Using Mann-Whitney U test (Wilcoxon rank sum test), I am comparing two groups to see whether they are statistically different.   Based on almost the  same median and mean values between the two groups, I definitely thought that p-value would be very high.  But P-value was < 0.0001 (attached).  Any ideas why P-value is significant?   P-value from T-test was about 0.15.       sas code: proc NPAR1WAY data=nis.cdiselect wilcoxon; class primary; var age; run; ... View more

proc genmod data = eyestudy; class carrot id; model lenses = carrot/ dist = poisson link = log; repeated subject = id/ type = unstr; estimate 'Beta' carrot 1 -1/ exp; run; above was copied from below: https://stats.idre.ucla.edu/sas/faq/how-can-i-estimate-relative-risk-in-sas-using-proc-genmod-for-co...   Above statement allows exp(beta) and exp(confidence intervals). But I don't understand, the part of estimate statement, 1 -1.  Is it because carrot is binary variable?  If the variable has more than 2 categories or continuous, how estimate statement will be different.  I would very much appreciate your help!   ... View more

  Using the national dataset, my study aim is to obtain cdi infection rate and mortality over 12-year period.   While I am doing so, I saw significant differences in rates among crude, adjusted for age/sex, and adjusted for age/sex/comorbidities.  Then I went ahead and obtained mortality for entire sample regardless of primary or secondary diagnoses.   Below are the results.   You can see almost 10x differences between 2nd (adjusted for age and sex) and 3rd  (adjusted for age/sex/race/comorbidities) results.     crude adjusted for age and sex adj for demographics and comorbidities 2003 0.02202 0.01558 0.1463 2004 0.02096 0.01498 0.1376 2005 0.02043 0.01444 0.1294 2006 0.02018 0.01415 0.1234 2007 0.01916 0.01361 0.1149 2008 0.02014 0.01379 0.1174 2009 0.01893 0.01307 0.1084 2010 0.01862 0.01286 0.1034 2011 0.01872 0.01253 0.0968 2012 0.01845 0.01259 0.09664 2013 0.0189 0.01286 0.09651 2014 0.01901 0.01301 0.09573   My sas codes are below.   Questions: 1.I don’t know why numbers are significantly different.  Maybe Poisson is inappropriate for obtaining adjusted rates, but appropriate for IRR in multivariable model…?   2.What would be the best method(s) to perform trends analyses for rates and IRR…?   Best, Sun   Crude mortality proc genmod data=NIS.cdi; class year female agegroup / param=glm; model died (event='1')=year  / type3 dist=poisson link=log offset=log_discharge; weight trendwt; store plmsourcenis; run;   proc plm source=plmsourceni; lsmeans year / ilink cl;run;     Mortality after adjusting for sex and age proc genmod data=NIS.cdi; class year female agegroup / param=glm; model died (event='1')=year female agegroup / type3 dist=poisson link=log offset=log_discharge; weight trendwt; store plmsourcenis_sexage; run;   proc plm source=plmsourcenis_sexage; lsmeans year / ilink cl;run;     Mortality after adjusting for sex, age, and comorbidities proc genmod data=NIS.cdi; class year female agegroup race_three CM_AIDS CM_alcohol CM_anemdef CM_arth CM_bldloss CM_CHF CM_chrnlung CM_coag CM_depress CM_DM CM_dmcx CM_drug CM_HTN_C CM_hypothy CM_liver CM_lymph CM_lytes CM_mets CM_neuro CM_obese CM_para CM_perivasc CM_psych CM_pulmcirc CM_renlfail CM_tumor CM_ulcer CM_valve CM_wghtloss / param=glm;   model died (event='1')=year female agegroup race_three CM_AIDS CM_alcohol CM_anemdef CM_arth CM_bldloss CM_CHF CM_chrnlung CM_coag CM_depress CM_DM CM_dmcx CM_drug CM_HTN_C CM_hypothy CM_liver CM_lymph CM_lytes CM_mets CM_neuro CM_obese CM_para CM_perivasc CM_psych CM_pulmcirc CM_renlfail CM_tumor CM_ulcer CM_valve CM_wghtloss / type3 dist=poisson link=log offset=log_discharge; weight trendwt; store plmsourcenis_com; run;   proc plm source=plmsourcenis_com; lsmeans year / ilink cl;run;   ... View more

I got yearly rates with sas code below:   proc genmod data=cdi;  class year sex age_group / param=glm; model cdiff= year sex age_group / type3 dist=poisson link=log offset=log_discharge; estimate "rate: year=2003" intercept 1 year 1 0 0 0 0 /e .........;run;   I would appreciate sas codes (or references) for trend analyses.  Using Cochran armitage test would be appropriate (I am familiar with this).   ... View more

I am trying to see whether there is a significant upward or downward trend in certain infection over time.  I calculated rates/95% confidence intervals using proc genmod.  Can I use Cochran-armitage test (year vs. mean proportion) for trends?  If not, what method would be appropriate? ... View more

I am interested in a disease prevalence in each group (total 4 groups).  To determine statistical differences in proportions among these groups, I would like to know how many people I need in each group.  Can I use "proc power multreg", Or proc power twosamplefreq (Bonferroni correction, alpha=0.0083).  If I use proc power twosamplefreq, do I need to set three different odds ratio in reference to control and alpha adjustment (0.0083) with Bonferroni correction (6 comparison, alpha 0.05/6=0.0083).  Thank you.   proc power; multreg model = fixed nfullpredictors = xx ntestpredictors = 3 rsquarefull = xx rsquarediff = xx ntotal = . power = 0.8; run;   proc power; two samplefreq test=lrchi oddratio=1.5 2 2.5 ref proportion=0.5 npergroup=. alpha=0.05 0.0083 power=0.8; run; ... View more