[논문]리커트 5점척도에서 자극에 의한 응답결과의 변화 측정에 관한 연구

노영희

doi:10.3743/kosim.2011.28.3.335

리커트 5점척도에서 자극에 의한 응답결과의 변화 측정에 관한 연구
A Study on Measuring the Change of the Response Results in Likert 5-Point Scale Measurement 원문보기

정보관리학회지 = Journal of the Korean society for information management, v.28 no.3 = no.81, 2011년, pp.335 - 353

노영희 (Department of Library & Information Science, Konkuk University)

초록
AI-Helper

본 연구에서는 리커트 5점 척도 설문에 참여했던 응답자들이 특정 자극에 의해 동일한 2차 설문이 주어졌을 때, 본인의 처음 응답결과를 어떻게, 어떤 방향으로 바꾸는지를 측정하고자 하였다. 이를 위해 3개 설문지의 1차, 2차 또는 3차에 걸친 재설문 결과들을 집단간 차이, 자극의 종류, 설문목적의 차이, 응답변화의 방향 및 변화정도의 관점에서 분석하였다. 본 연구를 통해 발견된 연구결과는 다음과 같다. 첫째, 전문가 집단과 일반 집단 중 전문가 집단이 상대적으로 의견을 바꾸지 않는 것으로 유의하게 검증되었다. 둘째, 설문목적에 따른 차이는 없는 것으로 조사되었고, 자극의 종류 중 시스템 사용경험보다는 다른 사람들의 의견이 정보로 주어졌을 때 더 많은 영향을 받는 것으로 나타났다. 셋째, 최초응답에서 긍정적인 답변에 응답했을수록 답변을 바꾸지 않는 것으로 나타났고 부정적인 답변자는 대부분 긍정적인 방향으로 의견을 바꾸는 것으로 유의하게 검증되었다. 넷째, 최초 응답을 바꾸는 경우 응답변화의 폭이 2단계 이상인 경우는 그다지 많지 않고 대부분 1단계 정도 전후로 바꾸는 경향이 있는 것으로 분석되었다. 마지막으로 중간응답자가 의견을 가장 많이 바꾸고 양극단의 경우 의견을 잘 바꾸지 않을 것이라는 예측을 하였으나 부정적인 답변자일수록 의견을 긍정적인 방향으로 바꾸는 것으로 분석되었다.

Abstract ▼ AI-Helper

This study examines how and which direction respondents who participated in 5-point Likert scale surveys change their initial responses when they are given an identical second survey after certain treatments. The research employs three identical questionnaires (first, second and third surveys) to analyze survey results based on group differences, kinds of treatment, survey purposes, and response change direction and the degree. This paper concludes that, first, it is significant that specialist groups do not change their initial responses compared to a general librarian group. Second, there are no differences by survey purpose; however, participants tend to change their initial responses by others' opinions rather than by previous use experiences. Third, participants who initially answered positively tend not to change their responses, and most participants who answered negatively change their initial responses in a positive direction. Fourth, when there are changes, participants change their initial responses by less than two points, and most of them change by one point. Finally, the hypothesis that middle responses change most and that participants who respond at both ends do not change their opinion was rejected by the finding that participants who answered on the negative end tend to change their initial responses in a positive direction.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

For the first survey, general librarians participated in the survey without system use experience, and for the second survey, they all had experience using the system, thus, the treatment was system use. Based on that, this research conducted analysis on the differences among groups and differences by treatment and by survey purpose. Especially, this paper focuses on how, in what direction, and to what degree participants’ responses changed when they answered closer to the positive end of the scale (point 5 on the Likert scale) or closer to the negative end (point 1 on Likert scale).
Even though this study did not clearly define various other factors such as psychological changes, survey interest changes, and survey background knowledge changes, this research has important implications for further studies.
Accordingly, this study attempts to analyze the degree of changes based on the result of the first survey, and provides suggestions and discussions on how to evaluate changes of answers to each question. This study focuses on how much these treatments or information intercepts are influential to participants.
That is, it was not possible to conduct second and third surveys that can explain all of the factors influencing response change, such as survey purpose, kinds of treatment, and differences between groups. Thus, this study employed existing surveys and results that were similar to this research purpose. Thus, it is not possible to determine which factor influenced response change.

