동일방법편의(Common Method Bias)의 원인과 해결방안 = Causes and Remedies of Common Method Bias

다국어 초록 (Multilingual Abstract)

  Common method bias (CMB hereafter) is a methodological error that occurs when all variables of a research framework are measured by one common method (e.g., questionnaire). CMB causes a significant effect to an internal validity of the measurement. Therefore, CMB distorts the true relationship between variables and makes researchers lead to incorrect conclusion about the result. This paper first describes the meaning, effects, and causes of CMB. Then, with the review of papers published in Korean Management Review and Korean Journal of Management, the level of recognition of Korean researchers and their efforts to overcome CMB are described. Finally, remedies of CMB are shown in detail.<BR>  Effects<BR>  Variance of a measurement score can be classified into three types: Trait variance, method variance, and error variance. If every variable in research is measured by a common method, there would be covariance among method variances of the variables. This covariance can distort the true relationship among variables.<BR>  After the review of 70 MTMM-related papers, Cote & Buckley (1987) asserted that only 41.7% of the variance of measurement can be explained by true trait. 26.3% and 32.0% of the total variance are resulted from method factors and random errors, respectively. However, Williams & Brown (1994) concluded that effects of CMB vary both in extent and in direction depending on research situations.<BR>  Causes<BR>  Basically, CMB occurs when predictor and criterion variables are obtained from the same source or rater. It, however, can be caused by the measurement itself as well. As for method effects by characteristics of raters, they are caused by the artifactual covariance between predictor and criterion variables. Specific causes of the artifactual covariance can be social desirability, consistency motif, implicit theory, and personal traits. Causes of CMB within the measurement itself are also related to measurement items and measurement contexts. Specifically, characteristics of measurement items such as item complexity and ambiguity, scale format, scale anchor, and negatively-worded item may cause CMB. In addition, measurement contexts, the time and the place of measurement are also likely to cause CMB.<BR>  Validity of Self Report<BR>  Due to numerous problems including CMB, there have been unceasing disputes over the use of self-report survey as a measurement instrument. Although self-report surveys have many serious problems, it is not wise just to avoid them when we take efficiency and effectiveness of self-report surveys into consideration. Therefore, we need to investigate other solutions rather than just to avoid self-report survey in order to overcome CMB.<BR>  Phenomenon in Korean Academic Society of Business<BR>  We reviewed 460 papers published in Korean Management Review for past 10 years and 167 papers published in Korean Journal of Management from 1992 to 2005 to evaluate how many researchers in Korea have recognized and tried to overcome CMB. By reviewing papers published in Korean Management Review, we found that more researchers in the areas of human resource management and organization behavior than other areas such as marketing and management information system did recognize the effects of CMB. By reviewing papers published in Korean Journal of Management, we found that although many recognized the effects of CMB, few actually tried to overcome them.<BR>  Remedies<BR>  Even though it is impossible to perfectly remove CMB, there exist various ways to detect and control it. By and large CMB can be overcome in the stages of research design, data collection, and/or statistical analysis.<BR>  In the stage of research design, CMB can be controlled by using distinct measurement instruments, the temporal, proximal, psychological, and methodological separati

국문 초록 (Abstract)

  본 논문은 최근 들어서 중요한 방법론상의 이슈로 부각되고 있는 동일방법편의의 정의, 영향, 원인, 및 해결방안을 다루고 있다. 동일방법편의란 독립변수와 종속변수를 동일한 측정도구와 응답원에 의해 측정하였을 경우에 발생하는 오류다. 이는 측정의 타당도에 심각한 영향을 미쳐 연구모형 내 변수간 관계의 정도를 증가시키거나 감소시켜 연구결과를 왜곡한다.<BR>  동일방법편의가 발생하는 원인은 일관성 유지 동기, 사회적 바람직성 등 응답자의 심리적 특성에 가장 직접적인 원인이 있다. 또한 이는 설문항목 자체의 특성이나 측정상황 등에 의해 그 효과가 더 커진다. 그러나 동일방법편의의 문제를 해결하기 위해 자기보고법의 사용을 무조건 회피하는 것은 자기보고법의 이점을 고려할 때 반드시 바람직한 것은 아니다.<BR>  한편, 본 논문에서는 국내 연구자들의 동일방법편의에 대한 인식수준의 추이와 현황을 알아보기 위해 경영학연구 및 인사ㆍ조직연구에 게재된 논문을 살펴보았다. 그 결과 경영학 내 여타 분야에 비해 인사ㆍ조직 분야에서의 동일방법편의에 대한 인식수준이 상대적으로 높은 것으로 드러났다. 그러나 동일방법편의를 해결하기 위한 노력은 여전히 크게 미흡하다.<BR>  동일방법편의를 해결하기 위한 가장 좋은 방법은 각 변수의 측정방법과 응답원을 달리하는 것이다. 그러나 현실적으로는 이러한 분리가 불가능한 경우가 많기에, 본 논문에서는 연구설계 단계, 설문지 작성 단계, 통계처리 단계에서 연구자가 사용하는 통계기법에 따라 동일방법편의의 문제를 해결할 수 있는 적절한 방법을 소개한다.

