Recent content by hlsmith

  1. hlsmith

    False Discovery Rate and the BH method

    BH = ???, this will also make your post more searchable!
  2. hlsmith

    How to create a subset with a normal distribution

    You can easily partition data into subsets. Do you wish for replacement or not (meaning an observation could be selected more than once? Are you desiring for the subset to have the same distribution moments or just be a random subseT? You can do this in most any program. If a program does not...
  3. hlsmith

    High statistical significance with low R squared coefficient

    Well back to a couple components, I bet you can slap 95% confidence intervals on the prior model of 500 units if you really wanted and see the estimated variability of the estimate.
  4. hlsmith

    What statistics to use?

    Looks like homework, you have to provide a good effort and ask directed questions related to specific questions you have. Nobody is just going to answer all of those questions for you when you haven't put forth any effort.
  5. hlsmith

    How to analyze a long series of repeated values.

    The ideal model would be multilevel modeling. It is a little more complex but deals with measurements clustered in individuals. It addresses the within and between group variability and runs even if you have some missing data.
  6. hlsmith

    Survival analysis with delayed entries (and left truncation ?)

    If data quality follow a pattern and aren't questionable at random, you have some form of systematic bias. It is up to you to figure out the mechanism and whether it biases results or if you can generalize results just to a particular subset.
  7. hlsmith

    High statistical significance with low R squared coefficient

    You are testing that their is a positive or negative relationship (slope). With a big enough sample you can prove the smallest of relationships (is not zero). You likely have a large enough sample to prove the slope just isn't zero. I will point out that in most fields an r^2 of around 0.5 would...
  8. hlsmith

    Support for stats assignment help

    Assignment of examine?
  9. hlsmith

    Significant 2x2 interaction, but non-significant simple main effects - how to interpet?

    For clarification on what ondansetron wrote, you don't test the main terms, but you do keep them in the model.
  10. hlsmith

    Significant 2x2 interaction, but non-significant simple main effects - how to interpet?

    It is fine if the main effects are not significant. I am guessing there was content rationale to test the interaction and that is how why you examined it. What exactly are your variables. You said it is a continuous by binary variable interaction, correct? Why are you calling your model a...
  11. hlsmith

    Survival analysis with delayed entries (and left truncation ?)

    If I follow you, it seems like your access/viewing of the older data is potentially biasing you. If the old data is questionable in any regards, why use any of it at all? So your desired sample is disabled individuals and the outcome is death, correct. Am I missing anything? What variables are...
  12. hlsmith

    Comparison of beta coefficients within the same group

    A slight point of clarification, sobel examines mediated effects, i was referencing confounding, and you also have backdoor paths from controlling for common effects and interaction issues. It is best to try and draw out the proposed relationships.
  13. hlsmith

    Comparison of beta coefficients within the same group

    Well I am sure there is an easy way/test, but this is not my expertise area. You could potentially looked at the partial R^2 values with confidence intervals on them. I know there are eta and omega squared values for these estimates and not sure if one does a better job of adjusting for changes...
  14. hlsmith

    Confidence Interval in Statistics test

    If I was absolutely pressured to select between A-C, I would pick B. What they are probably trying to get at is that given alpha = 0.05, we are willing to accept results as extreme as revealed by chance 5% of the time, thus the opposite of that vague interpretation would be we are 95% sure the...
  15. hlsmith

    a question for the experts!

    Well this doesn't seem like a controlled experiment performed in a vacuum, so it may get wishy-washy. So 34 candidates, that is straightforward. But later you are calling them A,..,D? How many interviewers are there in total? Was interviewer assignment suppose to be random? Was interviewer...