가설 설정

Question 1: In 5-point Likert scale measurement, do participants responding point 3, the neutral point, change their initial responses most frequently and are at the highest degree of change after treatment?
Question 2: In 5-point Likert scale measurement, do participants responding point 1 (negative) or point 5 (positive), barely change their initial responses even with any kind of treatment?
Question 3: If participants change their initial re- sponses, how much is the degree of change?
Question 4: If participants change their initial responses, are they in the positive direction (closer to point 5) or negative direction (closer to point 1), or are they at the neutral point?
Question 5: Can the survey purpose or kind of treatment be classified as influential factors?
Question 6: Are there differences among the three survey groups?

제안 방법

In other words, scholars have analyzed user responses before and after using the system through survey method; however, they tend to present significant levels showing whether user attitude changed positively or there were no changes even after using the system. Accordingly, this study attempts to analyze the degree of changes based on the result of the first survey, and provides suggestions and discussions on how to evaluate changes of answers to each question. This study focuses on how much these treatments or information intercepts are influential to participants.
Especially, this paper focuses on how, in what direction, and to what degree participants’ responses changed when they answered closer to the positive end of the scale (point 5 on the Likert scale) or closer to the negative end (point 1 on Likert scale).
Target groups consisted of two specialist groups and one general librarian group. In the case of the specialist groups, this study employed the Delphi method, and all three surveys were conducted based on 5-point Likert scale measurement. During the first survey administration, one of two specialist groups was polled to develop library evaluation indicators and the other was polled to develop metadata.
The data collected was not sufficient to clearly determine treatment differences and group differences. That is, it was not possible to conduct second and third surveys that can explain all of the factors influencing response change, such as survey purpose, kinds of treatment, and differences between groups. Thus, this study employed existing surveys and results that were similar to this research purpose.
Questionnaires for first, second and third surveys are identical. The research also examines degree of change by respondents who answered neutrally, and then compares it with degree of change by respondents who answered positively or negatively.
This paper examines the degree of change in responses across first, second and third administration of the same set of questionnaires, which used a 5-point Likert scale for measurement. It focuses on how neutral middle responses change and compares the response changes of participants at both positive and negative ends of the scale.
This research analyzes changes of survey results from previous studies conducted by author of this study, based on survey questionnaire method and Delphi technique (using questionnaires). Survey questionnaires used a 5-point Likert scale.
In this paper, response change was examined by using 5-point Likert scale measurement, and this was relatively unique compared to existing studies. This research intended to measure how initial responses of middle point or both end points on the Likert 5-point scale were changed by certain information or treat- ment, and analyzed the direction and degree of such changes. Moreover, it studied variables such as differences in the group characteristics of specialist groups and the general librarian group and survey purposes, and their influences on response changes.
This study analyzed how initial responses of participants in surveys change after treatment based on existing survey results. Surveys and response results used in this research are the ones already used in previous studies by the author of this research project; the target group was librarians.
This study attempted to analyze the degree and the direction of changes of survey participants’ initial responses by respondents’ system use experiences or others’ opinions.
This study employed a nonparametric test instead of using a parametric method to ensure normality because all variables in this study are measured based on an ordinal Likert scale. In other words, the influence of the first survey result as a treatment to the change in the second survey response was tested by the Johnkheere-Terpstra test.
Two Delphi surveys and one general survey were conducted in this research. For the Delphi surveys, participants were paid 100 US dollars per person, and for the general survey 10 US dollars was given to each respondent.

