JASP 0.14 Tutorial: Chi-Squared Test of Independence (Contingency Tables) (Episode 22)
Vložit
- čas přidán 11. 09. 2024
- In this JASP tutorial, I go through how to do a Chi-squared Test of Independence (CrossTabs or Contingency Tables) with a sample dataset from the Data Library. Options include getting observed counts along with expected counts, as well as exploring the outcome with the stat.
JASP: jasp-stats.org
NOTE: This tutorial uses the new preview/beta build of 0.14. This build contains slightly more functions/features than the previous builds used for tutorials on this channel, but it is functionally the same for the purposes of this tutorial.
Find me on Twitter: / profaswan
Go to my website: swanpsych.com
Twitch streams on psych & related topics: / cogpsychprof
JASP was recommenden to me and I was banging my head against the wall on how to do the test (as I not only have 0 experience in the app but also 0 experience in statistics). This video was amazing!! thank you very much
Good stuff. Started using JASP couple of days ago. Pretty intuive software. These videos are extremely useful as starter's introduction.
Thanks! I’m glad they’re helping
Excellent, thank you. I understand. You are very clear.
Simple and clear.
Thanks.
Great video, thanks! I have data from a survey where participants were given 3 choices (agree - neutral - disagree) and if only one or two of the choices were selected by the respondents, the chi-sq doesn't display the missing value, and so I'm afraid that the test isn't run correctly. How can I mitigate this?
I’m not sure I fully understand your design/question, so I’ll broadly answer the missing value issue - categorical variables need an input and don’t do well with missing values. It’s best to just not include those cases in the analysis.
@@AlexanderSwan That's fair, it's tricky to describe in text without images. All my respondents selected either "neutral" or "disagree" for one of my questions, so the "agree" option was not included in the contingency table produced by JASP. But what you're saying is that this is in fact correct and should be left as is?
Again, I appreciate the help greatly, your guides for JASP has been very useful. Thanks
How do you interpret the effect sizes here?
I'm not sure if I understand your question -- the magnitude of the chi-square here is the magnitude of the effect. So the bigger the outcome, the more related the two concepts in the TOI.