F ÖZTÜRK

4853

A discrete shrinking method as alternative to least squares

F or the classical iinear regression problem , a num ber of estim ators alternative to least squares have been proposed for situations in w hich m ulticollinearity is a problem . This paper investigates m ean square error properties of biased regression estim ators and presents a proce- dure for obtaining im proved estim ators.
Keywords:

regression, squares ulticollinearity,

PDF

___

  • Communications, Series A1:Mathematics and Statistics
Communications Faculty of Sciences University of Ankara Series A1 Mathematics and Statistics-Cover
  • ISSN: 1303-5991
  • Yayın Aralığı: Yılda 4 Sayı
  • Başlangıç: 1948
  • Yayıncı: Ankara Üniversitesi
Arşiv
Sayıdaki Diğer Makaleler

P. D. SRIVASTAVA

Some Common Fixed Point Theorems İn Uniform SpaceS

M. S KHAN

On truncated poisson queue with balking, reneging and heterogenity

M. EL ATA

A note on matrix transformations of some generalized sequence spaces into semiperiodic sequence space

S. M SIRAJUDEEN

M. A BELTAGY

Matrix transformations on Cesáro difference sequence spaces

C. ORHAN

On the minimal index of the generalized minimal ruled sufaces in the euclidean n-space En

N KURUOĞLU

On finiteness of homological dimension of generalized homology modules of finite-dimensional CW-complexes

Şahin KOÇAK

Lata Mishra SHANTI

A criterion for restricted ideal sheaves and on regular covering spaces

Cengiz ULUÇAY