Is numpy.polyfit with 1 degree of fitting, TLS or OLS?

Question

I have two timeseries x and y, both have the same length. Using numpy.polyfit , I fit a straight line through the data with:

numpy.polyfit(x,y,1)

Is this Total Least Squares (TLS) or Ordinary Least Squares (OLS) ? I want to fit a TLS in python, how can this be done?

Answer 1

您可以使用scipy.odr它将计算应等于 tls 的正交回归。