Recent content by hlsmith

  1. hlsmith

    Significance testing over time on frequency count

    It seems like you should be implementing time series data with the dependent variable being a rate, then looking for patterns or changes in slope. Also, do you have actual income data, that would be more telling.
  2. hlsmith

    Mistake in a textbook: What proportion of studies make "wrong" conclusions?

    Well to continue the deviation, many of the newer "machine learning" / "Deep Learning" approaches haven't integrated Bayesian priors. I would say a big change will be the use of these latter algorithms more often. And these newer algorithms haven't fully embraced Bayesian themes. The tipping...
  3. hlsmith

    How can I show a relationship between a fixed measure and several data points for 10 patients?

    Why do people have a different number of values. It is usually best if a poster just describes the real context instead of dancing around it. Many times important information is lost!
  4. hlsmith

    Protocol comparison: repeated measures ANOVA and mixed linear models

    I didn't follow your post. Are you saying the results from the random effects and fixed effects models are comparable or are you saying the code is similar?
  5. hlsmith

    Is a Fisher's Exact test in a 7x9 contingency table feasible?

    Yeah, your thoughts are correct for the most part. if you have expected cell counts <5 you use Fisher's test, which is your case. Your row names are cut off and I didn't quite understand the output of the Z-score table, but it sounded like chi-sq residuals.
  6. hlsmith

    Continous (Ordinal) Outcome with Middle Group as Target

    I have worked on so many projects in the past two weeks, I don't even remember the context, let me think here. So given my prior descriptions, all patients receive the same dosing protocol which at time point X, everyone is suppose to have a certain blood concentration for a chemical. I...
  7. hlsmith

    PROC GLM

    Yeah I think I looked up glmselect after posting that and it is really directed toward model selection and selection criteria. So Cadillac for selection.
  8. hlsmith

    Overdispersion/ unobserved heterogenity in logistic regression.

    I get your rationale, but they set it up as a rate (e.g., number of positive trials divided by the number of possible positive trials). But you always see these types of data modeled as counts. I bet a Google search of Poisson would reveal very comparable examples over and over again.
  9. hlsmith

    Overdispersion/ unobserved heterogenity in logistic regression.

    I will skim that other article tomorrow, but yeah you can't compare outcomes from different models, that is true. I would be interested to read why they say that isn't true in linear models.
  10. hlsmith

    Overdispersion/ unobserved heterogenity in logistic regression.

    I will start with overdispersion, why the heck are they using logistic instead of Poisson??????? They end up with odds ratios instead of rate ratios which are more interpretible and what the outcome is scalewise! Not drinking the Kool-Aid unless someone gives a good rationale, I will check the...
  11. hlsmith

    Is a Fisher's Exact test in a 7x9 contingency table feasible?

    Let us step back, what is the your purpose for running a Fisher's exact test?
  12. hlsmith

    Which statistical test for six subjects?

    So it is an all or nothing scenario. So you either adhered or didn't? If so, perhaps a one-sample Fisher's exact test. So you are comparing your data to a constant. But what do you want to do with the result, since they weren't suppose to deviate and you know they did?
  13. hlsmith

    Best techniques for surveying large populations

    Well yeah. This seems like it falls under a type of industrial engineering or quality control process, which probably have a better framework. I am just generalizing basic statistics. In doing that, you could state a priori how big of a difference would be considered of importance and determine...
  14. hlsmith

    Protocol comparison: repeated measures ANOVA and mixed linear models

    You still have a very small study with very few samples, so the multilevel model may be underpowered and definitely oversaturated if you think there may be an interaction term. I believe your code would be: model <- lmer(dna_concentration ~ 1 + (1 | sample_id) + treatment + site +...
  15. hlsmith

    Protocol comparison: repeated measures ANOVA and mixed linear models

    are you trying to do a factorization with the use of "*" in the models, also if so, does that still leave the base terms in the model? So is it equivalent to: dna ~ Treatment + site + treatment*site? P.S., Yes the Imer coding is confusing, I have only used it a couple of times.