Survey Research Social Research Methods 2217 6501 Fall

  • Slides: 27
Download presentation
Survey Research (調查研究) Social Research Methods 2217 & 6501 Fall, 2006 1

Survey Research (調查研究) Social Research Methods 2217 & 6501 Fall, 2006 1

Part I: The Overview of Survey Research questions appropriate for a survey u a

Part I: The Overview of Survey Research questions appropriate for a survey u a brief history of survey research u the logic of survey research u 2

Survey: the most widely used data-gathering technique in the social sciences and in related

Survey: the most widely used data-gathering technique in the social sciences and in related fields n “easy” to conduct surveys? No! Good surveys require thought and effort [調查研究在社會科學研究中很普 遍,也常被誤認為很容易進行,其實好 的調查需要深思與努力。] n 3

Research Questions Appropriate for a Survey n n Self-reported belief or behaviors q Behavior

Research Questions Appropriate for a Survey n n Self-reported belief or behaviors q Behavior (行為) q Attitudes/beliefs/opinions (態度/信念/意見) q Characteristics (特徵) q Expectations (期待) q Self-classification (自我歸類) q Knowledge (知識) Be careful about “why” questions q If ask respondents’ subjective understanding, “why” questions are appropriate 4

A History of Survey Research n n Can be traced back to the census

A History of Survey Research n n Can be traced back to the census (人口普 查) Several reasons to explain the popularity of survey research (post-1950 growth) q q q Computers Organizations (at universities) Data storage Funding Methodology: substantial research efforts applied 5

The Logic of Survey Research n The survey: sample many respondents who answer the

The Logic of Survey Research n The survey: sample many respondents who answer the same questions q n Test multiple hypotheses and infer temporal order Correlational (關聯性的研究): use control variables to approximate the causality test 6

Steps in Conducting a Survey: n n n Develop an instrument (a survey questionnaire

Steps in Conducting a Survey: n n n Develop an instrument (a survey questionnaire or interview schedule) Conceptualization and operationalization →write clear and complete questions How to record and organize data for analysis To collect data Coding and entering data Analyze the data & report the result 7

8

8

Conducting a survey: Survey research: complex and expensive n requires coordination between many people

Conducting a survey: Survey research: complex and expensive n requires coordination between many people and steps n requires organization and accurate record keeping [調查研究可能是非常複雜且昂貴,需要多人 配合,步驟也很多,調查的行政 作非常需要 組織及正確的記錄。] n 9

Part II. Constructing the Questionnaire principles of good question writing u aiding respondent recall

Part II. Constructing the Questionnaire principles of good question writing u aiding respondent recall u getting honest answers u open vs. closed questions u wording issues u questionnaire design issues u 10

Principles of good question writing n A good questionnaire forms an integrated whole. q

Principles of good question writing n A good questionnaire forms an integrated whole. q n Two key principles: q q n Have an introduction & nice flow Avoid confusion (避免混淆) Keep the respondent’s perspective in mind ( 從受訪者的觀點來思考) Question writing: an art & a science q Takes skills, practice, patience, and creativity 11

Ten things to avoid when writing survey questions: n n Avoid jargon, slang, and

Ten things to avoid when writing survey questions: n n Avoid jargon, slang, and abbreviations ( 避免用術語、俚語、縮寫) Avoid ambiguity, confusion, and vagueness (避免語意模糊、混淆、不確定 的字詞) q n Avoid the use of indefinite words or response categories Avoid emotional language and prestige bias (避免情緒性的字詞或專家偏差) q Use neutral language 12

Ten things to avoid when writing survey questions: n Avoid double-barreled questions (避免 一題兩問)

Ten things to avoid when writing survey questions: n Avoid double-barreled questions (避免 一題兩問) q n A double-barreled question: two or more questions joins together Avoid leading questions (避免引導式問 句) q Do not lead the respondent to choose one response over another by its wording 13

Ten things to avoid when writing survey questions: n Avoid asking questions that are

Ten things to avoid when writing survey questions: n Avoid asking questions that are beyond respondents’ capabilities (避免讓受訪者 無法回答) q q n n Phrase questions in the terms in which respondents think Be very clear in asking questions Avoid false premises (避免錯誤前提) Avoid asking about distant future intentions (避免詢問未來的意圖) 14

Ten things to avoid when writing survey questions: n Avoid double negatives (避免雙重否定) q

Ten things to avoid when writing survey questions: n Avoid double negatives (避免雙重否定) q n Double negatives: confusing Avoid overlapping or unbalanced response categories (避免重覆或偏重某些答案類別) q Response categories should be mutually exclusive, exhaustive, and balanced 15

