0

I want to compare between the level of Th17 cells in the blood of a group patients with Sarcoidosis, and whether or not it is correlated with them having fibrosis. So, a continuous variable and a dichotomous variable, and one group, not two. Mann Whitney can't be applied as far I understand. So, what test to use if the data are not normal? Also, what test to use of one of the variables is not dichotomous, but can have multiple values??

Alpha
  • 1
  • So you are comparing the distribution of some continuous variable between two groups? Can you tell us some more, like sample size, and show us some plots? But maybe try Wilcoxon test – kjetil b halvorsen Feb 25 '24 at 19:32
  • @kjetilbhalvorsen Sample size is 25, no, not 2 groups, just one group of patients. I want to check if there is a correlation between the level of Th17 in their blood (continuous variable), and whether or not they have fibrosis (dichotomous variable). – Alpha Feb 25 '24 at 19:46
  • 1
    Fibrosis or not seem to define two groups (maybe in your case subgroups) for the purpose of the wilcox test. If you had more observations, maybe https://stats.stackexchange.com/questions/190156/t-tests-manova-or-logistic-regression-how-to-compare-two-groups – kjetil b halvorsen Feb 25 '24 at 19:51
  • @kjetilbhalvorsen I was thinking of an alternative to the point bieserial when data are not normal? – Alpha Feb 25 '24 at 20:04
  • 1
    What question do you have for your data to (hopefully) answer, if the Th17 level is high/lower in the fibrosis group than in the control or healthy group? – Dave Feb 25 '24 at 20:15
  • @Dave I want to answer wheher the increase of Th17 in some patients correlates with fibrosis. No healthy group. Just one group of patients, some have fibrosis, and some don't. I have their data of Th17 cells levels. I want to check if it correlates with fibrosis. – Alpha Feb 25 '24 at 20:19
  • 1
    That sounds like a two-group comparison, exactly what a t-test or Wilcoxon test addresses. What do you see differently? (Do you, for instance, have “before-and-after” measurements for each group?) – Dave Feb 25 '24 at 20:25
  • @Dave unequal group sizes (12 data points in the "No Fibrosis" group and 13 in the "Fibrosis" group). The Wilcoxon signed-rank test is applicable only when the compared groups have the same number of samples? or I am mistaken? – Alpha Feb 25 '24 at 21:44
  • 1
    Often, and here in particular, “Wilcoxon test” refers to the Wilcoxon-Mann-Whitney U test, which does not require equal group sizes. The signed-rank test bearing Wilcoxon’s name is analogous to the paired t-test and, thus, requires equal group sizes but is a different test. Both the paired t-test and signed-rank test also require a natural pairing of the points, such as before-and-after. $//$ One of your hang-ups seems to be a lack of normality. If you had normality, would a two-sample t-test make sense? – Dave Feb 25 '24 at 21:52
  • @Dave Thanks, yes, then in this case the Wilcoxon-Mann-Whitney U test could be applied? – Alpha Feb 25 '24 at 22:03
  • This sounds like a situation where WMWU can be used. WMWU is basically asking if the two groups have different distributions. – Dave Feb 25 '24 at 23:59

0 Answers0