Welcome!

Sign in with your CogSci, Facebook, Google, or Twitter account.

Or register to create a new account.

We'll use your information only for signing in to this forum.

Supported by

Calculation of 95% CI and splitting by a variable

antonisantonis Posts: 5
edited April 23 in JASP & BayesFactor
  1. In Descriptives->Descriptive statistics->Statistics, there is no option for calculation of 95% CI. JASP can calculate mean and SD, but then I must use Excel or calculate it manually.
  2. I wanted to calculate the mean, 95%CI, SD etc of a dependent variable according to the values of an independent variable (e.g. gender). I didn't want to run any test, just to report the mean, 95%CI and SD separately for the males and females. There is no such option in Descriptive statistics. In plots, there is an option to create a boxplot after splitting by gender. Make this option (to split by a variable) more widely available.
  3. I tried t statistics. In t statistics there is an option to calculate 95%CI. However, 95%CI still does not appear in the table (VAR8 is the gender, and VAR25_1 is the dependent variable). It seems that this option is only for the "t value". I selected Descriptives plots and only there can I see the 95% CI, but it is only visual and the exact values are not available.

Comments

  • EJEJ Posts: 392

    Good points. The 95% CI is an inferential measure and we didn't feel it belongs in descriptives. But I'll discuss this with the team. Making the "split by" option more general is highly desirable, we agree.
    E.J.

    Thanked by 1antonis
  • antonisantonis Posts: 5

    Well, on second thoughts, I can understand why you feel that it doesn't belong in descriptives (because it is often calculated using the student t distribution). However, I believe that there should be at least an option in t test to display the confidence interval, as I mentioned before (and not only visually in box plot).
    Thanks for your quick reply.

  • EJEJ Posts: 392

    Thanks. We are working on it!
    E.J.

Sign In or Register to comment.