Search results

  1. Miner

    explaing basic stats concepts to my cat

    The cat understands. It just does not care.
  2. Miner

    residuals linearity

    Do you have the ability to store your residuals then generate a plot similar to this where the color represents the density of the plotted points? Some call this a binned scatterplot. Or use a lighter shade of gray on your plotted points where it better shows the density of points?
  3. Miner

    residuals linearity

    It does not appear to show the indicators of nonlinearity. You want to focus on the most dense portion of the plot. Nonlinearity is usually pronounced. Of course you can always add a quadratic term and see what that does to your model (i.e., significance of term, AIC/BIC). It does not appear...
  4. Miner

    Using/converting KM survival data

    Focus on the "Years Since Intervention" and "Cumulative Failures" columns. Difference the "Cumulative Failures" column and match the differences with the correct "Years Since Intervention" rows. This will give you years matched with the number of patients that survived that long.
  5. Miner

    residuals linearity

    I have seen this pattern when you have a boundary condition that limits the range of the residuals. It is easier to see when you are using regular residuals. Standardized and Studentized residuals obscure that. The graph below shows it better. Try plotting the residuals against each of the...
  6. Miner

    Scree plot interpretation

    I agree with @Karabiner. I usually include the Kaiser criterion that the Eigenvalues must also be greater than 1.
  7. Miner

    how to analyze data with 3 samples with factorial experimental design

    This is very problematic because these three factors are 100% confounded (aliased) with each other. You cannot separate the effects of one from the others.
  8. Miner

    ANOVA after logistic regression?

    To use ANOVA you would need to use the actual arrival times instead of early vs late.
  9. Miner

    Statistical test to assess differences between two groups with different trait measures

    I would use a General Linear Model with Type nested within Sex.
  10. Miner

    I need some help with my finance question. It’s not exactly related to statistics but still involves it

    This is not about statistics, but about finance. Look up the Present Value of money.
  11. Miner


    Means = Averages Standard Deviation is a measure of the variation in the sample N = sample size This is an ANOVA (ANalysis Of VAriance) table. It is a hypothesis test for testing if there is a statistically significant difference between the average of any one drug. The small significance...
  12. Miner


    The significance (Sig.) level (or p-value) being less than 0.05 (typical alpha risk) indicates statistical significance. You stated in an earlier post that higher response times were detrimental. Drug A is the only drug that is statistically different from the placebo AND it has a higher mean...
  13. Miner


    Most of these charts just provide summary statistics of the three drugs. The key elements are: 1) 1-way ANOVA table. This shows that there is at least one contrast between the three drugs that is statistically significant. 2) Multiple comparisons using Bonferroni post-hoc test. This shows...
  14. Miner


    The test tells you that Drug A significantly increases reaction time vs the placebo, and that Drug B does not significantly increase the reaction time vs. the placebo. Therefore, Drug B appears to be the answer.
  15. Miner


    Sorry, I do not use SPSS.
  16. Miner


    I recommend using Dunnett's post-hoc test. It will test drugs A and B against the placebo reducing the total number of tests.
  17. Miner

    AIC models

    No. Confidence intervals indicate the uncertainty in means around the regression line while prediction intervals indicate the uncertainty of individual predictions made with the regression equation. See this explanation.
  18. Miner

    AIC models

    There are two unrelated questions being asked. Your question about AIC is directed toward finding the optimum "statistical" model. Your question about removal of terms is directed toward how far from the optimum can I simplify the model for purely practical reasons and still have a model that...