I understand that Zipf's Rank-size distribution would allow me to estimate the sales of a book given the amazon sales rank. How can I fit the distribution without knowing book sales leading to a rank. Sales Rank is calculated with time since last sale in mind, a decay function.

| cite | improve this question | | | | |
  • 1
    $\begingroup$ If you are asking if you can fit a model without any data, the answer is no. Also, I have noticed that only a few sales can cause large changes in the Amazon rank on any given day. So you might want to average ranks across days. Most Authors only get sales data quarterly or semi-annually, so you might want to average the Amazon ranking over one of those periods of time. You probably could find authors willing to cooperate with you by providing sales figures, but perhaps not authors from the very high sales volume books. Good luck. $\endgroup$ – Joel W. Jul 10 '12 at 0:26
  • $\begingroup$ Thank you. The goal is to build a regional tourism predictor based on the sales of travel guides, maps, etc of my target region. $\endgroup$ – Roland Kofler Jul 17 '12 at 14:40

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.