Results 1 to 7 of 7

Thread: Extracting out the trendline from a log curve fit

  1. #1

    Thread Starter
    New Member
    Join Date
    Jan 2004
    Posts
    9

    Exclamation Extracting out the trendline from a log curve fit

    Does anyone know how, given a data set, I can pull out the equation of the trendline without having to plot the chart and visually type in the code?
    I have to perform this and build up equations for best fits for around 500 data arrays - so am in great need for an automated process. I dont believe the data anlaysis regression tool would also be suited (unless there is a way of accesing this from VBA which I am not aware of).

    I would appreciate your help.

    Many thanks,
    Tanveer.

  2. #2
    Hyperactive Member
    Join Date
    May 2004
    Location
    Right here
    Posts
    275
    What's the reason you can't just do it in Excel and use the built-in regression analysis function?

  3. #3

    Thread Starter
    New Member
    Join Date
    Jan 2004
    Posts
    9
    Hi,
    I dont know how this is possible? which function are you referring to? Using data analysis tool pack, it creates a matrix - and I dont think its a good idea to generate matrix data for 500 names?
    Is this do-able in VBA? any sources of reference will be appreciated.

    Thanks

  4. #4
    Hyperactive Member
    Join Date
    May 2004
    Location
    Right here
    Posts
    275
    I could be misunderstanding the type of data you're dealing with here - I thought the data was the type with x-y coordinates that you could just plot on a standard pair of axis, with a relationship existing between x and y

    i.e. y = some function of x

    If so then excel can find the equations for such graphs.......if you're dealing with a different sort of data then sorry but I don't know how you'd do it.

  5. #5

    Thread Starter
    New Member
    Join Date
    Jan 2004
    Posts
    9
    Yes I have 500 sets of X-Y data, and for each data set I need to extract out the function of the polynomial fit along with the R2 value.
    I need this to be done without generating excessive data in the form that the regression tool pack gives.

    Does this help clarify the problem I face?

    Cheers.

  6. #6
    Hyperactive Member
    Join Date
    May 2004
    Location
    Right here
    Posts
    275
    Can you post a download link to some (or all) of the data in either an Excel or ASCII format so I can have an attempt at doing it in Excel?

    Or is it classified information?

  7. #7
    Frenzied Member yrwyddfa's Avatar
    Join Date
    Aug 2001
    Location
    England
    Posts
    1,253

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  



Click Here to Expand Forum to Full Width