Recent content by hlsmith

  1. hlsmith

    "The bigger the sampling error, the bigger the confidence interval."

    @Belle_Grace all you need to do is look up some of the formulas for confidence intervals to answer your questions...
  2. hlsmith

    How to interpret interaction effect when the relation it interacts with is negative instead of positive

    What evidence (literature) did you base your hypothesis on - was it founded? Your hypothesis was wrong, so it would reject it I guess, since the presented context was not well known. I wouldn't get all hung up on whether it rejected or provided evidence toward supporting it. I would just state...
  3. hlsmith

    Critical F value for testing Full vs Reduced models.

    I know I am a hard as s on this but both seem pretty saturated.
  4. hlsmith

    Extrapolation

    I was just thinking about your last post. If you have a high estimate, that may be a sign of a curvelinear relationship. Do your residuals reveal any irregularities?
  5. hlsmith

    Extrapolation

    It is my belief that if the value of X is within the sample space of other values it is still just interpolation. If you have a particular example that you think is really wonky, post it and we can see.
  6. hlsmith

    Extrapolation

    Sounds like interpolation. That is when you estimate a value within the range of your data, but you just did not have an observation for it in the dataset. For example, I want to estimate the weight of someone that is 60 inches and my dataset includes: 56, 54, 58, 62, 63, 66. Welcome to the forum!
  7. hlsmith

    Distributions

    Well you have binary random variables, so I would imagine you are dealing with the binomial distribution.
  8. hlsmith

    Calculate type 2 error using one data file

    Historically ML is more used with prediction instead of inference. This is partially what you are coming up against. What machine learning algorithm did you use and is this solely a prediction use? You may be likely to do an in-sample confusion matrix, but it will under-represent your type 2...
  9. hlsmith

    Hello Statisticians!

    We will do our best. Welcome aboard!! What is your background?
  10. hlsmith

    Probabibility

    Bayes fo' life. Plug values into Bayes theorem. Show work and we will work with you.
  11. hlsmith

    Distributions

    I think I learned last week that binary distributions are traditionally pr(....) and continuous are p(....). Just sharing. Oh yeah - what Dason said.
  12. hlsmith

    How to interpret interaction effects when main effects are also significant

    If you are hypothesizing an interaction, then you are saying the effects of the main terms are conditional on each other. Thus you no longer care about the main terms, regardless if they are significant or not. You solely report the interaction term.
  13. hlsmith

    Multilevel Longitudinal Models and Correlated Errors

    Is the critique which variance/covariance structure you used? You can try different ones then see how much it changes fit measures, but your decision should also be based on your content knowledge of the topic. Controlling for random effects will account for additional variability, but I am...
  14. hlsmith

    Visualising hierarchical multiple regression

    How is your model structured as in the following would be used in R for a random intercept and effects model: Interest ~ 1 + mother + father + gender ( 1 + ?variable | cluster_ID) What is your sample size and number of groups in the clusters?
  15. hlsmith

    Visualising hierarchical multiple regression

    How do you define "mathematics"? Is this a binary variable?