I'm trying to see the isolated and combined effects of precipitation and three different human disturbances indexes are having an effect on the growth of a cactus. I have a gradient of eight different values of precipitation and eight different values of each index (livestock grazing, wood extraction, and people pressure). The problem is I only have one value of growth per each precipitation and disturbance index, so when I run the glm it give me this:
Estimate Std. Error t value Pr(>|t|) (Intercept) -169.80595 NA NA NA PRECIP_fs 0.26926 NA NA NA PPI_fs 24.27342 NA NA NA GPI_fs -17.30260 NA NA NA WEI_fs -8.59929 NA NA NA PRECIP_fs:PPI_fs -0.03989 NA NA NA PRECIP_fs:GPI_fs 0.02980 NA NA NA PRECIP_fs:WEI_fs 0.01346 NA NA NA
Next, when I do the selection of the models by akaike it gives me this:
--- Model selection table (Int) GPI_fs PPI_fs PRE_fs WEI_fs GPI_fs:PRE_fs PPI_fs:PRE_fs PRE_fs:WEI_fs adjR^2 df logLik AICc delta weight 128 -169.800 -17.300 24.2700 0.26930 -8.599000 0.0298000 -0.039890 0.013460 1.0010 9 218.520 -509.0 0.00 1 64 -97.160 -9.826 11.8400 0.15820 0.009629 0.0171900 -0.019400 0.7505 8 -23.166 -81.7 427.37 0 112 -70.380 0.967 4.0220 0.09459 -1.326000 -0.006018 0.002076 0.5005 8 -25.936 -76.1 432.91 0 96 -21.670 1.025 0.2026 0.03506 2.120000 -0.0008887 -0.003303 0.3940 8 -26.708 -74.6 434.46 0 1 9.688 0.0000 2 -28.710 63.8 572.86 0 5 27.610 -0.02481 0.1931 3 -27.852 67.7 576.74 0 Models ranked by AICc(x)
Is it ok to use this selection of models when the original glm gave me only "NA" or not? If this is not correct, how do I fix it?
I don't understand what you model is nor do i understand how you selected your model. I would probably recommend using adaptive lasso to build your model. I do suugest that you see this website: https://www4.stat.ncsu.edu/~boos/var.select/lasso.adaptive.html
And perhaps this text: https://faculty.marshall.usc.edu/gareth-james/ISL/ISLR%20Seventh%20Printing.pdf
Please notice this property of adaptive lasso: https://www.google.com/search?q=oracle+property+addaptive+lasso&oq=oracle+property+addaptive+lasso&aqs=chrome..69i57j0.28647j0j4&sourceid=chrome&ie=UTF-8
this work is easiest to do in R, free open sourse and very powerful, an introduction is at: http://sgpwe.izt.uam.mx/files/users/uami/gma/R_for_dummies.pdf
another place to get some useful R Code is: https://www.google.com/search?ei=bb3AXpvYING0tAaY44CgBg&q=jared+lander+r+for+everyone+sexond+ed.&oq=jared+lander+r+for+everyone+sexond+ed.&gs_lcp=CgZwc3ktYWIQAzoCCAA6BggAEBYQHjoFCCEQoAE6BQghEKsCOgcIIRAKEKABUPOPAljR4QJgquUCaABwAHgAgAGIAYgBvgmSAQM2LjaYAQCgAQGqAQdnd3Mtd2l6&sclient=psy-ab&ved=0ahUKEwjbwsLTh7rpAhVRGs0KHZgxAGQQ4dUDCAw&uact=5
And our work is attached. Best,
David Booth
Ette Etuk then it is not a problem that the original GLM gave me only "NA"?
NO there is something if you get all NAs. Find it before you do anything else.
D. Booth
- Badges
- Science topic
- Similar topics
- Indexes