Hello,
I've performed a Mantel test between my microbiological data and the geographic distance where those samples were collected, using a table with 516 samples. However, the test doesn't provide the degrees of freedom (df), so I'm trying to calculate it manually.
In a simple test, the df = sample size - 1, while in a correlation test, it is df = sample size - 2. In the case of the Mantel test, the correlation is not between two samples or columns, but between all the 516 rows present in the table. I found different ~possible~ answers, but none of them was clear or objective regarding its calculation. For example: http://www.pelagicos.net/MARS6300/lectures/MARS6300_Lecture21_sp2018.pdf (Mantel test output - TEST STATISTIC: t-distribution with infinite degrees of freedom using asymptotic approximation of Mantel) and (https://v8doc.sas.com/sashtml/stat/chap19/sect42.htm#:~:text=In%20general%2C%20the%20number%20of,%2C%20df%20%3D%20q%20%2D%20t.)
I'm using the mantel() function in R, from the vegan package, with the "spearman" correlation method.
Any help is appreciated! Thank you so much
Adriana
Adriana Cravo
TEST STATISTIC: t-distribution with infinite degrees of freedom using asymptotic approximation of Mantel (1967). If t < 0, then negative association is indicated. If t > 0, then positive association is indicated. I am not sure what are your Z scores. Just watch out for Type 1 error.
Good luck.
Adriana Cravo
TEST STATISTIC: t-distribution with infinite degrees of freedom using asymptotic approximation of Mantel (1967). If t < 0, then negative association is indicated. If t > 0, then positive association is indicated. I am not sure what are your Z scores. Just watch out for Type 1 error.
Good luck.
Degree of freedom is calculated by using the following formula: DF = (r-1)(c-1) Where DF = Degree of freedom r = number of rows c = number of columns
A Mantel test is one way of testing for spatial autocorrelation. Using functions in the ade4 library, we can perform a Mantel test in R.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size