목차 (Table of Contents)

• 〈초록〉
  Ⅰ. 도입말
  Ⅱ. 동일방법편의의 의미와 영향
  Ⅲ. 동일방법편의의 원인
  Ⅳ. 동일방법편의에 대한 국내의 인식수준과 현상
  Ⅴ. 자기보고법 사용의 타당성
  Ⅵ. 동일방법편의의 해결방안
  Ⅶ. 맺음말
  참고문헌
  ABSTRACT
  

참고문헌 (Reference)

1 한주희, "조직문화 인식 유형이 조직몰입 유형에 미치는 영향에 관한 연구" 한국인사.조직학회 5 (5): 95-134, 1997

2 "백기복. 1992. 한.미 기업관리자들의 리더쉽 유형 비교-시나리오 기법에 의한 탐색 적 연구. .인사.조직 연구." 한국인사.조직학회 259-286,

3 Gabbard, "sensitivity to measuring change and construct validity of therapist adaptability. Journal of Counseling Psychology" 377-386,

4 Bagozzi, "Y. 1991. Multitrait-multimethod matrices in consumer research. Journal of Consumer Research" 426-439,

5 Bagozzi, "Y. 1990. Assessing method variance in multitrait-multimethod matrices The case of self-reported affect and perceptions at work. Journal of Applied Psychology" 547-560,

6 A, "W. R. 1992. An integrative look at the use of additive and multiplicative covariance structure models in the analysis of MTMM data. Journal of Marketing Research" 51-64,

7 Howard, "W. M. 1980. Is a behavioral measure the best estimate of behavioral parameters" perhaps (perhaps): 293-311,

8 & Todor, "W. D. 1985. Relationships between leader reward and punishment behavior and group processes and productivity. Journal of Management" 53-73,

9 D. C, "Three alternative models. Academy of Management Journal" 321-331,

10 Schmitt, "The importance of theory and measurement. Journal of Organizational Behavior" 393-398,

11 Hahn, J, "The impact of the characteristics of organizational culture on the bases for organizational commitment" 5 (5): 95-134, 1997

12 Watson, "The disposition to experience negative aversive emotional states. Psychological Bulletin" 465-490,

13 "T. R. 1961. Acquiescence as a response set and as a personality characteristic. Educational and Psychological Measurement" 295-307,

14 Fisher, R. J, "Social desirability bias and self-reported values" 17 : 105-120, 2000

15 Williams, "S. E. 1994. An alternative approach to method effects by using latent-variable models Application in organizational behavioral research. Journal of Applied Psychology" 323-331,

16 Howard, "S. E. 1985. Construct validity of measures of college teaching effectiveness. Journal of Educational Psychology" 187-196.

17 Cole, "S. E. 1981. The effect of mono versus multiple operationalization in construct validation efforts. Journal of Consulting and Clinical Psychology" 395-405,

18 Billings, "S. 1978. Use of path analysis in industrial/organizational psychology Criticisms and suggestions. Journal of Applied Psychology" 677-688,

19 Ones, D. S, "Role of social desirability in personal testing for personnel selection: The red herring" 81 : 660-679, 1996

20 Phillips, "R. G. 1986. Notes on the theoretical and practical consequences of implicit leadership theories for the future of leadership measurement. Journal of Management" 31-41,

21 Byrne, "R. D. 1993. Modeling MTMM data from additive and multiplicative covariance structures An audit of construct validity concordance. Multivariate Behavioral Research" 67-96,

22 Edwards, "R. D. 1973. Measurement of personality traits Theory and technique. Annual Review of Psychology" 24 : 241-278,

23 Watson, "R. 1987. Beyond negative affectivity Measuring stress and satisfaction in the work place. In J. M. Ivancevich & D. C. Ganster From theory to suggestion" Haworth Press.

