2018 Vol. 38 No. 1 80-85 PSYCHOLOGICAL EXPLORATION * SWLS 1,2 2, 1. 241000 2. 100875, ( M group ) ( M1) ( M2) ( M3) ( M4) - ( M5) ( M6) ( SWLS), 1343 ( 17-25, 20. 01 ± 1. 53), ( vs. ), ( vs. ), ( vs. ), ( vs. ), ( vs. ), ( vs. ) ( SWLS) : ( 1) ( Δχ 2 = 0. 49 ~ 10. 59,p > 0. 05) ; ( 2),M5 M6 ( Δχ 2 ( 1 = 3. 96 20. 89,p < 0. 05) ; ( 3),M3 M4 ( Δχ 2 ( 4) = 14. 75,Δχ 2 ( 5) = 23. 91,p < 0. 05) ; ( 4) ( Δχ 2 = 11. 01 ~ 41. 95, p < 0. 05) ; ( 5),M4 ( Δχ 2 ( 5) = 64. 40,p < 0. 05) ; ( 6),M6 ( Δχ 2 ( 1) = 11. 49,p < 0. 05) ; ; B841. 2 A 1003-5184 2018 01-0080 - 06 1 Internet or On - line Dodou & Winter 2014 Raffaelli et al. 2016 1 Measurement Equivalence / Invariance 2 Hardre Crowson & Xie 2012 4 1-12 Cieciuch et al. 2015 Hauk 2015 Lewis 3 Watson & White 2009 Meade Lautenschlager & Michels 2007 Hauk 2015 4 Observer bias response bias Davis 1999 5 * CBA120108 E - mail zhengguang_liu@ 126. com
38 1 SWLS 81 2008 Hardre et al. 2012 SWLS 2 Factorial Invari- 2. 1 ance Byrne Shavelson & Muthén 1989 Byrne Multi - group Confirmatory Factor Analysis MCFA Meade & Lautenschlager 2004 1343 MCFA 355 26. 40% 988 M group M0 73. 60% Invariant Covariance M1 Configural Invariance M2 Metric Invariance M4 Strict Invariance - M5 Factor Variance / Covariance Invariance M6 Latent Mean Invariance Vandenberg & Lance 2000 the Satisfaction With Life Scale 17 ~ 25 20. 01 ± 1. 53 846 63. 00% 497 37. 00% 2. 2 SWLS Diener et al. 1999 SWLS 7 1 ~ 7 5 Diener et al. 1985
82 2018 α Δχ 2 χ 2 Δχ 2 0. 78 0. 70 Wang Yuen & Slaney Δdf χ 2 Δχ 2 2009 α 0. 90 3 2. 3 3. 1 SWLS SWLS 1 0. 02 ~ 0. 47 0. 14 ~ 0. 80 M group 0 ~ 2 0 ~ 7 M1 M2 Curran West & Finch 1996 M3 M4 - α 0. 90 M5 M6 α 0. 86 ~ 0. 92 χ 2 / df CFI TLI 90% CI RMSEA SRMR 1 % M SD α group1 975 72. 60% 19. 26 6. 73 0. 25-0. 31 0. 90 group2 368 27. 40% 19. 65 7. 13 0. 03-0. 37 0. 91 group1 1032 76. 80% 19. 79 6. 63 0. 16-0. 38 0. 89 group2 311 23. 20% 17. 99 7. 33 0. 38-0. 14 0. 92 group1 374 27. 80% 19. 73 7. 00 0. 34-0. 20 0. 91 group2 969 72. 20% 19. 23 6. 77 0. 12-0. 41 0. 90 group1 868 64. 60% 20. 16 7. 12 0. 14-0. 40 0. 91 group2 475 35. 40% 17. 93 6. 04 0. 08-0. 50 0. 86 1343 100. 00% 19. 37 6. 84 0. 19-0. 33 0. 90 1 3. 95 1. 57-0. 02-0. 74 2 3. 96 1. 55 0. 06-0. 70 3 4. 15 1. 57-0. 11-0. 77 4 4. 05 1. 60-0. 04-0. 80 5 3. 26 1. 78 0. 47-0. 80 3. 2 CFI > 0. 95 TLI > 0. 95 RMSEA 2 0. 10 SRMR < 0. 08 RMSEA 2 χ 2 df Δχ 2 Δdf CFI ΔCFI 90% CI RMSEA SRMR M group1 44. 45 5 0. 990 0. 067-0. 115 0. 090 0. 020 M group2 54. 16 5 0. 960 0. 126-0. 204 0. 163 0. 030 M1 98. 61 10 0. 980 0. 095-0. 136 0. 115 0. 023 M2 100. 25 14 1. 64 4 0. 980 0. 000 0. 079-0. 114 0. 096 0. 026 M3 102. 89 18 2. 44 4 0. 981 0. 001 0. 068-0. 100 0. 084 0. 026 M4 113. 48 23 10. 59 5 0. 979-0. 002 0. 063-0. 091 0. 077 0. 027 M5 114. 84 24 1. 36 1 0. 979 0. 000 0. 062-0. 089 0. 075 0. 036 M6 115. 33 25 0. 49 1 0. 979 0. 000 0. 060-0. 087 0. 073 0. 033
