1) COmparing 2 drugs (independent groups) and their effect on composite endpoint of DVT/VTE/sztroke/death/ CVD as primary efficacy and safety for major bleeding. outcomes are discrete (yes or no values)
-----if cell value> 5 , will use ChiSquare for independent test to evaluate both efficacy and safety endpoint, if ;ess than 5 fishers exact test.- is this correct.
also would P value be better presentation of data or using odds ratio with confidence interval be better.
Can I use OPEN Epi- the online statistics tool for the above?
also if I want to lets say stratify further into subgroups to compare the efficacy anf safety endpoints based on 2 disease groups - VTE/DVT and Afib- what test would I then use? same as above or anything different.
Does PS software let you plot forest plot or is there any easier use friendly free software that I can use the ODDS ratio I obtain from OPEN EPI .com to generate Forest plot?
If the data are from a normal distribution, you can just do an unpaired t-test. A chi-squared test can be used if the data are non-Gaussian distributed (non-parametric) or you could use a Wilcoxon test. It doesn't really matter what test you use, so long as the data meet the the criteria. But you also need to outline assumptions, hypotheses, power, and use a control in the comparison :)
The independent t-test, also called the two sample t-test, independent-samples t-test or student's t-test, is an inferential statistical test that determines whether there is a statistically significant difference between the means in two unrelated groups. use it as a test and run your data on SPSS to simplify your study.
- Badges
- Science topic