Search results

  1. J

    Logistic regression with partly aggregated data

    @Mamaho, If you're still around, you might try the following. Create a variable z that takes the value 0 if x is below the detection limit, and 1 otherwise; and assign a value of 0 (or any numerical value at all, it won't matter) to x if x is below the detection limit. Then run the following...
  2. J

    need help with statistical analysis

    Nominal dependent variables can be cumbersome. The book that helped me out a lot when I was first confronted with nominal DVs was Introduction to Categorical Analysis by Alan Agresti. I think you'll find the book well worth the investment.
  3. J

    Critical F value for testing Full vs Reduced models.

    For the F-statistic, the numerator degrees of freedom is the difference between the number of parameters in the full model and the number of parameters in the reduced model, and the denominator degrees of freedom is n - p_f, where n is the sample size and p_f is the number of parameters...
  4. J

    Averages - how does this happen?

    Simpson's paradox
  5. J

    Which test is appropriate for correlating categorical and continuous variables?

    I would calculate odds ratios from logistic regression.
  6. J

    Caclulating Sample Size

    That qualtrics online calculator is inappropriate for a two-sample t-test. Accurate calculation of the required sample size for a t-test employs iterative methods and so really necessitates using software. One (free) option is to install the statistical software program "R" (google it) and...
  7. J

    Factor Analysis

    I suspect that noetsi will want to understand what the factors represent in terms of the commodities comprising them, so he'll probably want to do factor analysis. And, yes, I think correlations of spending by individuals among commodities will lead to sensible, understandable factors. The...
  8. J

    Paired or independant t-test

    Clearly, the data were paired (observed on the same subject), so the paired version of the t-test was the correct version.
  9. J

    Pre and post- test on more then one day

    You can used a linear mixed model with animal as a random variable, and each pre-post difference as the dependent variable. I don't know what the difference is between "baseline" and "pre_1."
  10. J

    Simple Equation

    Mukund, you made a sign error. (s - p)(1 - x) = px s - sx - p + px = px sx = s - p x = 1 - p/s
  11. J

    Collapsing hazard ratio comparisons from 3 groups to 2 groups before meta-analysis

    I assume that the lines you are referring to are the survival functions. Yes, they have to separate for the variable defining the groups to be significant. But it's the hazard functions h(t), not the survival functions S(t) for the two groups that have to be proportional. The hazard function...
  12. J

    Collapsing hazard ratio comparisons from 3 groups to 2 groups before meta-analysis

    @hlsmith - The hazard rate is an instantaneous risk per unit time. An assumption of the basic Cox model is that the hazard ratio is constant with respect to time; that is, it is the same at every time t under study. Under this assumption the length of follow-up is irrelevant, because you'll...
  13. J

    Collapsing hazard ratio comparisons from 3 groups to 2 groups before meta-analysis

    @hlsmith - The follow-up times shouldn't be important, because Cox regression treats the hazard ratio as time-independent.
  14. J

    Collapsing hazard ratio comparisons from 3 groups to 2 groups before meta-analysis

    @__Oliver__ - If I understand your problem correctly, for each study (other than your own) you have HR(A vs B) and HR(B vs C), but you want HR(A vs combined B and C). I think this problem is tractable. Here's a first shot at it: Let X\Y denote the hazard ratio for X vs Y. Then for each...
  15. J

    Cohens-d coefficient with pooled standard deviations

    According to the instructions, the correct answer is the one the effect-size calculator gives.
  16. J

    Is Multivariate Analysis possible?

    Overfitting is an internet story? Who knew?!
  17. J

    Is Multivariate Analysis possible?

    There's a rule of thumb (which in my experience is a good one) that the ratio of observations to predictors should be at least 10 to avoid overfitting the data. You should, therefore, probably try to drop one predictor. I would look at the correlation matrix of the predictors. If any of them...
  18. J

    Is Multivariate Analysis possible?

    Unfortunately, I can't make sense of your post. Please translate it into English and figure out a way to format it properly.
  19. J

    ANOVA or Poisson Regression

    I'm not crazy about either ANOVA or Poisson regression for this problem. For ANOVA, theoreticaly, neither the normality nor the homoscedasticity assumptions are valid. The latter is automatically violated because you are modeling proportions, and the variance of a proportion depends on the...