Comments on: How to Perform T-test for Multiple Variables in R: Pairwise Group Comparisons https://www.datanovia.com/en/blog/how-to-perform-t-test-for-multiple-variables-in-r-pairwise-group-comparisons/ Data Mining and Statistics for Decision Support Fri, 05 Jun 2020 06:49:16 +0000 hourly 1 https://wordpress.org/?v=6.8.2 By: Gene https://www.datanovia.com/en/blog/how-to-perform-t-test-for-multiple-variables-in-r-pairwise-group-comparisons/#comment-20497 Fri, 05 Jun 2020 06:49:16 +0000 https://www.datanovia.com/en/?p=15430#comment-20497 In reply to kassambara.

I got it! Thank you very much for your answer!

]]> By: kassambara https://www.datanovia.com/en/blog/how-to-perform-t-test-for-multiple-variables-in-r-pairwise-group-comparisons/#comment-20496 Thu, 04 Jun 2020 06:50:28 +0000 https://www.datanovia.com/en/?p=15430#comment-20496 In reply to Gene.

Thank you for the positive feedback!

If you have multiple groups, then I would go with ANOVA then post-hoc test (if ANOVA is significant).

Every time you conduct a t-test there is a chance that you will make a Type I error (i.e., false positive finding). This error is usually 5%. By running two t-tests on the same data you will have increased your chance of “making a mistake” to 10%. Three t-tests would be about 15% and so on. These are unacceptable errors. An ANOVA controls for these errors so that the Type I error remains at 5% and you can be more confident that any statistically significant result you find is not just running lots of tests.

]]> By: Gene https://www.datanovia.com/en/blog/how-to-perform-t-test-for-multiple-variables-in-r-pairwise-group-comparisons/#comment-20492 Thu, 04 Jun 2020 03:11:44 +0000 https://www.datanovia.com/en/?p=15430#comment-20492 Hi! Excellent tutorial website! I saw a discussion at another site saying that before running a pairwise t-test, an ANOVA test should be performed first. It is like the pairwise t-test is a Post hoc test. I am wondering, can I directly analyze my data by pairwise t-test without running an ANOVA?

]]>