대상 데이터

This study analyzed how initial responses of participants in surveys change after treatment based on existing survey results. Surveys and response results used in this research are the ones already used in previous studies by the author of this research project; the target group was librarians. The Delphi technique was used in Survey 1 (Noh 2010a) and Survey 2 (Noh 2010b), and an on-line survey method was used in Survey 3 (Noh 2010c).

이론/모형

Here, responses that changed from first survey to second and from second survey to third were all considered as one single case. As a result, there were few changes when the initial responses were in the highest positive direction, and it was significant based on the JohnkheereTerpstra test (see Table 5).
This research analyzes changes of survey results from previous studies conducted by author of this study, based on survey questionnaire method and Delphi technique (using questionnaires). Survey questionnaires used a 5-point Likert scale. In the second and third surveys, this research analyzes degree of change in responses compared to previous survey answers.
Table 6 and Table 7 demonstrate response change rates by survey, from the first survey to the second and from the second survey to the third; the results of each survey have similar trends as above. The results are all significant with the Johnkheere-Terpstra test (see Table 6 and Table 7).
This sub-section compares each group’s average, standard deviation, and two-way contingency table, and also tests significances by using the JohnkheereTerpstra test.

성능/효과

Consequently, this study has found that there are group differences between specialist groups and the general librarian group, and that the specialist groups had a tendency not to change their initial responses compared to the general librarian group. At the same time, this study has shown that respondents who were in negative direction on the first survey tended to change their responses in a positive direction significantly, and participants who initially answered with positive point responses did not change their initial responses.
First, the analysis result on the differences between the specialist groups and the general librarian group showed that specialist groups did not change their initial responses compared with the general librarian group. Also, as the survey was repeated, response change average increased and deviation decreased in specialist groups; however, for the general librarian group, the average increased and deviation decreased.
The resulting data showed that the scale ‘Clear - 10 ... 0 - Unclear’ consistently lead to significantly higher ratings in all seven cases.

후속연구

Nevertheless, there were group differences in responses to the second and third surveys, and it was significant that response change was influenced by treatment. However, it is true that more data in various dimensions will be necessary for further studies.

참고문헌 (53)

Amoo, T. and H. H. Friedman. 2001. "Do numeric values influence subjects' responses to rating scales?" Journal of International Marketing and Marketing Research, 26: 41-46.

상세보기
Armitage, C. and C. Deeprose. 2004. "Changing student evaluations by means of the numeric values of rating scales." Psychology Learning and Teaching, 3: 122-125.

상세보기
Armstong, R. L. 1987. "The midpoint on a five-point Likert-type scale." Perceptual and Motor Skills, 64: 359-362.

상세보기
Beck, J. 1996. Career anchors, organizational commitment, and job plateaus: An analysis of hotel executive operating committee members' career development. (Doctoral Dissertation, Purdue University, 1996). Dissertation Abstracts International, 58(03). (Publication Number: AAT 9725508).
Becker, S. L. 1954. "Why an order effect." Public Opinion Quarterly, 18: 271-278.

상세보기
Belson, W. A. 1966. "The effects of reversing the presentation order of verbal rating scales." Journal of Advertising Research, 6: 30-376.
Bignami-Van Assche, S. G., G. Reniers, and A. A. Weinreb. 2003. "An assessment of the KDICP and MDICP data quality." Demographic Research, S1(2): 31-76.
Brook, D. and G. J. Upton. 1974. "Primacy effects in single trial free recall." Applied Statistics, 23: 414-419.

상세보기
Carp, F. M. 1974. "Position effects on interview response." Journal of Gerontology, 29: 581-587.
Church, A. H. 1993. "Estimating the effect of incentive on mail survey response rates: A meta-analysis." Public Opinion Quarterly, 57: 62-79.

