Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote -1 down vote favorite

I'm trying to extend this graph via the provided trendline formula. I'm inserting the formula into the next row and trying to assign X to be the date value, but it doesn't appear to be working. Do I need to apply a function to the date value in order for it to work? Basically I'm trying to predict what June 17th's downloads will be based on the formula.

Anyone know how do to this?

enter image description here

share|improve this question
If you give the exact value of the fitted line at the endpoints of you graph you supplied that would make this much easier. On another note, from eyeballing the regression line and the observed values, the independent (and normally distributed) errors assumption is almost certainly violated here if you're trying to do inference about $\beta$. – Macro Jul 21 '11 at 23:42

1 Answer

up vote 2 down vote

$X$ might represent some time ticks starting from $1$ or whatever integer value the Excel assigns to it. Since your downloads are nonnegative, it is not the best way to predict the trend without prior transformation of the response variable, probably some logistic curve would fit it better.

In any case if you still want to do a linear regression model in Excel, you may transform you time points to integers by letting them to start from $1, 2, \dots, T$ and to do the regression using build in formulas (or the analysis tool pack add-in). Probably this link or the MS link will guide you. I personally as many others on this site would recommend to use either gretl or R.

share|improve this answer

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.