Thread: Line of Best Fit

Hi quick question: Does a line of best fit HAVE to be a straight line? because I have a set of data that look like they form a logarithmic function.


see, that does not look good. Any ideas or tips?!

Thanks for your time

Yes, a line of best fit has to be a line which is just a short way of saying straight line. All lines are straight!

thank you.

Originally Posted by sakonpure6

Hi quick question: Does a line of best fit HAVE to be a straight line? because I have a set of data that look like they form a logarithmic function.


see, that does not look good. Any ideas or tips?!

Thanks for your time

Yes, your line of best fit does have to be a line. HOWEVER, since your data looks logarithmic, then a logarithmic transformation to the data would be appropriate to make your data linear.

Note that the model might be appropriate. If we let , this gives , a LINEAR function.

So what you can do is to evaluate for each of your observed x values, and then do a least squares linear regression on the two sets and . Your model will then be much more accurate, and then it can be written in terms of again.