A NEW METHOD FOR ESTABLISHING REGRESSION MODEL
Xu Shuang’an;Yao Yibin;Kong Jian; and Gong Peipei
School of Geodesy and Geomatics,Wuhan University, Wuhan 430079
Abstract The regression method is used to study the related but not determined relations between variables, which is widely used in the field of deformation monitoring data processing and analyzing.The method based on classical leastsquares under the indirect adjustment model or on singular value decomposition under the overall leastsquares criterion for solving vegression parameters has some limitations in practical applications,it may weaken the statistical significance of the regression model and the significance test even will fail .A new method is proposed that is to establish the approximate regression equation by the traditional method first,then amendment the regression model by the Total LeastSquares. The feasibility and correctness of the new method are verified by the simulation data and measured real deformation data and the prediction accuracy can be improved.
Key words :
regression model
classical least squares
total least-square
significance test
forecast and analysis
Received: 01 January 1900
Corresponding Authors:
Xu Shuang’an
Cite this article:
Xu Shuang’an,Yao Yibin,Kong Jian et al. A NEW METHOD FOR ESTABLISHING REGRESSION MODEL[J]. , 2010, 30(4): 117-121.
Xu Shuang’an,Yao Yibin,Kong Jian et al. A NEW METHOD FOR ESTABLISHING REGRESSION MODEL[J]. jgg, 2010, 30(4): 117-121.
URL:
http://www.jgg09.com/EN/ OR http://www.jgg09.com/EN/Y2010/V30/I4/117
[1]
YAN Guangfeng,CEN Minyi. Optimum Linear Regression Model Selection Algorithm with Lagrange Multipliers [J]. jgg, 2021, 41(11): 1111-1117.
[2]
XIE Jian,LONG Sichun. Classic Least Squares Method to the Weighted EIV Model [J]. jgg, 2019, 39(5): 544-546.
[3]
DENG Xingsheng,HUANG Xiaopeng,PENG Sichun. Weighted Total Least-Squares Adjustment with Partial Prior Random Parameter [J]. jgg, 2018, 38(9): 968-973.
[4]
WANG Zhu’an,CHEN Yi,MAO Pengyu. The Application of the Posterior Estimation on Weighted Total Least-Squares to Three Dimensional-Datum Transformation [J]. jgg, 2018, 38(2): 216-220.
[5]
WU Kaiyan,ZHANG Xianzhou,MA Long,LUO Lie,ZHANG Zheng,YU Qiao. A Multivariable Grey Deformation Analysis Model Based on Multivariate Total Least-Squares Optimization [J]. jgg, 2016, 36(8): 682-685.
[6]
HU Chuan,CHEN Yi,ZHU Weidong,QIAN Chengjun. Comparisons of Total Least Squares and Least Squares for Fitting Spatial Lines [J]. jgg, 2015, 35(4): 689-692.
[7]
YAN Wei,NIU Anfu. The Fractal Characters of the Low Frequency Residual’s Space
Distribution of Continuously Monitoring GPS Sites [J]. jgg, 2015, 35(3): 401-405.
[8]
Lu Chenlong,Kuang Cuilin,Dai Wujiao,Lu Jun. EXTRACTING SEASONAL SIGNALS FROM CONTINUOUS GPS TIME
SERIES BASED ON VARYING-COEFFICIENT REGRESSION MODELS [J]. jgg, 2014, 34(5): 94-100.
[9]
Zhong Chonghao,Yao Yibin,Liu Qiang,Zhang Liang. ITERATIVE METHOD FOR THE WEIGHTED TOTAL LEASTSQUARES [J]. jgg, 2014, 34(4): 153-156.
[10]
Hong Min,Shao Desheng,Wang Lingli,Zhang Yong,Fu Yunwen,Ma Lin,Wang Yan,Li Chunguang. USING SPATIAL CORRELATION BETWEEN CONTINUOUS GNSS TIME
SERIES TO ACHIEVE REGIONAL DEFORMATION ANOMALIES [J]. jgg, 2014, 34(2): 175-178.
[11]
Zhao Qing,Zhao Changsheng,Zhu Yu. EFFECT OF DIFFERENT AGING FACTORS ON DISPLACEMENT [J]. jgg, 2013, 33(3): 56-58.
[12]
Yang Shiping, Fan Dongming, Long Yuchun. THREE-DIMENSIONAL COORDINATION TRANSFORMATION
ADAPTED TO ARBITRARY ROTATION ANGLE BASED
ON TOTAL LEAST SQUARES METHOD [J]. jgg, 2013, 33(2): 114-119.
[13]
Hu Chuan ;and Chen Yi;. PARAMETERS ESTIMATION OF AUTOREGRESSION WITH STRUCTURED TOTAL LEAST SQUARES [J]. , 2013, 33(1): 45-47.
[14]
Yang Shiping ;Fan Dongming ;and Long Yuchun . AN IMPROVED WEIGHTED TOTAL LEAST SQUARES ALGORITHM [J]. , 2013, 33(1): 48-52.
[15]
Yan Feng;and Yao Yibin. SHORT-TERM PREDICTION METHODS AND REALIZATION OF EARTH ROTATION PARAMETERS [J]. , 2012, 32(4): 71-75.