Quantifying R2 bias in the presence of measurement error

被引:4
作者
Majeske, Karl D. [1 ]
Lynch-Caris, Terri [2 ]
Brelin-Fornari, Janet [2 ]
机构
[1] Oakland Univ, Sch Business Adm, Rochester, MI 48309 USA
[2] Kettering Univ, Flint, MI 48504 USA
关键词
measurement error; regression analysis; R2; bias correction; gage RR; REGRESSION; SUBJECT; MOTION; MODELS; TABLES;
D O I
10.1080/02664760902814542
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Measurement error (ME) is the difference between the true unknown value of a variable and the data assigned to that variable during the measuring process. The multiple correlation coefficient quantifies the strength of the relationship between the dependent and independent variable(s) in regression modeling. In this paper, we show that ME in the dependent variable results in a negative bias in the multiple correlation coefficient, making the relationship appear weaker than it should. The adjusted R2 provides regression modelers an unbiased estimate of the multiple correlation coefficient. However, due to the ME induced bias in the multiple correlation coefficient, the otherwise unbiased adjusted R2 under-estimates the variance explained by a regression model. This paper proposes two statistics for estimating the multiple correlation coefficient, both of which take into account the ME in the dependent variable. The first statistic uses all unbiased estimators, but may produce values outside the [0,1] interval. The second statistic requires modeling a single data set, created by including descriptive variables on the subjects used in a gage study. Based on sums of squares, the statistic has the properties of an R2: it measures the proportion of variance explained; has values restricted to the [0,1] interval; and the endpoints indicate no variance explained and all variance explained respectively. We demonstrate the methodology using data from a study of cervical spine range of motion in children.
引用
收藏
页码:667 / 677
页数:11
相关论文
共 34 条
  • [1] Adamec E., 2003, Quality Engineering, V15, P383, DOI 10.1081/QEN-120018036
  • [2] MODEL COMPARISONS AND R2
    ANDERSONSPRECHER, R
    [J]. AMERICAN STATISTICIAN, 1994, 48 (02) : 113 - 117
  • [3] [Anonymous], MEAS SYST AN
  • [4] [Anonymous], 2003, IMPLEMENTING 6 SIGMA
  • [5] The accuracy of measuring the kinematics of rising from a chair with accelerometers and gyroscopes
    Boonstra, MC
    van der Slikke, RMA
    Keijsers, NLW
    van Lummel, RC
    Malefijt, MCD
    Verdonschot, N
    [J]. JOURNAL OF BIOMECHANICS, 2006, 39 (02) : 354 - 358
  • [6] A review of methods for measurement systems capability analysis
    Burdick, RK
    Borror, CM
    Montgomery, DC
    [J]. JOURNAL OF QUALITY TECHNOLOGY, 2003, 35 (04) : 342 - 354
  • [7] Cheng CL, 1999, STAT REGRESSION MEAS
  • [8] Prediction intervals in linear regression taking into account errors on both axes
    del Río, FJ
    Riu, J
    Rius, FX
    [J]. JOURNAL OF CHEMOMETRICS, 2001, 15 (10) : 773 - 788
  • [9] System and modelling errors in motion analysis: Implications for the measurement of the elbow angle in cricket bowling
    Elliott, Bruce C.
    Alderson, Jacqueline A.
    Denver, Eliot R.
    [J]. JOURNAL OF BIOMECHANICS, 2007, 40 (12) : 2679 - 2685
  • [10] Fung KY, 1999, ENVIRONMETRICS, V10, P213, DOI 10.1002/(SICI)1099-095X(199903/04)10:2<213::AID-ENV349>3.0.CO