상세보기
Cobanoglu, C. B. Warde, and P. J. Moreo. 2001. "A comparison of mail, fax and web-based survey methods." International Journal of Market Research, 43(4): 441-452.
Cummins, R. A. and E. Gullone. 2000. "Why we should not use 5-point Likert scales: The case for subjective quality of life measurement." Proceedings, Second International Conference on Quality of Life in Cities, Singapore: National University of Singapore, 74-93.
Dawes, J. 2008. "Do data characteristics change according to the number of points used? An experiment using 5-point, 7-point and 10-point scales." International Journal of Market Research, 50: 61-77.

상세보기
De Leeuw, E. D. 1992. Data Quality in Mail, Telephone, and Face-to-face Surveys. Amsterdam: TT Publications.
Dillman, D. A. 1999. Mail and internet surveys: The tailored design method, (2nd Ed.). New York: John Wiley and Sons.
Dillman, D. A. and J. Tarnai. 1988. "Administrative issues in mixed mode surveys." In R. M. Groves, P. P. Biemer, L. E. Lyberg, J. T. Massey, W. L. Nicholls, II & J. Wakesberg (Eds.), Telephone survey methodology (pp. 509-528). New York: Wiley.

상세보기
Everett, S. A., J. H. Price, A. Bedell, and S. K. Telljohann. 1997. "The effect of a monetary incentive in increasing the return rate of a survey to family physicians." Eval Health Professions, 20: 207-4.

상세보기
Fox, R. J., M. R. Crask, and J. Kim. 1988. "Mail survey response rate: A meta-analysis of selected techniques for introducing response." Public Opinion Quarterly, 52: 467-491.

상세보기
Friedman, H. H., Y. Wilamowsky, and L. W. Friedman.1981. "A comparison of balanced and unbalanced rating scales." The Mid-Atlantic Journal of Business, 19(2): 1-7.
Garland, R. 1991. "The mid-point on a rating scale: Is it desirable?" Marketing Bulletin, 2: 66-70, Research Note 3.

상세보기
Goldberg, L. R. 1981. "Unconfounding situational attributions from uncertain, neutral, and ambiguous ones: A psychometric analysis of descriptions of oneself and various types of others." Journal of Personality and Social Psychology, 41(3): 517-552.

상세보기
Green, B. F. 1969. "Attitude measurement." In G. Lindzey (Ed.), Handbook of Social Psychology. Cambridge, Mass.: Addison-Wesley.

상세보기
Guy, R. F. and M. Norvell. 1977. "The neutral point on a Likert scale." Journal of Psychology: Interdisciplinary and Applied, 95(2): 199-204.

상세보기
Hartley, J. and L. R. Betts. 2010. "Four layouts and a finding: The effects of changes in the order of the verbal labels and numerical values on Likert-type scales." International Journal of Social Research Methodology, 13(1): 17-27.

상세보기
Jacoby, J. and M. S. Matell. 1971. "Three-point Likert scales are good enough." Journal of Marketing Research, 8: 495-500.

상세보기
James, J. and R. Bolstein. 1992. "Large monetary incentives and their effect on mail survey response rates." Public Opinion Quarterly, 56: 442-53.

상세보기
Komorita, S. S. 1963. "Attitude content, intensity and the neutral point on a Likert scale." Journal of Social Psychology, 61: 327-334.
Krosnick, J. A. and D. F. Alwin. 1987. "An evaluation of a cognitive theory of response-order effects in survey measurement." Public Opinion Quarterly, 51: 201-209.

상세보기
Kulas, J. T., A. A. Stachowski, and B. A. Haynes. 2008. "Middle response function in Likert-responses to personality items." Journal of Business Psychology, 22: 251-259.

상세보기
Likert, R. 1932. "A technique for the measurement of attitudes." Archives in Psychology, 140: 1-55.

상세보기
Matell, M. S. and J. Jacoby. 1972. "Is there an optimal number of alternatives for Likert scale items? Effects of testing time and scale properties." Journal of Applied Psychology, 56(6): 506- 509.

상세보기
McFadden, L. S. and S. E. Krug. 1984. "Psychometric function of the "neutral" response option in clinical personality scales." Multivariate Experimental Clinical Research, 7: 25-33.

