps not always so important for the selected person. Here we have an informational problem which we will talk more about later on. 7
Questionnaire development Questionnaire development 8
A Good Questionnaire Appears A questionnaire is only as good as the questions it asks As easy to compose as a good poem But, it is usually the result of long, painstaking work 9
The Major Decisions in Questionnaire Design 1. What should be asked? Questionnaire relevance Questionnaire accuracy 2. How should each question be phrased? Structured/unstructured Disguised /undisguised 3. In what sequence should the questions be arranged? 4. What questionnaire layout will best serve the research objectives? 5. How should the questionnaire be pretested? Does the questionnaire need to be revised? 10
Fixed-alternative questions Single-dichotomy Multi-choice alternatives Frequency determination Attitude rating scales Check list question 11
No hard and fast rules Only guidelines Avoid Complexity: use simple conversational language Avoid leading and loaded questions Avoid ambiguity: be as specific as possible Avoid double-barreled items Avoid making assumptions Avoid burdensome questions Developing a Questionnaire 12
Simplified Scaling Example In its most basic form, attitude scaling requires that an individual agree with a statement or respond to a single question. This type of self-rating scale merely classifies respondents into one of two categories THE PRESIDENT SHOULD RUN FOR RE-ELECTION AGREE DISAGREE 13
Category Scales A category scale is a more sensitive measure than a scale having only two response categories - it provides more information. Questions working is an extremely important factor in the usefulness of these scales. Example How important were the following in your decision to visit Switzerland? (check one for each item) VERY SOMEWHAT NOT TOO IMPORTANT IMPORTANT IMPORTANT CLIMATE COST OF TRAVEL FAMILY ORIENTED 14
The Likert Scale An extremely popular means for measuring attitudes. Respondents indicate their own attitudes by checking how strongly they agree or disagree with statements. Items 1. It is more fun to play a tough, competitive tennis match tan to play an easy one. Strongly agree Strongly disagree 2. There is really no such thing as a tennis stroke that cannot be mastered. 3. Playing tennis is a great way to exercise.
Constant Sum Scale Divide 100 points among each of the following brands according to your preference for the brand: Brand A Brand B Brand C 16
Graphic Rating Scales A graphic rating scale presents respondents with a graphic continuum. Pictorial Visual Communications Thermometer of emotion How do you feel when your close friends do not allow you to copy their lectures? 17
A Comparative Rating Scale A Comparative Rating Scale asks respondents to rate a concept by comparing it with a benchmark Comparing delivery service of Pizza Hut and The Pizza company, you think service provided by Pizza Hut is. MUCH BETTER ABOUT THE SAME WORSE THAN 18
1. Do you believe that private citizens have the right to own firearms to defend themselves, their families, and property from violent criminal attack? Yes No Undecided 1a. How many years have you been playing tennis on a regular basis? Number of years: b. What is your level of play? Novice............... -1 Advanced....... -4 Lower Intermediate..... -2 Expert......... -5 Upper Intermediate..... -3 Teaching Pro.... -6 c. In the last 12 months, has your level of play improved, remained the same or decreased? Improved.............. -1 Decreased....... -3 Remained the same..... -2 19
2a. Do you belong to a club with tennis facilities? Yes....... -1 No....... -2 b. How many people in your household - including yourself - play tennis? Number who play tennis 3a. Why do you play tennis? (Please X all that apply.) To have fun.......... -1 To stay fit............ -2 To be with friends...... -3 To improve my game... -4 To compete........... -5 To win............... -6 b. In the past 12 months, have you purchased any tennis instructional books or video tapes? Yes....... -1 No....... -2 20
Cover Letter Dear Passenger: American Airlines is pleased to have you on board today. To help us provide the best service possible, we need to know more about you and your opinions of our service. If you are over 11 years old, we would appreciate it if you would complete this questionnaire. Your individual response will be kept secretly, the data will only be analyzed in the big picture. Your flight attendant will pick up your completed questionnaire shortly. Thank you. 21
4. Please rate each of the following with regard to this flight, if applicable. Excellent Good Fair Poor 1 2 3 4 Courtesy and Treatment from the: Skycap at airport.............. Airport Ticket Counter Agent.... Boarding Point (Gate) Agent..... Flight Attendants.............. Your Meal or Snack............. Beverage Service.............. Seat Comfort.................. Carry-On Stowage Space........ Cabin Cleanliness............. Video/Stereo Entertainment...... On-Time Departure............ 22
Lecture #9 23 Layout for Internet Questionnaires
Lecture #9 24
Lecture #9 25
Lecture #9 26
Lecture #9 27
Lecture #9 28
Lecture #9 29
Pretesting Pre-testing the questionnaire Sample Sample size Analysis Revision/deletion of question items Back translation 30
THE GOAL OF MEASUREMENT VALIDITY 31
Reliability and Validity on Target Old Rifle New Rifle New Rifle Low Reliability High Reliability High Validity Reliable but Not Valid 32
SENSITIVITY A measurement instrument s ability to accurately measure variability in stimuli or responses. 33
Some other examples Agree/Disagree questions These types of questions are commonly used in surveys. Here interviewees are asked if they agree or disagree to a statement read to them. To be useful, agree-disagree questions can be only asked about extremes of a situation. For example, to the statement: My health is fair Interviewees can readily agree if their health is good or disagree if their health is poor. 34
Some other examples Sensitive questions Facts or events with some degree of social undesirability, e.g., domestic violence, rape, HIV/AIDS, are usually not reported accurately in an interview. If a researcher expects the admission of something that is very embarrassing or illegal, a lot of efforts is necessary to convince interviewees that risks are minimal. Specifically, the following steps may be considered if sensitive questions are to be asked: 35
Some other examples Multiple-choice questions There are two or more alternatives that they prefer, interest, or agreement. Example: Why they (students) went to a certain college? The following response alternatives might be listed about chosen school: 1- Good academic reputation 2- Specific programme of study desired 3- Enjoyable campus life 4- Many friends from home attend 5- High quality of the faculty 36