38 1 SWLS 83 2 χ 2 df Δχ 2 Δdf CFI ΔCFI 90% CI RMSEA SRMR M group1 65. 93 5 0. 980 0. 086-0. 133 0. 109 0. 024 M group2 21. 99 5 0. 990 0. 062-0. 151 0. 105 0. 020 M1 87. 92 10 0. 982 0. 088-0. 129 0. 108 0. 023 M2 93. 54 14 5. 62 4 0. 982 0. 000 0. 075-0. 110 0. 092 0. 029 M3 101. 60 18 8. 06 4 0. 981-0. 001 0. 068-0. 099 0. 083 0. 032 M4 110. 49 23 8. 89 5 0. 980-0. 001 0. 062-0. 090 0. 075 0. 030 M5 114. 45 24 3. 96 * 1 0. 979-0. 001 0. 061-0. 089 0. 075 0. 052 M6 135. 34 25 20. 89 ** 1 0. 974-0. 005 0. 068-0. 095 0. 081 0. 093 M group1 22. 36 5 0. 990 0. 058-0. 139 0. 096 0. 019 M group2 66. 72 5 0. 980 0. 090-0. 138 0. 113 0. 025 M1 89. 08 10 0. 982 0. 088-0. 130 0. 109 0. 023 M2 91. 45 14 2. 37 4 0. 982 0. 000 0. 074-0. 109 0. 091 0. 027 M3 106. 20 18 14. 75 ** 4 0. 980-0. 002 0. 070-0. 101 0. 085 0. 028 M4 130. 11 23 23. 91 ** 5 0. 976-0. 004 0. 070-0. 097 0. 083 0. 033 M5 130. 41 24 0. 30 1 0. 976 0. 000 0. 068-0. 095 0. 081 0. 033 M6 130. 83 25 0. 42 1 0. 976 0. 000 0. 066-0. 093 0. 079 0. 033 M group1 45. 83 5 0. 990 0. 072-0. 124 0. 097 0. 018 M group2 40. 78 5 0. 970 0. 090-0. 159 0. 123 0. 034 M1 86. 61 10 0. 982 0. 087-0. 128 0. 107 0. 025 M2 106. 30 14 19. 69 ** 4 0. 979-0. 003 0. 082-0. 117 0. 099 0. 047 M3 137. 42 18 31. 12 ** 4 0. 972-0. 007 0. 084-0. 115 0. 099 0. 047 M4 179. 37 23 41. 95 ** 5 0. 964-0. 008 0. 087-0. 115 0. 101 0. 058 M5 190. 38 24 11. 01 ** 1 0. 962-0. 002 0. 088-0. 115 0. 102 0. 088 M6 215. 84 25 25. 46 ** 1 0. 956-0. 006 0. 094-0. 120 0. 107 0. 083 * p < 0. 05 * * p < 0. 01 CFI > 0. 95 TLI > 0. 95 SRMR < 0. 08 1 4 vs. M1 ~ M6 Δχ 2 p > 0. 05 vs. 2 vs. vs. M1 ~ M4 Δχ 2 p > 0. 05 vs. - M5 M6 Δχ 2 1 = 3. 96 20. 89 p < 0. 05-3 vs. M1 M2 Δχ 2 p > 0. 05 M3 M4 Δχ 2 4 = 14. 75 Δχ 2 5 vs. = 23. 91 p < 0. 05 4 vs. M1 ~ M6 Δχ 2 p < 0. 05
84 2018 Cheung & Rensvold M1 ~ M3. 2008. Widaman & Reise 1997. 40 2 228-239. Byrne B. M. Shavelson R. J. & Muthén B. 1989. Testing 2008 for the equivalence of factor covariance and mean structures The issue of partial measurement invariance. Psychological ΔCFII Δχ 2 Δχ 2 Bulletin 105 3 456-466. ΔCFI ΔTLI Δχ 2 ΔCFI Cheung G. W. & Rensvold R. B. 2002. Evaluating Goodness ΔCFI ΔCFI > 0. 001 - of - Fit Indexes for Testing Measurement Invariance. Structural Equation Modeling A Multidisciplinary Journal 9 2 2002 Cheung Rensvold 233-255. ΔCFI Δχ 2 Cieciuch J. Davidov E. Oberski D. L. & Algesheimer R. ΔCFI > 0. 002 Δχ 2 2015. Testing for measurement invariance by detecting local misspecification and an illustration across online and pa- p < 0. 