상세보기
Mueller, J. E. 1970. "Choosing among 133 candidates." Public Opinion Quarterly, 34: 395-402.

상세보기
Nicholls, M. R., C. A. Orr, M. Okubo, and A. Loftus. 2006. "Satisfaction guaranteed: The effect of spatial biases on responses to Likert scales." Psychological Science, 17: 1027-1028.

상세보기
Noh, Y. 2010a. "A study on developing evaluation criteria for electronic resources in evaluation indicators of libraries." Journal of Academic Librarianship, 36(1): 41-52. .

상세보기
Noh, Y. 2010b. "A study on designing of metadata for constructing the Library Map Information System." Journal of the Korean Society for Information Management, 27(3): 241-264.

원문보기 상세보기
Noh, Y. 2010c. "A Study on Metadata Elements for Web-based Reference Resources System Developed through Usability Testing." Library Hi Tech, 29(2): 242-265. .
Payne, J. D. 1971. "The effects of reversing the order of verbal rating scales in a postal survey." Journal of the Market Research Society, 14: 30-44.
Payne, S. L. 1951. The Art of Asking Questions. Princeton: Princeton University Press.
Quinn, S. B. and W. A. Belson. 1969. The Effects of Reversing of the Order of Presentation of Verbal Rating Scales in Survey Interviews. London: Survey Research Centre.
Ruggg, D. and H. Cantril. 1944. "The wording of questions." In H. Cantril (Ed.) Gauging public opinion. Princeton: Princeton University Press

상세보기
Schwarz, N. B., H. J. Knauper, E. Hippler, E. Noelle- Neumann, and L. Clark. 1991. "Rating scales: Numeric values may change the meaning of scale labels." Public Opinion Quarterly, 55: 570-582.

상세보기
Schwarz, N., H. J. Hippler, and E. Noelle-Neumann. 1992. "A cognitive model of response-order effects in survey measurement." In N. Schwarz& S. Sudman (Eds.), Context effects in social and psychological research (pp. 187-199). New York: Springer-Verlag.

상세보기
Sedlmeier, P. 2006. "The role of scales in student ratings." Learning and Instruction, 16: 401- 415.

상세보기
Shcuman, H. and S. Presser. 1981. Questions and Answers in Attitude Surveys. New York: Academic Press.
Sheehan, B. K. and J. S. McMillan. 1999. "Response variation in e-mail surveys: An exploration." Journal of Advertising Journal, 39(4): 45-54.

상세보기
Stewart, T. J., E. Roberts, P. Eleazer, R. Boland, and D. Widland. 2006. "Reliability and validity issues for two common measures of medical students' attitudes toward older adults." Educational Gerontology, 32: 409-421.

상세보기
Weems, G. H., A. J. Onwuegbuzie, J. B. Schreiber, and S. J. Eggers. 2003. "Characteristics of respondents who respond differently to positively and negatively worded items on rating scales." Assessment and Evaluation in Higher Education, 28: 587-607.

상세보기
Wildt, A. R. and M. B. Mazis. 1978. "Determinants of scale responses: Label versus position." Journal of Marketing Research, XV: 261-267.
Worcester, R. M. and T. R. Burns. 1975. "A statistical examination of the relative precision of verbal scales." Journal of Market Research Society, 17(3): 181-197.

상세보기
Wyatt, R. C. and L. S. Meyers. 1987. "Psychometric properties of four 5-point Likert-type scales." Educational and Phychologicla Measurement, 47: 27-35.

상세보기
Yammarino, F. J., S. J. Skinner, and T. L. Childers. 1991. "Understanding mail survey response behavior: A meta-analysis." Public Opinion Quarterly, 55: 613-639.

상세보기
Yun, G. W. and C. W. Trumbo. 2000. "Comparative response to a survey executed by post, e-mail, & web form." Journal of Market Research Society, 6(1): 235-239.

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증