Re: [R-sig-eco] Binning
In addition to Roman's suggest of the Biven's book, the first few chapters of this other book discuss trade-offs in selecting binning categories, and has algorithms for estimating optimal bin distributions. Linhart, H. and W. Zucchini (1986). Model Selection. New York, John Wiley and Sons. -Brian Inouye scttchamberla...@gmail.com wrote: Dear R ecologists, We are trying to figure out the correct way to decide the width and number of bins for our analysis. We have a meta-anlaysis in which effect sizes are collected from the equator to the poles. We want to run a simulation that picks a random subset of data points from bins along the x-axis (latitude), do a meta-analysis, and repeat N times. Then compare observed meta-analysis results to that of the simulation set of results. It seems in my reading thus far that picking bin widths and number of bins is largely arbitrary. Is this correct? Number of observations is very large at the temperate latitudes (30-40 degrees) and very sparse in the tails (towards the equator and poles). We are using the absolute value of latitude, so there are no negative numbers. Is it okay to use different bin widths along the latitude axis? If so, we could create bins with more equitable number of data points by increasing the bin width from 30-40 degrees towards the equator and poles. Thanks in advance, Scott Chamberlain Rice University, EEB Dept. [[alternative HTML version deleted]] ___ R-sig-ecology mailing list R-sig-ecology@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
[R-sig-eco] nested factor for which i would like a parameter estimate
Hello all, I am trying to test whether sound diversity predicts bird diversity. The question i have concerns how to deal with a factor that could be treated either as a random or fixed factor. Response: bird_entropy (continuous) Fixed factors: landtype (factor), sound_entropy (continuous), AM/PM (factor) Random factor: Plot The problematic factor is AM/PM. We have 29 total sampling plots, each of which is measured for sound_diversity at five subplots, once in the AM (dawn) and again in the PM (dusk), for a total 10 measurements per plot. (Each plot has only one, overall measure of bird_diversity). On the one hand, AMPM is nested within plot, but on the other hand, we would like to estimate a parameter for AMPM, since we expect different suites of sound producers (not just birds) at different times of the day. However, it's reasonable to expect temporal correlation between AM and PM. The first model seems uncontroversial to me (these are post-model-selection). Mod.lme1 - lme(bird_entropy ~ sound_entropy * landuse, random = ~ 1 | plot / AMPM, data=Bird) But i'm curious to know if this second model is reasonable, and if so, how would I code the plot variable? Mod.lme2 - lme(bird_entropy ~ sound_entropy * landuse + AMPM, random = ~ 1 | plot, data=Bird) Thanks all, Doug ___ R-sig-ecology mailing list R-sig-ecology@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology