期刊文献+

自变量相对重要性评价中优势分析法和相对权重法的模拟比较 被引量:3

下载PDF
导出
摘要 【提要】目的比较和评价不同实验条件下优势分析法与相对权重法在估计自变量相对重要性时的指标差异,探索影响两方法的估计结果差异的因素。方法通过设置不同相关程度、自变量共线性水平及自变量个数等因子,模拟产生64000个不同实验条件下的实验数据,通过分析得出两种方法估计的自变量重要性的估计值及结果排序的一致性的差异。结果所有实验条件下估计值差值均值呈偏态分布,P5~P95百分位数区间不包含0。重要性排序结果的一致性检验Kendallτ均值为0.949,标准差0.05。结论两方法的重要性估计值差异虽小却不容忽视,优势分析法的估计结果比相对权重普遍略偏大,Kendallτ的回归分析表明自变量个数是影响两方法重要性估计结果排序的主要因子。自变量有无子集划分不影响方法间一致性。
出处 《中国卫生统计》 CSCD 北大核心 2014年第1期104-106,共3页 Chinese Journal of Health Statistics
基金 国家自然基金(81172771) 宁波大学研究生科研创新基金(G12JA001)
  • 相关文献

参考文献13

  • 1Johnson JW,Lebreton JM. History and use of relative importance indi- ces in organizational research. Organizational Research Methods,2004,7 (3) :238-257.
  • 2Johnson JW. A heuristic method for estimating the relative weight of predictor variables in multiple regression, multivariate behavioral re- search,2000,35 ( 1 ) : 1-19.
  • 3Chao YCE, Zhao Y, Kupper LL. Quantifying the relative importance of predictors in multiple linear regression analyses for public health stud- ies. Journal of Occupational and Environmental Hygiene, 2008,5 ( 8 ) : 519-529.
  • 4Tonidandel S ,Lebreton JM,Johnson JW. Determining the statistical signifi- cance of relative weights. Psychological Methods ,2009,14 ( 4 ) : 387-399.
  • 5Budescu DV. Dominance analysis a new approach to the problem of rel- ative importance of predictors in multiple regression. Psychological Bul- letin, 1993,114 ( 3 ) :542-551.
  • 6Azen R,Budescu DV. The dominance analysis approach for comparing predictors in multiple regression. Psychological Methods, 2003,8 ( 2 ) : 129-148.
  • 7Huo Y, Budescu DV. An extension of dominance analysis to canonical correlation analysis. Multivariate Behavioral Research, 2009,44 ( 5 ) : 688-709.
  • 8Lebreton JM, Tonidandel S. Multivariate relative importance : extending relative weight analysis to multivariate criterion spaces. Journal of Ap- plied Psychology ,2008,93 (2) :329-345.
  • 9张波,代鲁燕,黄启风,沈其君.logistic回归中自变量相对重要性的相对权重估计[J].中国卫生统计,2012,29(2):191-192. 被引量:8
  • 10Lebreton JM,Ployhart RE,Ladd RT. A Monte Carlo comparison of rel- ative importance methodologies. Organizational Research Methods, 2004,7 ( 3 ) :258-282.

二级参考文献21

  • 1张冬,陈香美,魏日胞.急性肾衰竭的流行病学研究[J].北京医学,2006,28(4):233-235. 被引量:20
  • 2Johnson JW. A heuristic method for estimating the relative weight of predictor variables in multiple regression. Multivariate Behavioral Re- search,2000,35 ( 1 ) : 1-19.
  • 3lohnson JW, LeBreton JM. History and use of relative importance indi- ces in organizational research. Organizational Research Methods, 2004, 7(3) :238-257.
  • 4LeBreton JM, Tonidandel S. Multivariate relative importance : Extending relative weight analysis to multivariate criterion spaces. Journal of Ap- plied Psychology,2008,93 (2) :329-345.
  • 5Chao YE, Zhao Y, Kupper LL, et al. Quantifying the Relative Impor- tance of Predictors in Multiple Linear Regression Analyses for Public Health Studies. Journal of Occupational and Environmental Hygiene, 2008,5 (8) :519-529.
  • 6Tonidandel S, LeBreton JM. Determining the relative importance of pre- dictors in logistic regression : An extension of relative weights analysis. Organizational Research Methods,2010,13(4) :767-781.
  • 7Menard S. Six approaches to calculating standardized logistic regression coefficients. The American Statistician ,2004,58 ( 3 ) :218-223.
  • 8Azen R, Traxel N. Using Dominance Analysis to Determine Predictor Importance in Logistic Regression. Journal of Educational and Behav- ioral Statistics,2009,34 (3) :319-347.
  • 9Darlington RB. Multiple regression in psychological research and practice[J].Psychological Bulletin,1968,(03):161-182.
  • 10Greenland S,Schlesselman J J,Criqui MH. The fallacy of employing standardized regression coefficients and correlations as measures of effect[J].American Journal of Epidemiology,1986,(02):203-208.

共引文献18

同被引文献27

  • 1谢宝国,龙立荣.优势分析方法及其应用[J].心理科学,2006,29(4):922-925. 被引量:55
  • 2JOHNSON JW. A Heuristic Method for Estimating the Relative Weight of Predictor Variables in Multiple Regression. Multivariate Behavioral Research,2000,35( 1 ) : 1-19.
  • 3CHAO YCE, ZHAO Y, KUPPER LL. Quantifying the Relative Im- portance of Predictors in Multiple Linear Regression Analyses for Public Health Studies. Journal of Occupational and Environmental Hwiene .2008_5 ( 8 ) 519-529.
  • 4BRING J. A geometric approach to compare variables in a regression model. The American Statistician, 1996,50 ( 3 ) : 57-62.
  • 5BUDESCU DV. Dominance analysis A new approach to the problem of relative importance of predictors in multiple regression. Psycholog- ical Bulletin, 1993,114 (3) : 542-551.
  • 6AZEN R, BUDESCU DV. The dominance analysis approach for comparing predictors in multiple regression. Psychological Methods, 2003,8(2) : 129-148.
  • 7HUO Y, BUDESCU DV. An Extension of Dominance Analysis to Canonical Correlation Analysis. Multivariate Behavioral Research, 2009,44(5) : 688-709.
  • 8LEBRETON JM, TONIDANDEL S. Multivariate relative impor- tance: Extending relative weight analysis to multivariate criterion spaces. Journal of Applied Psychology,2008,93 (2) : 329-345.
  • 9LEBRETON J M, PLOYHART R E, LADD R T. A Monte Carlo Comparison of Relative Importance Methodologies. Organizational Research Methods, 2004,7 ( 3 ) : 258-282.
  • 10FAN X,FELSOVALY A,SIVO SA. SAS for Monte Carlo Studies A Guide for Quantitative Researchers. SAS Publishing ,2003.

引证文献3

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部