Recent content by andyw

  1. A

    Interactive terms

    Afternoon all, I've been running some GLMs using a stepwise backwards deletion routine (main effects, 2 way, 3 way), deleting the least significant terms between each repeat. I've found some significant interactive terms and just wanted to check that my interpretation of what these mean is...
  2. A

    GLM output

    I am conducting a series of GLMs in order to find the minimum adequate model, the largest model in which all factors are significant. In some of my models all factors are significant, except for the intercept... what does this mean?? thanks andy
  3. A

    Bonferroni correction in GLMs

    I'm running a series of General Linear Models, attempting to explain factor x with 6 other factors; individually, all 2-way and all 3-way. Due to the large number of significances which I am trying to find is it neccessary to apply a Bonferroni correction to effectively decrease the p-value...
  4. A

    Quantifying trends and patterns, which test to use?

    Attached is an image of some graphs showing the relationship between a factor which varies year on year, compared to various other factors. With many of the factors it is clear to see that there is a relation between them, however I'm unsure as to how best to show this quantitatively! Many...
  5. A


    I have two datasets, before and after the application of a treatment. The treatment is theorised to produce an increase in "factor x", and difference between the two datasets should be a positive value, however due to noise/error etc in the data some of the difference values are negative. In...