what is the difference between (path Non parametric - > Independent samples then select Mann Whitney) and path Non parametric -> legacy -> 2 independent samples?
Because , while doing both , calculated value of Mann-Whitney is differ in both output.
Is there any different approaches?
Hello Shahul,
I ran a sample data set from Sidney Siegel's Nonparametric statistics (1956) text both ways, and get exactly the same results in spss 27. Could you give your syntax and data for the two analyses? Perhaps that would help to identify what's going on with your situation.
Good luck with your work.
The "legacy" path brings up a dialog for the NPAR TESTS command (1st link below). The other path brings up a dialog for the newer NPTESTS command. (IIRC, NPTESTS requires one to set the measurement levels of the variables via the VARIABLE LEVELS command.)
- https://www.ibm.com/support/knowledgecenter/en/SSLVMB_26.0.0/statistics_reference_project_ddita/spss/base/syn_npar_tests.html
- https://www.ibm.com/support/knowledgecenter/en/SSLVMB_26.0.0/statistics_reference_project_ddita/spss/base/syn_nonparametric.html
By the way, I found this old SPSSX-L thread in which I posted a rant after my first experience with the newer NPTESTS command:
- http://spssx-discussion.1045642.n5.nabble.com/RANT-NPTESTS-vs-NPAR-TESTS-td2807847.html
HTH.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS