Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
faq:how_not_to_interpret_results_from_a_cluster-based_permutation_test [2015/11/02 07:35]
77.165.5.71 [The extent of the cluster depends]
faq:how_not_to_interpret_results_from_a_cluster-based_permutation_test [2017/08/17 11:21] (current)
Line 5: Line 5:
  
 ==== The correct interpretation ==== ==== The correct interpretation ====
-The permutation test as implemented in **[[/​reference/​ft_statistics_montecarlo]]** serves to test  the null hypothesis (H0) that the data in the experimental conditions come from (are drawn from) the same probability distribution. In specialised statistics books, ​on sometimes reads the technical term that the probability distributions are **exchangeable**. Getting a significant result means that we can reject the null hypothesis (H0) that the data come from the same probability distribution in favour of the alternative hypothesis (H1) that the data come from different distributions. Based on a significant test result, you therefore can report that **"​there is a significant difference between condition A and condition B"**.+The permutation test as implemented in **[[/​reference/​ft_statistics_montecarlo]]** serves to test  the null hypothesis (H0) that the data in the experimental conditions come from (are drawn from) the same probability distribution. In specialised statistics books, ​one sometimes reads the technical term that the probability distributions are **exchangeable**. Getting a significant result means that we can reject the null hypothesis (H0) that the data come from the same probability distribution in favour of the alternative hypothesis (H1) that the data come from different distributions. Based on a significant test result, you therefore can report that **"​there is a significant difference between condition A and condition B"**.
  
 <note warning > <note warning >