Regression Statistics in Python

Regression is an optimization method for adjusting parameter values so that a correlation best fits data. Parameter uncertainty and the predicted uncertainty is important for qualifying the confidence in the solution. This tutorial shows how to perform a statistical analysis with Python for both linear and nonlinear regression. See apmonitor.com/che263/index.php... for source code.

[@robertocabiecesdiaz3775]

Please could you tell me the reference book you have used to estimate the confidence and the prediction. I would really appreciate it

[@apm]

Here is a reference for additional information: Chatterjee, S., Hadi, A. S. and Price, B. (2000). Regression Analysis by Example. 3rd

[@maayanchik1]

Hi there, Great video, explanation and code!
Is there a way to incorporate analytical errors on the actual data points into the 95% confidence intervals and prediction bands?
Also- is there a justification to do so if the prediction bands are wider the the largest analytical error?

[@apm]

I suppose that you could include analytical errors but the symbolic solution would be very large and likely irreducible because the data is still stochastic. You could give it a try with a tool like Sympy.

[@frankvalenti8350]

I have a question, if i am importing a spread sheet into python, and the x axis in the spread sheet is formatted to month/day/year how to i change those values to numbers so i can curve fit?

[@apm]

Change the cell type from date to number

[@mirakaddour2753]

thanks alot