中文摘要：

混合总体最小二乘（mixedLS-TLS）合理地顾及了系数矩阵和观测向量误差，却没有考虑数据中可能存在的粗差。利用IGGII方案，提出一种稳健的混合总体最小二乘方法，并通过平面拟合进行验证。结合模拟数据和真实数据，通过与最小二乘（LS）、总体最小二乘（TLS）和混合总体最小二乘的对比分析，证实这种稳健混合总体最小二乘的平面拟合结果最为可靠。

英文摘要：

Errors in coefficient matrix and observation vectors can be reasonably taken into account in mixed LS-TLS. However, in such a solution, gross errors in the observation data are ignored. To solve this problem, a robust method of mixed LS-TLS is proposed based on the IGGII scheme. A comparative evaluation with least squares, total least square,s and mixed LS-TLS was conducted for plane fitting with a set of simulations and a set of real-life data. The results confirm that the proposed method is more reliable than the others.