Hello,   we're using PROC PHREG to model a Cox regression with 3 time-dependent covariates and want to test if all 3 interactions from this time-dependent covariates equals zero, but we are unable to create a correct TEST statement. The code without the TEST statement (which we assume as valid): proc phreg data = tteana;<br /> class trtpn(ref="1") region; * TRTPN has values 0 or 1, REGION has 4 categories ;<br /> model aval * cnsr(1) = trtpn region aeno1 aeno2 aeno3 aeno1*trtpn aeno2*trtpn aeno3*trtpn / rl;<br /> * TIM1, TIM2, and TIM3 as well as AVAL are time variables ;<br /> if tim1 <= .z or aval <= tim1 then do;<br /> aeno1 = 0; aeno2 = 0; aeno3 = 0; <br /> end;<br /> else do;<br /> if (aval > tim1 and (aval <= tim2 or tim2 = .)) THEN DO;<br /> aeno1 = 1; aeno2 = 0; aeno3 = 0; <br /> end; <br /> else do;<br /> if (aval > tim2 and (aval <= tim3 or tim3 = .)) THEN DO;<br /> aeno1 = 0; aeno2 = 1; aeno3 = 0;<br /> end; <br /> else do;<br /> if (aval > tim3 ) THEN DO;<br /> aeno1 = 0; aeno2 = 0; aeno3 = 1;<br /> end; <br /> end;<br /> end;<br /> end;<br /> *T1: test aeno1*trtpn = aeno2*trtpn = aeno3*trtpn = 0;<br />run; The TEST statement does not work and issues an error message (the * is not allowed).   The idea we had, was to create 3 new variables DUMMY1-DUMMY3, which are the same as the interaction terms the following way:   proc phreg data = tteana;<br /> class trtpn(ref="1") region ;<br /> model aval * cnsr(1) = trtpn region aeno1 aeno2 aeno3 dummy1 dummy2 dummy3 / RL;<br /> if tim1 <= .z or aval <= tim1 then do;<br /> aeno1 = 0; dummy1 = aeno1*trtpn;<br /> aeno2 = 0; dummy2 = aeno2*trtpn;<br /> aeno3 = 0; dummy3 = aeno3*trtpn;<br /> end;<br /> else do;<br /> if (aval > tim1 and (aval <= tim2 or tim2 = .)) then do;<br /> aeno1 = 1; dummy1 = aeno1*trtpn;<br /> aeno2 = 0; dummy2 = aeno2*trtpn;<br /> aeno3 = 0; dummy3 = aeno3*trtpn;<br /> end; <br /> else do;<br /> if (aval > tim2 and (aval <= tim3 or tim3 = .)) then do;<br /> aeno1 = 0; dummy1 = aeno1*trtpn;<br /> aeno2 = 1; dummy2 = aeno2*trtpn;<br /> aeno3 = 0; dummy3 = aeno3*trtpn;<br /> end; <br /> else do;<br /> if (aval > tim3 ) then do;<br /> aeno1 = 0; dummy1 = aeno1*trtpn;<br /> aeno2 = 0; dummy2 = aeno2*trtpn;<br /> aeno3 = 1; dummy3 = aeno3*trtpn;<br /> end; <br /> end;<br /> end;<br /> end;<br /> T1: Test dummy1 = dummy2 = dummy3 = 0;<br />run;  We get a result from the TEST statement, but the estimates for AENO1, AENO2, AENO3 are different from the ones in the first procedure run, the estimates for REGION are the same, the estimates for DUMMY1-DUMMY3 are the negative of the estimates of AEON1*TRTPN, AEON2*TRTPN, AEON3*TRTPN above.   Our questions: Are the both models the same?     If yes, why are the estimates for different?     If no, what exactly is the difference between the two models? Is there any other way to get the test result we want?   Any help would be greatly appreciated and thanks in advance trying to understand our problem! ... View more

With the following (example) code a picture is created which looks fine if using IMAGE_DPI=100 in the ODS LISTING (see graph1.pdf). But if using IMAGE_DPI=1200 (what is needed by customer) the symbols are displayed in a very light shade (nearly invisible) which could not be acceptable (see graph2.pdf). Any ideas how to solve this? Thanks for any ideas or hints! SAS code:   data test;   input avg diff sgrpdc count_score;   cards; 2 0 1 1 5 -1 1 1 12 2.5 1 2 18 1.2 1 1 20 -3 1 3 20 -1 1 1 23 3.5 1 2 25 -4 1 1 27 2.1 1 2 33 0.4 1 4 3 1.1 2 1 6 -1 2 2 12 0.5 2 1 15 -1.2 2 2 18 -3 2 1 20 -1 2 1 24 0.5 2 1 26 -4 2 1  ; run;   proc template;   define style styles.mypng;   parent=styles.listing;   style GraphData1 from GraphData1 / color=black contrastcolor=black linestyle=1         markersymbol='plus';   style GraphData2 from GraphData2 / color=black contrastcolor=black linestyle=1         markersymbol='circle';   style GraphOutlines from GraphOutlines / color=black contrastcolor=black linestyle=1                                 linethickness=4pt;   end;   define statgraph sgdesign;   begingraph;     entrytitle "Score for Cystic Fibrosis and COPD subjects p=0.xxxx";       layout overlay / yaxisopts=(label="Within Subject