I'm running data analysis for an online marketplace. I want to determine the influence of the time a perishable good (say a concert ticket) is online versus the probability of a sale.

I have made a plot showing that 'time online' is an important factor: items online for 2 days have 1.5x the probability of selling compared to 3 hours online. In what way can I prove this statistically?

I have looked into probit models. Is that the right way to go?

  • 1
    $\begingroup$ You can try logit or probit models for this. Based on the regression coefficients, you can find the actual impact of time on probability of selling. $\endgroup$
    – steadyfish
    Commented Jul 23, 2013 at 13:29


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.