Search results

  1. K

    Exact Poisson CI

    Hi. This is given as the "exact" CI for a Poisson rate in many places. k is the observed number, mu is the true rate. My problem is the different df at each end. When alpha gets large and tends to 100% you would expect the limits to converge on k. They don't. Is there a real "exact" CI for...
  2. K

    Extract matrix from specified place in a data fram

    Hi folks. Is there a quick way to get a matrix with the data from, say, (2, 5) to (15, 20) in a given data frame? Cheers, kat
  3. K

    P values and patents

    I have just got my first job involving a patent. The client is hoping to enhance their chances in the patent office with some stats results. Is there anything anybody can tell me about the presentation style most likely to impress them? Perhaps p values? fancy charts? citations? or would it be a...
  4. K

    Regression and voter fraud

    A useful video for any teachers, with an unexpected artifact.
  5. K

    Half distance analog for half life

    Hi folks. Is there a recognized term for the distance needed for the level of something to drop to one half? For example, the distance down a stream for a contaminant to drop to half that at its source? Thanks, kat
  6. K

    Cherry picking?

    From a paper - "When analyses were conducted to compare total plate coverage across the three sites (A vs. B vs. C) the observed differences were not significant (p > 0.1). However, when sites A and B were grouped to compare the impact (site C) vs. reference sites it became apparent that...
  7. K

    Piecewise regression

    Bats tend to be active near hedgerows and the activity drops off as they move into adjacent pasture. The problem is to determine at what distance the activity can be considered zero. I have the activity levels at a series of scattered monitoring stations at various distances away from the...
  8. K

    Reference for 1-exp(-t/T)

    Hi. I'm looking for a quotable reference that looks something like Pr(at least one occurrence in time t | average waiting time = T) = 1-exp(-t/T) for events happening at random. Everywhere I look I find rate version 1-exp(-lambda.t) which is identical, but not the version I want. Any clues...
  9. K

    Two way anova and Bonferroni

    After emphasizing again and again to students the problems with multiple p values and possible ways of dealing with them, one asked me why we didn't use Bonferroni on the two (or three) p values in a standard two way anova table. I don't know. Or should we, but nobody does? Or do some people? kat