24 Moorman, "P. M. 1992. A meta-analytic review and empirical test of the potential confounding effects of social desirability response sets in organizational behaviour research. Journal of Occupational and Organizational Psychology" 131-149,

25 "P. E. 1994. Using self-report questionnaires in OB Research A comment on the use of a controversial method. Journal of Organizational Behavior" 385-392,

26 123-151. New York, "P. E. 1992. A consideration of the validity and meaning of self-report measures of job conditions. In C. L. Cooper & I. T. Robertson International review of industrial and organizational psychology" 7 :

27 Chen, "P. E. 1991. Negative affectivity as the underlying cause of correlations between stressors and strains. Journal of Applied Psychology" 398-407,

28 "P. E. 1987. Method variance as an artifact in self-reported affect and perceptions at work Myth or significant problem Journal of Applied Psychology" 438-443,

29 Podsakoff, P. M, "Organi zational citizenship behavior: A critical review of the theoretical and empirical literature and suggestions for future research" 26 : 513-563, 2000

30 Conway, J. M, "Method variance and method bias in industrial and organizational psychology" Malden, MA: Blackwell Publishers 2002

31 Cote, J. A, "Measurement error and theory testing in consumer research: An illustration of the importance of construct validation" 14 : 579-582, 1998

32 Williams, L. J, "Measurement and nonmeasurement process with negative affectivity and employee attitudes" 81 : 88-101, 1996

33 Williams, "M. R. 1989. Lack of method variance in self-reported affect and perceptions at work Reality or artifact Journal of Applied Psychology" 462-468,

34 Harrison, "M. E. 1993. Cognitive processes in self-report responses Tests of item context effects in work attitude measures. Journal of Applied Psychology" 129-140,

35 J, "M. 1992. Dispositional affect and workrelated stress. Journal of Applied Psychology" 322-335,

36 Marsh, H. W, "Latent variable models of multitrait-multimethod data" Thousand Oaks, CA: Sage Publication 1995

37 Bagozzi, "L. W. 1991. Assessing construct validity in organizational research. Administrative Science Quarterly" 421-458,

38 "L. J. 1950. Further evidence on response sets and test validity. Educational and Psychological Measurement" 3-31,

39 "L. 1957. A theory of cognitive dissonance. Stanford" Stanford University Press.

40 Harvey, "K. J. 1985. Confirmatory factor analysis of the job diagnostic survey Good news and bad news. Journal of Applied Psychology" 461-468,

41 "K. F. 1985. Hierarchically nested covariance structure models for multitrait-multimethod data. Applied Psychological Measurement" 1-26,

42 Baik, "K. B. 1992. A comparison of leadership styles between Korean and American managers An exploratory study using a scenario approach. Korean Journal of Management" 259-286,

43 R, "K. A. 1988. Cognitive processes underlying context effects in attitude measurement. Psychological Bulletin" 299-314,

44 Jackson, "K. 1993. New measures of job control and production responsibility. Journal of Applied Psychology" 753-762,

45 C. A, "K. 1981. Controlling acquiescence response bias by item reversal The effect on questionnaire validity. Educational and psychological measurement" 1101-1114,

46 Burke, "J. M. 1993. The role of negative affectivity in understanding relations between self-reports of stressors and strains A comment on the applied psychology literature. Journal of Applied Psychology" 402-412,

47 C. A, "J. F. 1979. The effect of leniency on leader behavior descriptions. Organizational Behavior and Human Performance" 1-29,

48 Becker, "J. A. 1994. Additive and multiplicative method effects in applied psychological research An empirical assessment of three models. Journal of Management" 625-641,

49 G. R, "J. 1977. An examination of the need-satisfaction models of job attitudes. Administrative Science Quarterly" 427-456,

50 Marsh, "H. W. 1989. Confirmatory factor analyses of multitrait-multimethod data" 335-361,

51 Cote, "Generalizing across 70 construct validation studies. Journal of Marketing Research" 315-318,

52 Howard, "G. S. 1994. Why people say nasty things about self-reports Journal of Organizational Behavior" 399-404,

53 Cole, "G. S. 1987. Construct validity and the relation between depression and social skill. Journal of Counseling Psychology" 315-321,

54 Johns, "G. 1994. How often were you absent-A review of the use of self-reported absence data. Journal of Applied Psychology" 574-591,

55 Heider, "F. 1947. Attitudes and cognitive organization. The Journal of Psychology" 107-112,

56 Campbell, "E. J. 1967. Methods factors in multitrait-multimethod matrices" 409-426,

57 & Organ, "D. W. 1986. Self-reports in organizational research Problems and prospects. Journal of Management" 69-82,

58 Goffin, "D. N. 1992. Analysis of multitrait-multirater performance appraisal data" 363-385,

59 Zerbe, "D. L. 1987. Socially desirable responding in organizational behavior A reconception. Journal of Management Review" 250-264,

60 Martin, "D. H. 1989. Some effects of computerized interviewing on job applicant responses. Journal of Applied Psychology" 72-80,

61 Berman, "D. A. 1976. Correlation bias in observer ratings. Journal of Personality and Social Psychology" 263-273,

62 Clark, "D. 1991. Theoretical and empirical issues in differentiating anxiety from depression. In J. Becker & A. Kleinman Psychosocial aspects of mood disorders" 39-,

63 Campbell, "D. 1959. Convergent and discriminant validation by the multitrait-multimethod matrix. Psychological Bulletin" 81-105,

64 Harrison, D. A, "Context, cognition, and common method variance: Psychometric and verbal protocol evidence" 68 : 246-261, 1996

65 Peterson, R. A, "Constructing effective questionnaires" Thousand Oaks, CA: Sage 2000

66 Kline, T. J. B, "Common method variance and specification errors: A practical approach to detection" 134 : 401-421, 2000

67 Podsakoff, P. M, "Common method biases in behavioral research: A critical review of the literature and recommended remedies" 88 : 879-903, 2003

68 Kahn, "C. F. 1957. The dynamics of interviewing. New York"

69 "B. M. 1975. Attribution of the “causes” of performance A general alternative interpretation of cross-sectional research on organizations. Organizational Behavior and Human Decision Processes" 414-432,

70 Williams, "B. K. 1994. Method variance in organizational behavior and human resource research Effects on correlations" 185-209.

71 Schmitt, "Analysis of multitraitmultimethod matrices. Applied Psychological Measurement" 1-22,

72 Hernandez, A, "Analysis of multitrait-multioccasion data: Additive versus multiplicative models" 37 : 59-87, 2002

73 Parkes, "Additive and interactive predictors of mental health. Journal of Applied Psychology" 399-409,

74 Lindell, M. K, "Accounting for common method variance in cross-sectional research designs" 86 : 114-121, 2001

75 "A. J. 1985. Methods of coping with social desirability bias A review. European Journal of Social Psychology"

76 Swain, "A. J. 1975. Analysis of parametric structures for variance matrices. Unpublished doctorial dissertation University of Adelaide"

77 Hinkin, T. R, "A review of scale development practices in the study of organizations" 21 : 967-988, 1995

78 Stone, "A reply to Salancik. Journal of Management" 255-258,

79 Kemery, "A reply to Podsakoff and Todor. Journal of Management" 525-544,

80 Ilgen, "A process focus. In B. M. Staw & L. L. Cummings Research in organizational behavior" JAI Press. 5 : 141-, j.m.1983.performanceappraisal

81 Richman, W. L, "A meta-analytic study of social desirability distortion in computer-administered questionnaires, traditional questionnaires, and interviews" 84 : 754-775, 1999

82 Spector, P. E, "A longitudinal study of relations between job stressors and job strains while controlling for prior negative affectivity and strains" 85 : 211-218, 2000

83 Lance, C. E, "A critique of the correlated trait-correlated uniqueness models for multitrait-multimethod data" 7 : 228-244, 2002

84 Spector, P. E, "A consideration of the validity and meaning of self-report measures of job conditions" New York: Wiley 10 : 249-274, 1995

85 J, "& Drasgow. F. 1987. A revision of the job diagnostic survey Elimination of a measurement artifact. Journal of Applied Psychology" 69-74,