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.

I would like to create a function to determine annual chance of flooding given a specific ground elevation. The data I have available to me are water surface elevations at 5 specific recurrence intervals (10yr, 25yr, 50yr, 100yr, and 500yr). My initial approach was to run a linear regression using a log10 of the water surface values as the y axis and a log10 value for each interval. This did not yield very reliable results. Since then I have began exploring a piecewise linear interpolation solution. y = f(x) as it is described in the scipy interp1d. I can not seem to get this to work either.

I have seen this solution in Excel using Trend and some other functions, but I will need to run this over well over 1 million records. Again the idea is if you have a ground elevation of 556.345, where does it best fit between 5 intervals. How can I do this?

share|improve this question
Does "did not yield very reliable results" mean that you expect a program to predict the future? – Jochen Ritzel Jan 26 '11 at 2:28
1  
^^^ The program should more or less correctly predict the known past. – 9000 Jan 26 '11 at 2:32
I think you're looking for a method rather than Python code. – Rafe Kettler Jan 26 '11 at 3:15

migrated from stackoverflow.com Jul 16 '12 at 1:54

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

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