In this paper, we propose an iterated algorithm to estimate orthogonal regression with censored data in one or two independent variables. Literature gives a procedure which aims at dealing with bivariate data with one variable censored, while the procedure we submit in this article can be applied into both bivariate and multivariate data fitting, appearing to be an improved version. Furthermore, this new procedure is simpler and much easier to generalize to higher dimensional situations. Numerical simulation demonstrates that using this procedure, there will not be significant difference between the estimated orthogonal regression line and the theoretical orthogonal regression line. |