Search results

  1. Y

    What test should be used to compare nominal data between 5 groups

    Cochran Armitage Trend test is an option to test the linear trend of the proportions of 6 indications over 5 years. If you need to adjust for other covariates, you can use proc glimmix or proc logistic in SAS including categorical variable of 6 indications and year as continuous or categorical...
  2. Y

    Confidence Intervals for Incidence rate

    You need to know # of cases and total number of people, then use SAS proc freq including count statement to report proportion and confidence interval.
  3. Y

    Statistical comparisons for large sample sizes (n>1000)

    For any trial, sample size calculation warrants the sample size archiving the pre-specified power and type 1 error. Apparently n=1000 for each exposure group is too large, even for an observational study. After the minimum sample size reaches, the more subjects enrolled the smaller p-value tends...
  4. Y

    My t-test results are significant, but are they meaningful?

    Suppose you had 135 observations, each for one country including y and N for # of cases and total number of people. To compare the the proportion of COVID-19 cases between two regions classified in your question, you can try proc logistic or proc glimmix: proc glimmix; class region...
  5. Y

    Combining different measures of survival for a SR

    Meta analysis is often used for integrating the effect size from multiple studies, such as odds ratio and hazards ratio. You may want to check if the papers provide the similar effect size with standard errors and study sample size. I suspect you do not have patient level data from published...
  6. Y

    which efficacy population you are using for onc phase1/2a

    ITT/mITT is often used for randomized trials. For early oncology studies, the population for efficacy analysis in your question is FAS full analysis set including all subjects who took study drug and had at least one post-baseline efficacy assessment. If tumor response needs confirmed, two...