05 per - and - pencil samples. European Political Science 14 Fournier et al. 2007 4 521-538. Curran P. J. West S. G. & Finch J. F. 1996. The robustness of test statistics to nonnormality and specification error ΔCFI ΔCFI in 2 confirmatory factor analysis. Psychological Methods 1 1 16-29. Davis R. N. 1999. Web - based administration of a personality questionnaire Comparison with traditional methods. Behav- ior Research Methods Instruments & Computers A Journal of the Psychonomic Society Inc 31 4 572-577. Diener E. Emmons R. A. Larsen R. J. & Griffin S. 1985. The satisfaction with life scale. Journal of Personality Assessment 49 1 71-75. Diener E. Suh E. M. Lucas R. E. & Smith H. L. 1999. Subjective well - being Three decades of progress. Psychological Bulletin 125 2 276-302. SWLS Dodou D. & Winter J. C. F. D. 2014. Social desirability is the same in offline online and paper surveys A meta - analysis. Computers in Human Behavior 36 36 487-495. Fournier J. Gaudreau P. Demontrond - Behr P. Visioli J. Forest J. & Jackson S. 2007. French translation of the Flow State Scale - 2 Factor structure cross - cultural invariance and associations with goal attainment. Psychology of ΔCFI Sport and Exercise 8 6 897-916. SWLS Hardre P. L. Crowson H. M. & Xie K. 2012. Examining Contexts - of - Use for Web - Based and Paper - Based Questionnaires. Educational & Psychological Measurement 72 6 1015-1038. Hauk S. 2015. A Comparison of Web - based and Paper -
38 1 SWLS 85 and - Pencil Homework on Student Performance in College Algebra. Primus Problems Resources & Issues in Mathematics Undergraduate Studies 25 1 61-79. Lewis M. I. Watson B. & White K. M. 2009. Internet versus paper - and - pencil survey methods in psychological experiments Equivalence testing of participant responses to health - related messages. Australian Journal of Psychology 61 2 107-116. Meade A. W. & Lautenschlager G. J. 2004. A Monte - Carlo Study of Confirmatory Factor Analytic Tests of Measurement Equivalence / Invariance. Structural Equation Modeling A Multidisciplinary Journal 11 1 60-72. Meade A. W. Lautenschlager G. J. & Michels L. C. 2007. Are Internet and Paper - and - Pencil Personality Tests Truly Comparable An Experimental Design Measurement Invariance Study. Organizational Research Methods 10 10 322-345. Raffaelli M. Armstrong J. Tran S. P. Griffith A. N. Walker K. & Gutierrez V. 2016. Focus on Methodology Beyond paper and pencil Conducting computer - assisted data collection with adolescents in group settings. Journal of Adolescence 49 1-9. Vandenberg R. J. & Lance C. E. 2000. A review and synthesis of the measurement invariance literature Suggestions practices and recommendations for organizational research. Organizational Research Methods 3 1 4-70. Wang K. T. Yuen M. & Slaney R. B. 2009. Perfectionism depression loneliness and life satisfaction a study of high school students in Hong Kong. The Counseling Psychologist 37 2 249-274. Widaman K. F. & Reise