glm

  1. J

    Maximum likelihood estimation and GLMs - can you help me refresh my rusty memory?

    Hi all, I was wondering if you can help me refresh my rusty memory on maximum likelihood estimation. I think I remember the basic concept from my university courses in a previous life. Banal example: we want to fit a normal distribution to the observations 3,4,5, then N(4,1) is the best...
  2. R

    Data analysis with a GEE, is my method valid?

    Hi everyone, I’ve been doing some statistical analyses in R on some data. It’s for use in a manuscript I’m hoping to get published in a biological journal. Unfortunately, the tests I ended up having to run are kind of at the limit of my understanding, so I was hoping that I could run through...
  3. M

    GLM with non-parametric post hoc testing?

    Hi guys, I have a question regarding the appropriate use of comparisons for independent samples (3 factor levels), please. Overall sample size is N=546, subsamples: 218 or 228 or 100), convenience sampling, stratified. I use ANOVA with post hoc Tukey, if Levene indicates variance...
  4. H

    Comparing count data and cultivars in R

    Hi, I'm trying to analyse an experiment with this setup: A plant species with 16 different cultivars of 4-5 plants per cultivar (completely randomised within greenhouse, no blocks) An insect species that was allowed to spread freely for 4 days on the plants. The insect number per plant was...
  5. H

    How to analyse deviance (GLM in R)

    Hi! This might be quite basic, but how do I analyse the fit of my GLM from the deviance? In the summary of my model, I get a deviance of 140.1 (df.resid = 52). Can I tell from these numbers, if the fit is acceptable? Thanks in advance for any replies!:tup:
  6. H

    Fit of generalized linear model (Poisson distribution)

    Hi guys Can anyone tell us how to evaluate the fit of our generalized linear model with a poisson distribution? We can't really tell if the model is a good fit or not. Do you use the deviance to answer this question? If so, what does it tell us in the following example? Thank you in advance...
  7. W

    Which statistical analyses do I need to use?

    Hello everyone! :wave: I'm having some trouble resolving two assignments with SPSS. First one is that I need to analyse if there's a difference between poor and rich European countries (using a GDP per capita index variable) and link it with thinking that the environment is the most important...
  8. S

    Constant negative fitted values...am I missing something?

    Hello all, I'm attempting to fit a model where y variable is a variety of $/ha/year figures (all positive) ranging between 0.01 and 2520. The output of this should always have positive fitted values (none of these values should ever be below 0), and yet I get constant negative fitted values...
  9. S

    In a negative binomial GLM or GLMM what does theta stand for?

    When using a GLM or GLMM with a negative binomial distribution in R it is usually necessary to set the value of theta in the model. But what does theta actually stand for? And how do I caluclate it? I have been able to get around this for now by setting my models to calculate theta for me...
  10. P

    Bycatch of dolphins data, zero inflated and under-dispersed - what next?

    I am investigating the factors that influence the bycatch of dolphins using a poisson GLM. My response variable is bycatch rate per unit effort and varies from 0 to 0.125. However, my response is very zero-inflated (2304 of 2436 observations are zero). I have three response variables (two...
  11. E

    Generalized Linear Model and fixed effects

    I want to estimate a model with a fractional outcome variable following Papke & Wooldridge (2002). I run glm dep_var independent_var, family(binomial) link(logit) robust, right? How can I add a three level fixed effects? My approach until now was to use egen new_var = group(var1 var2 var3)...
  12. P

    Dispersion parameter

    I have the understanding that the dispersion parameter, \phi, in generalised linear models needs to be known for deviance to meaningful or otherwise it can be estimated from the model, but no analysis of deviance can be carried out. Why is it then that in binomial and poisson models in R/S+...
  13. L

    How to best combine 3 repeated experiments

    Hi there, I would appreciate some expert advice on how to best combine 3 replicated experiments into one analysis. I’m trying to check if a treatment effects growth of a plant Lemna minor. I have a highly controlled environment, but because of a space limitations were only able to use 3...
  14. T

    Which kind of general linear model?

    Hello statisticians, Let me introduce myself. I am a 19 year old student Applied Economic Sciences at the University of Antwerp (Belgium). We are given a task for the course 'regression and anova' consisting of 5 questions. The first four questions were no problem but I'm stuck at the last...
  15. S

    problems with Analysis Of Variance of unbalanced non parametric data

    Hello fellow R users :wave: I hope someone can help me solve this problem. I've been looking for a solution all day. I have a proportional response (% cover) variable. I have 2 explanatory factors, both with 3 or more levels: quadrats (of which there are many) and year (of which there are...
  16. M

    SPSS v21 - MANCOVA post-hoc test - post-hoc box grayed out

    Hi everyone, I'm looking to run a Tukey post-hoc test in GLM-->Multivariate with covariates (MANCOVA). When I add covariates I can no longer select "post-hoc" - the box is grayed out. Also, I can't click "compare main effects" in the options tab. Why is this? I have seen a thread...
  17. P

    Which statistical test? GEE?

    Hello! I'm currently playing which my data and am unsure about the statistical test to use. I have MRI data from 25 patients. I have 4 (predetermined) lesion types and a control area from which I obtained MRI values. Not all patients have all lesion types, some patients have several of the...
  18. J

    Statictical suggestion regarding DOE and GLM for the pharmacutical related problem

    We performed a DOE to study the relationship between simulated intestinal fluid (SIF) components and solubility of drugs. The DOE is composed of 7 factors (representing the components of SIF) and 2 levels for each drug. And we have done several drugs with the DOE. Now with the DOE analysis, we...
  19. A

    can not figure out simple question, please help

    hi everyone! I have the following question: while running univariate GLM, I have encountered the situation when mean differences between groups are the same, but in one test they reach statistical significance, whereas in other not. Probably the reason is that in one case std. deviations are...
  20. M

    Problems with S+ and nested GLM models

    Hi I was wondering if someone might be able to help. My department has just changed statistic programs to S+ and I'm trying to run a multi-factorial GLM with one nested factor (design below). What was simple task in our old software has stumped everyone in my department. Does anyone know how...