ESTIMATION METHODS FOR SIMPLE LINEAR REGRESSION WITH MEASUREMENT ERROR: A REAL DATA APPLICATION

DAĞALP R., KARABULUT İ., Ozturk F.

COMMUNICATIONS FACULTY OF SCIENCES UNIVERSITY OF ANKARA-SERIES A1 MATHEMATICS AND STATISTICS, cilt.66, sa.2, ss.311-322, 2017 (ESCI) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 66 Sayı: 2
  • Basım Tarihi: 2017
  • Doi Numarası: 10.1501/commua1_0000000821
  • Dergi Adı: COMMUNICATIONS FACULTY OF SCIENCES UNIVERSITY OF ANKARA-SERIES A1 MATHEMATICS AND STATISTICS
  • Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.311-322
  • Anahtar Kelimeler: Classical measurement error model, consistent estimator, error in variables, linear regression, mass density, regression calibration, SIMEX method, M-estimation, SIMULATION-EXTRAPOLATION, MODELS
  • Ankara Üniversitesi Adresli: Evet

Özet

The classical measurement error model is discussed in the context of parameter estimation of the simple linear regression. The attenuation effect of measurement error on the parameter estimation is eliminated using the regression calibration and simulation extrapolation methods. The mass density of pebbles population is investigated as a real data application. The mass and volume of a pebble are regarded an error-free and error-prone variables, respectively. The population mass density is considered to be the slope parameter of the simple linear regression without intercept.