+ Reply to Thread
Results 1 to 4 of 4

Thread: bayes for generating new data

  1. #1
    Points: 4,588, Level: 43
    Level completed: 19%, Points required for next Level: 162

    Posts
    30
    Thanks
    6
    Thanked 0 Times in 0 Posts

    bayes for generating new data




    I am estimating a tree inventory for a city. I have already measured the heights and identified the species for about 1000 trees in some areas of the city and I want to estimate the remaining species composition based on the collected data. There are about 150 different species. I have heights and locations for the unmeasured trees from using remote sensing techiniques but I just need to populate these unmeasured trees with species estimates, preferably taking into account the height to predict the species.
    I would like to use some kind of probability based method for this such as Bayes. Is this possible?

    So to give an unmeasured tree a species I need a method that looks at the height and uses the measured height and species relationship to predict the species.

  2. #2
    TS Contributor
    Points: 14,811, Level: 78
    Level completed: 91%, Points required for next Level: 39
    Miner's Avatar
    Location
    Greater Milwaukee area
    Posts
    1,171
    Thanks
    34
    Thanked 405 Times in 363 Posts

    Re: bayes for generating new data

    This sounds like an application for K-means cluster analysis.

  3. The Following User Says Thank You to Miner For This Useful Post:

    andyspeak (03-02-2017)

  4. #3
    Omega Contributor
    Points: 38,432, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,006
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: bayes for generating new data

    Is this a very crude example of what you would like to do: look at height to predict species. If that is the extent you could create cut-offs for heights and use the simple bayes theorem.
    If you want to look at a bunch of variable at once, I would create a poly-nominal logistic regression model. Though, I am sure you could do this as well using bayes, but I am not overtly familiar with those approaches beyond Bayesian Networks.
    Stop cowardice, ban guns!

  5. The Following User Says Thank You to hlsmith For This Useful Post:

    andyspeak (03-02-2017)

  6. #4
    Points: 4,588, Level: 43
    Level completed: 19%, Points required for next Level: 162

    Posts
    30
    Thanks
    6
    Thanked 0 Times in 0 Posts

    Re: bayes for generating new data


    Thanks. Will give those a try

+ Reply to Thread

           




Tags for this Thread

Posting Permissions

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






Advertise on Talk Stats