Hi,   When I submit the same proc template code below in proc sgrender with and without the format contf., obsid is left aligned when I don't apply the format but is right aligned when I apply the format (without changing any code in proc template). How can I left align obsid when I apply the format in proc sgrender?   proc sgrender data=combined template=combined; format obsid contf.; *format obsid contf.; run;   proc template; define statgraph combined; begingraph; layout lattice / columns=2 columnweights=(0.6 0.4) rowdatarange=union columngutter=10px; rowaxes; rowaxis / display=(tickvalues) tickvalueattrs=(size=8); endrowaxes; layout overlay / walldisplay=none xaxisopts=(linearopts=(viewmin=.5 viewmax=2 tickvaluelist=(.5 1 1.5 2)) griddisplay=on display=(line ticks tickvalues)); innermargin / align=left; axistable y=ObsId_char value=obsid / showmissing=false valuehalign=left headerlabel='Subgroup' HEADERLABELATTRS=(size=8) valueattrs=(size=8) labelattrs=(size=8) pad=(right=1pct) indentweight=indent; endinnermargin; .......(partial code)   Thanks, Anders ... View more

Hi,   I am trying to use SAS to fit an instrumental variable analysis on a binary outcome. From what I could find online, this can be done using the 2SLS estimator in proc syslin?   The data are as follows: death (outcome, yes/no), gene (exposure, class variable), which regulates "normalized" (mediator, continuous variable). The value of "normalized" is also affected by cohort, female, trg_i, and crp_log. What I want to know is:   1. If "normalized" (as an instrumental variable) is a causal risk factor for death. 2. If there is evidence for bias when using "normalized" as an observational variable vs. as an instrumental variable (using the Durbin-Wu-Hausman test) on risk of death.   Here is my code:   proc syslin data=causalmed 2sls; endogenous normalized; instruments gene cohort female trg_i crp_log; model normalized = gene cohort female trg_i crp_log; model death = normalized cohort female trg_i crp_log; run;   proc model data=causalmed; endogenous normalized; instruments gene; death = pnormalized*normalized + interc; fit death / ols 2sls hausman; quit;   Is my code correct? Any help would be much appreciated. Thanks! ... View more

Hi,   I am trying to use SAS to fit an instrumental variable analysis on a binary outcome. From what I could find online, this can be done using the 2SLS estimator in proc syslin?   The data are as follows: death (outcome, yes/no), gene (exposure, class variable), which regulates "normalized" (mediator, continuous variable). The value of "normalized" is also affected by cohort, female, trg_i, and crp_log. What I want to know is:   1. If "normalized" (as an instrumental variable) is a causal risk factor for death. 2. If there is evidence for bias when using "normalized" as an observational variable vs. as an instrumental variable (using the Durbin-Wu-Hausman test) on risk of death.   Here is my code:   proc syslin data=causalmed 2sls; endogenous normalized; instruments gene cohort female trg_i crp_log; model normalized = gene cohort female trg_i crp_log; model death = normalized cohort female trg_i crp_log; run;   proc model data=causalmed; endogenous normalized; instruments gene; death = pnormalized*normalized + interc; fit death / ols 2sls hausman; quit;   Is my code correct? Any help would be much appreciated. Thanks! ... View more

Hi,   Does anyone have experience with the interpretation of results from proc syslin and proc causalmed on binary outcomes?   Thanks, Anders ... View more

My company just migrated from desktop SAS (base SAS 9.4) to SAS studio. Today, I received some xlsx files and tried to open these files in SAS studio using this command:   PROC IMPORT DATAFILE="/sasfolders/user/anders/kb - data.xlsx" OUT=test DBMS=XLSX REPLACE; RUN;   Some of the variables in the excel file had names with a delimiter, e.g. old age, which SAS previously (desktop version) would rename to a valid SAS name like old_age. In the SAS studio version though, using:   PROC contents DATA=test; RUN;   The variable name in SAS studio seems to be the same as in excel using the name with a delimiter (old age), which I assume is still an invalid SAS name? So in the background SAS must have renamed the variable even though I can't see it in the SAS studio interface.   This is further complicated by the fact that I can't even run a proc freq because I can't figure out what SAS studio has assigned as a valid SAS name to the various columns.   Any help would be much appreciated. Thanks!!! Anders   ... View more