S. P. 1997. Exploring the measurement invariance of psychological instruments Applications in the substance use domain. The Science of Prevention Methodological Advances from Alcohol and Substance Abuse Research 9 281-324. Testing Measurement Invariance of Satisfaction with Life Scale SWLS based on the Multi - group Confirmatory Factor Analysis Wang Daoyang 1 2 Liu Zhengguang 2 1. Department of Psychology Anhui Normal University Wuhu 241000 2. Collaborative Innovation Center of Assessment toward Basic Education Quality Beijing Normal University Beijing 100875 Abstract Measurement Invariance is important in the psychometric application of self - report scale or questionare which is a prerequisite for cross - group comparison. As an popular method to analyze Measurement Invariance multi - group confirmatory factor analysis contains various theoritical models and has different combination of models in application. The current study systemetically summarized these relative theoritical models and then proposed several models for testing Factorial Invariance including confirmatory factor analysis across groups without any limitation Mgroup Configural Invariance Model M1 Metric Invariance Model M2 Scalar Invariance Model M3 Strict Invariance Model M4 Factor Variance / Covariance Invariance Model M5 Latent Mean Invariance Model M6. The study took the Satisfaction With Life Scale SWLS as an example with the subjects of 1343 college students age 17-25 20. 01 ± 1. 53 to test SWLS Measurement Invariance according to different groups as below In a hurry or not Hurry vs. No - hurry Mood in the test Positive mood vs. Negative mood Noise or not Noise vs. Non - noise Response time Long response time vs. Short response time Gender Male vs. Female Hukou Agricultural vs. Non - agricultural. The results show that a Factorial Invariance is tenable across the Hurry group and No - hurry group Δχ 2 = 0. 49 ~ 10. 59 p > 0. 05 b Partial Factorial Invariance is tenable across the Positive mood group and Negative mood group with M5 Invariance Model and M6 Invariance Model untenable Δχ 2 1 = 3. 96 20. 89 p < 0. 05 c Partial Factorial Invariance is tenable across the Noise group and Non - noise group with M3 Invariance Model and M4 Invariance Model untenable Δχ 2 4 = 14. 75 Δχ2 5 = 23. 91 p < 0. 05 d Factorial Invariance is tenable across the Long response time group and Short response time group Δχ 2 = 11. 01 ~ 41. 95 p < 0. 05 e Partial Factorial Invariance is tenable across the Male group and Female group with M4 Invariance Model untenable Δχ 2 5 = 64. 40 p < 0. 05 f Partial Factorial Invariance is tenable across the Rural group and Non - rural group with M6 Invariance Model untenable Δχ 2 1 = 11. 49 p < 0. 05. Key words measurement equivalence structural invariance SWLS