Tell me more ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.
up vote 2 down vote favorite

I have 12 (1 year's worth) values and I want to determine the trend and represent the trend as a positive or negative figure. What is the difference in using linear regression versus the monthly percent change averaged?

share|improve this question

1 Answer

up vote 5 down vote

The monthly percentage change averaged will have the implicit assumption that the growth is exponential while a linear regression has the assumption that it is linear.

If you do it properly, the average monthly percentage change involves taking the 11th root of the product of the $1+\frac{P_i}{100}$ terms, in which case it will depend on the first and last terms only, ignoring all intermediate months.

It might be sensible if you drew a graph of your data before any numerical analysis, to see what the pattern might be.

share|improve this answer
Drawing a graph isn't going to help the solution in this case. It needs to be automated. We're looking for a programmable algorithm - ultimately, the question is simply whether average percentage change vs. linear regression is going to be a more accurate representation. – Rob Jun 23 '11 at 15:07

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.