arrow
Volume 13, Issue 4
Confidence ellipsoids for the primary regression coefficients in m- equation seemingly unrelated regression models

Qingli Pan and Chuanlin Zhang

J. Info. Comput. Sci. , 13 (2018), pp. 269-282.

Export citation
  • Abstract
For a m-equation seemingly unrelated regression(SUR) model, this paper derives two basic confidence ellipsoids(CEs) respectively based on the two-stage estimation and maximum likelihood estimation(MLE), and corrects the two CEs using the Bartlett correction method, resulting in four new CEs. In the meantime via using the partition matrix, we derive a new matrix-derivative-based formulation of Fisher's information matrix for calculating the maximum likelihood estimator of the m-equation SUR model. By Monte Carlo simulation, the coverage probabilities and average volumetric characteristics of CEs are compared under different sample values and different correlation coefficients. Moreover, it is proved that the CE based on the second bartlett correction method performs better even in the case of small samples. Finally, we apply these CEs to the actual data for analysis. The CEs of the SUR model with multiple equations are found to be more accurate than the case with only two equations.
  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JICS-13-269, author = {Qingli Pan and Chuanlin Zhang}, title = {Confidence ellipsoids for the primary regression coefficients in m- equation seemingly unrelated regression models}, journal = {Journal of Information and Computing Science}, year = {2024}, volume = {13}, number = {4}, pages = {269--282}, abstract = { For a m-equation seemingly unrelated regression(SUR) model, this paper derives two basic confidence ellipsoids(CEs) respectively based on the two-stage estimation and maximum likelihood estimation(MLE), and corrects the two CEs using the Bartlett correction method, resulting in four new CEs. In the meantime via using the partition matrix, we derive a new matrix-derivative-based formulation of Fisher's information matrix for calculating the maximum likelihood estimator of the m-equation SUR model. By Monte Carlo simulation, the coverage probabilities and average volumetric characteristics of CEs are compared under different sample values and different correlation coefficients. Moreover, it is proved that the CE based on the second bartlett correction method performs better even in the case of small samples. Finally, we apply these CEs to the actual data for analysis. The CEs of the SUR model with multiple equations are found to be more accurate than the case with only two equations. }, issn = {1746-7659}, doi = {https://doi.org/}, url = {http://global-sci.org/intro/article_detail/jics/22436.html} }
TY - JOUR T1 - Confidence ellipsoids for the primary regression coefficients in m- equation seemingly unrelated regression models AU - Qingli Pan and Chuanlin Zhang JO - Journal of Information and Computing Science VL - 4 SP - 269 EP - 282 PY - 2024 DA - 2024/01 SN - 13 DO - http://doi.org/ UR - https://global-sci.org/intro/article_detail/jics/22436.html KW - Keywords:Seemingly unrelated regression, Confidence ellipsoids, Bartlett correction, Maximum likelihood estimation. AB - For a m-equation seemingly unrelated regression(SUR) model, this paper derives two basic confidence ellipsoids(CEs) respectively based on the two-stage estimation and maximum likelihood estimation(MLE), and corrects the two CEs using the Bartlett correction method, resulting in four new CEs. In the meantime via using the partition matrix, we derive a new matrix-derivative-based formulation of Fisher's information matrix for calculating the maximum likelihood estimator of the m-equation SUR model. By Monte Carlo simulation, the coverage probabilities and average volumetric characteristics of CEs are compared under different sample values and different correlation coefficients. Moreover, it is proved that the CE based on the second bartlett correction method performs better even in the case of small samples. Finally, we apply these CEs to the actual data for analysis. The CEs of the SUR model with multiple equations are found to be more accurate than the case with only two equations.
Qingli Pan and Chuanlin Zhang. (2024). Confidence ellipsoids for the primary regression coefficients in m- equation seemingly unrelated regression models. Journal of Information and Computing Science. 13 (4). 269-282. doi:
Copy to clipboard
The citation has been copied to your clipboard