Recent content by Stats fan

  1. S

    making R computing large factorials

    p.x.log <- function(n.of.points, x, p, q) { log.result <- sum(log(n.of.points:1)) - sum(log(x:1)) - sum(log((n.of.points-x):1)) + x*log(p) + (n.of.points-x)*log(q) exp(log.result) }
  2. S

    making R computing large factorials

    You could do the computations in log space
  3. S

    Software for Simple Linear Regression

    What about R: https://www.r-project.org/ .
  4. S

    Minimise chance of making type 1 error, without reducing alpha?

    Alpha = the probability of making a Type I error...
  5. S

    Anova

    I agree with ondansetron that reading a bit more about ANOVA in your textbook could help you a lot with answering the questions. However, if you prefer practice questions where the correct answer is explained, you may want to have a look here: http://statkat.com/selectquestions.php . You can...
  6. S

    Coefficient of correlation.

    That's correct. Also, note that dividing the values by 5 is the same as multiplying them by 1/5. So in de second question, the x values are multiplied by 2/5 (and 3/5 is added to them).
  7. S

    Coefficient of correlation.

    Well, the coefficient is determined by the strength and the direction of the linear relationship between two variables. If there is a linear negative relationship between two variables, the coefficient is between 0 and -1. If there is a linear positive relationship between two variables, the...
  8. S

    Coefficient of correlation.

    Then I disagree with that source. I think they made a mistake.
  9. S

    Coefficient of correlation.

    A is the correct answer for the second question. It seems like you get it!
  10. S

    Coefficient of correlation.

    At the bottom of this overview http://statkat.com/stattest.php?t=19 you can find a list of properties of the correlation coefficient. The property listed fourth can help you answering this question. Let me know if you can figure it out using this information.
  11. S

    How to know if I should use correlation or hypothesis test?

    I wouldn't say the order matters.
  12. S

    How to know if I should use correlation or hypothesis test?

    I think the 'trick' is to really understand what each method/test is for (e.g., one sample t test tests whether an unknown population mean mu is different from a certain fixed value, two sample t test tests whether an uninown population mean is different from another unknown population mean...
  13. S

    How to know if I should use correlation or hypothesis test?

    This website allows easy comparison of several tests: http://www.statkat.com/stattest.php?&t=10&t2=9&t3=19 . You can remove/add methods to compare with each other if you like. It might be useful for you!
  14. S

    track data across quartile groups (if that's even a thing)

    Ah I hadn't seen your last message when I posted my new response... Yes that is what I was suggesting. I assumed you had already done this
  15. S

    track data across quartile groups (if that's even a thing)

    Maybe I get it now. You have three variables (which you call categories, that got me confused), the first ranging from -36 to 36, the second from 0 to 760, and the third from 0 to 38. You have transformed each variable into an ordinal variable consisting of four quartiles. Now you want to know...