Aiding Respondent Recall (幫助受訪者回憶) n Recalling events accurately takes time and effort. (Our memory

Aiding Respondent Recall (幫助受訪者回憶) n Recalling events accurately takes time and effort. (Our memory is not that trustworthy!) q n n The problems of telescoping Need to customize questions and interpret results cautiously. Provide aids to respondents: q q q Specific instructions Extra thinking time Provide fixed time or location references Situational framing Decomposition Landmark anchoring 16

Getting Honest Answers: Sensitive Topics (較敏感的議題) n Respondents may be reluctant to answer questions

Getting Honest Answers: Sensitive Topics (較敏感的議題) n Respondents may be reluctant to answer questions on sensitive topics. 17

Getting Honest Answers: Sensitive Topics (較敏感的議題) n n Respondents may be reluctant to answer

Getting Honest Answers: Sensitive Topics (較敏感的議題) n n Respondents may be reluctant to answer questions on sensitive topics. Use different techniques to get honest answers: q q q Establish a comfortable setting before asking Use “enhanced” phasing of questions Provide contextual background information Ask more serious actions first Self-administered questionnaire or web-based survey Randomized response technique (RRT) 18

Getting Honest Answers: Social Desirability Bias (社會期許偏差) n n n Social desirability bias: respondents

Getting Honest Answers: Social Desirability Bias (社會期許偏差) n n n Social desirability bias: respondents tend to overstate an attitude or behavior (社會認可的 壓力讓受訪者高估某些回應) Why? Respondents want to make their reports conform to social norms. Phrase questions to give respondents “facesaving” alternatives. 19

Getting Honest Answers: Knowledge Questions (知識性的問題) n n n Knowledge questions may be threatening.

Getting Honest Answers: Knowledge Questions (知識性的問題) n n n Knowledge questions may be threatening. Many people have inaccurate factual knowledge. Researchers can improve by: q q q Phrase questions carefully Use a sleeper question (運用測謊題) Check for more details 20

Getting Honest Answers: Contingency Questions (條件式問項) n n A contingency question: to avoid asking

Getting Honest Answers: Contingency Questions (條件式問項) n n A contingency question: to avoid asking questions that are irrelevant for a respondent (目的: 避免問和受訪者無關的問 題) A two- (or more) part question: the first questions are screen or skip questions 21

Open versus Closed Questions (開放式 vs. 封閉式問項) n n Open-ended questions: unstructured, free response

Open versus Closed Questions (開放式 vs. 封閉式問項) n n Open-ended questions: unstructured, free response vs. Closed-ended questions: structured, fixed response Each has advantages and disadvantages (see Box 10. 5, p. 287) 22

Open versus Closed Questions (開放式 vs. 封閉式問項) 23

Open versus Closed Questions (開放式 vs. 封閉式問項) 23

Open versus Closed Questions (開放式 vs. 封閉式問項) 24

Open versus Closed Questions (開放式 vs. 封閉式問項) 24

Open versus Closed Questions (開放式 vs. 封閉式問項) n n n Open-ended questions: unstructured, free

Open versus Closed Questions (開放式 vs. 封閉式問項) n n n Open-ended questions: unstructured, free response vs. Closed-ended questions: structured, fixed response Each has advantages and disadvantages (see Box 10. 5, p. 287) Large-scale surveys used more closed-ended questions because they are easier and quicker to answer. We can mix open-ended and closed-ended questions, and use partially open questions. Be careful about responses for closed-ended questions. 25

Neutral Positions: should provide a “no opinion” choice? n n Reasons for and against

Neutral Positions: should provide a “no opinion” choice? n n Reasons for and against a neutral or middle position Three kinds of questions: standard-format, quasifilter, and full-filter questions (標準形式、半過濾式、 全過濾式問題) n n Floaters (猶疑者): respondents “float” from giving a response to not knowing Also consider recency effect (晚近效應) Either offer a middle position or make respondents to choose a position and then ask about their choices. Selective refusals for sensitive issues 26

Agree/Disagree, Rankings or Ratings (排 序或評分)? n n Questions or statements (問題或陳述)? Rate or

Agree/Disagree, Rankings or Ratings (排 序或評分)? n n Questions or statements (問題或陳述)? Rate or rank-order items? Questions about values often show little differentiation → “rank-then-rate” procedure Better to rank items than rating (排序可能較 容易區分答案選項的重要性) Be careful about visual presentation and answer categories 27