Search results

  1. spunky

    Endogeneity and R-squared

    True. since R^{2} is a linear combination of correlations and (standardized) regression coefficients, the bias it experiences depends on the size of the coefficients as well as how many of them are biased and in which direction we would observe the bias. However, the key point is that we don't...
  2. spunky

    Endogeneity and R-squared

    Well... it's not super difficult to show that for OLS regression models of the form Y= \beta_0 + \beta_1X_1 + \beta_2X_2 +...+\beta_pX_p + \epsilon , the R^{2} statistic is a function of the elements of the correlation matrix of the predictors and the vector of correlations between the...
  3. spunky

    Reporting Stats Results in APA format

    Sure thing. The APA Style Manual is the official guide for all this stuff
  4. spunky

    How much of Science is based on Statistics

    Another important search term for your googling adventure: 5 sigma A big chunk of evidence for the discovery of the Higgs Boson by CERN relies on that and when you read the description you realize it really is just a p-value.
  5. spunky

    Please show work

    Check this out to complete your work
  6. spunky

    Hello everyone

    Welcome! Here's a good solution to your problem.
  7. spunky

    Analyze non-normally distr. data from within-subjects-design

    Why would you expect the residuals to be normally distributed? Your dependent variable is bounded from 1 to 5 in discrete intervals. Just look at your quantile plot and see how they move in steps as opposed to a smooth, continuous curve. In any case... you're in one of those cases where I'm...
  8. spunky

    Analyze non-normally distr. data from within-subjects-design

    I think reading through this two would be more informative than me writing a whole rant about it: Normality: residuals or dependent variable? and Analyzing ordinal data with metric models: What could possibly go wrong?
  9. spunky

    Kappa for nonsquare tables

    I've never touched SAS in my life ¯\_(ツ)_/¯
  10. spunky

    Kappa for nonsquare tables

    Do you know that STATA does that it lets you handle it? Is it still fitting everything as if it were a square matrix and applying some sort of 'continuity correction'? I remember some software just throw in a 0.5 if there are 0s anywhere.
  11. spunky

    2 sample z test - Standardized Effect Size

    If you're assuming a Gaussian mixture then your answer is wrong UNLESS you further assume that the population means are zero. The general expression for the variance of a mixture is: \sigma^{2}=\sum_{i=1}^{k}p_i(\mu^{2}_i+\sigma^{2}_i)-\mu (where \mu is the grand mean of the mixture) So if...
  12. spunky

    Heterodastic thread on heteroskedasticity

    Well, the first part of my code has the DGP (Data Generation Process) so you can always reduce the simulated sample sizes to have a better look. Right now I'm doing 100 level 1 units (e.g. "kids") in 100 level 2 units (e.g. "classrooms") so if this were real data, my total sample size would be...
  13. spunky

    Heterodastic thread on heteroskedasticity

    What'cha mean by that? Like plotting the standardized/studentized residuals as opposed to raw residuals?
  14. spunky

    Heterodastic thread on heteroskedasticity

    Pfff... you're so right. I'm so dumb sometimes. Thanks for pointing it out!
  15. spunky

    Heterodastic thread on heteroskedasticity

    A follow-up the conversation that we were having. Basically, the idea that for a simulated, linear mixed effects model of the form Y = 0.5 + 0.5X_{1} + u_{0} + \epsilon_{ij} where u_{0} \sim N(0, 0.7) and \epsilon \sim N(0, 0.3) to get an intra-class correlation (ICC) of 0.7. ends up not...
  16. spunky

    Negative values in a Pattern Matrix after Exploratory Factor Analysis

    No. Corrected item-total correlations are.... well, that. You get the column of each item and correlate it with each sum score or average score or whatever way you're creating a 'score' in your scale. And they are "corrected" because the total score is calculated without the item you're...
  17. spunky

    Negative values in a Pattern Matrix after Exploratory Factor Analysis

    Care to elaborate on what this "Monte Carlo" is? Is this Horn's Parallel Analysis? This is weird because it honestly reads like a classic case of "oops, forgot to reverse code". If you run (corrected) item-total correlations treating each factor as an independent subscale, do you observe more...
  18. spunky

    Factor analysis with nested data

    Yes, you are violating a more general version of the assumption of heteroskedasticity. Because you have the same people responding to multiple surveys you have measurements (surveys) nested within respondents. For this kind of data you would need to perform multilevel factor analysis...
  19. spunky

    American Horror Story

    Is it good, though? Cuz I was a devout follower until Jessica Lange left. AHS-hotel with Lady GaGa just didn't do it for me :/
  20. spunky

    What is the best dip for tortilla chips?

    There is only one right answer to this question and that is GUAC. GUAC IS WACK.