Difference (V2 - V1)#in score"          labelattrs=(size=8) labelfitpolicy=splitalways labelsplitchar='#' labelsplitchardrop=true          linearopts=(viewmin=-6 viewmax=8 minorticks=true          minortickcount=4 tickvaluesequence=(start=-6 end=8 increment=2)))          xaxisopts=(label="Within Subject Average (V1 and V2) in Score"          labelattrs=(size=8) linearopts=(viewmin=0 viewmax=40          tickvaluesequence=(start=0 end=40 increment=10)));       scatterplot x=avg y=diff / group=sgrpdc                  name='scatter' markersizeresponse=count_score;       referenceline y=1 / lineattrs=(color=black) curvelabel="Mean:mw" curvelabelposition=max                curvelabellocation=outside curvelabelsplitchar='#' curvelabelsplitchardrop=true                curvelabelsplit=true curvelabelattrs=(color=black size=6);       referenceline y=3 / lineattrs=(color=black pattern=shortdash) curvelabel="+1.96SD:sd"                curvelabelposition=max curvelabellocation=outside curvelabelsplitchar='#'                curvelabelsplitchardrop=true curvelabelsplit=true curvelabelattrs=(color=black size=6);       referenceline y=-2 / lineattrs=(color=black pattern=shortdash) curvelabel="-1.96SD:#sd"                curvelabelposition=max curvelabellocation=outside curvelabelsplitchar='#'                curvelabelsplitchardrop=true curvelabelsplit=true curvelabelattrs=(color=black size=6);       discretelegend 'scatter' / opaque=false border=true halign=right valign=bottom                   displayclipped=true across=1 order=rowmajor location=inside;     endlayout;   endgraph;   end; run;   ods listing image_dpi=1200 gpath="c:\temp" style=mypng; ods graphics on / reset=all imagename="test1" imagefmt=png width=690px height=480px noborder;   proc sgrender data=test template=sgdesign; run; quit;   ods listing close; ods graphics off;   ... View more

I want to create a graph using GTL (SAS 9.4) which completely uses CMYK pure process black color. I replaced (hopefully) all colors in my style definition with CMYK color black (CMYK000000FF) or white (CMYK00000000) and create my statgraph definitions. The figure as PDF file looks as expected, but looking into the color scheme, black is not presented as pure black (CMYK000000FF) but as a combination of RGB values (e.g., cyan 75%, magenta 68%, yallow 67%, process black 90%).. Are thee any hints or ideas what's going wrong?   Here's my code (looks long because of all the color defintions): %LET color=CMYK000000FF; %**** Define the template; %let __font = %str(Arial); %let __fontsz = %str(8pt); %let __fontsz2 = %str(6pt); proc template; define style cmfm; parent=styles.listing; style color_list "Colors used in the listing style" / 'fgB2' = CMYK000000FF 'fgB1' = CMYK000000FF 'fgA4' = CMYK000000FF 'bgA4' = CMYK000000FF 'bgA3' = CMYK00000000 'fgA2' = CMYK000000FF 'bgA2' = CMYK000000FF 'fgA1' = CMYK000000FF 'bgA1' = CMYK000000FF 'fgA' = CMYK000000FF 'bgA' = CMYK00000000; style GraphColors "Abstract colors used in graph styles" / 'goffill' = CMYK000000FF 'gofill' = CMYK000000FF 'govbline' = CMYK000000FF 'gobline' = CMYK000000FF 'gncdata12' = CMYK000000FF 'gndata12' = CMYK000000FF 'gncdata11' = CMYK000000FF 'gndata11' = CMYK000000FF 'gncdata10' = CMYK000000FF 'gndata10' = CMYK000000FF 'gncdata9' = CMYK000000FF 'gndata9' = CMYK000000FF 'gncdata8' = CMYK000000FF 'gndata8' = CMYK000000FF 'gncdata7' = CMYK000000FF 'gndata7' = CMYK000000FF 'gncdata6' = CMYK000000FF 'gndata6' = CMYK000000FF 'gncdata5' = CMYK000000FF 'gndata5' = CMYK000000FF 'gncdata4' = CMYK000000FF 'gndata4' = CMYK000000FF 'gncdata3' = CMYK000000FF 'gndata3' = CMYK000000FF 'gncdata2' = CMYK000000FF 'gndata2' = CMYK000000FF 'gncdata1' = CMYK000000FF 'gndata1' = CMYK000000FF 'gncdata' = CMYK000000FF 'gndata' = CMYK000000FF 'gnclink' = CMYK000000FF 'gnlink' = CMYK000000FF 'gntext' = CMYK000000FF 'gblockheader' = CMYK000000FF 'gcphasebox' = CMYK000000FF 'gphasebox' = CMYK000000FF 'gczonec' = CMYK000000FF 'gzonec' = CMYK000000FF 'gczoneb' = CMYK000000FF 'gzoneb' = CMYK000000FF 'gzonea' = CMYK000000FF 'gcunder' = CMYK000000FF 'gunder' = CMYK000000FF 'gcover' = CMYK000000FF 'gover' = CMYK000000FF 'gcfinal' = CMYK000000FF 'gfinal' = CMYK000000FF 'gcinitial' = CMYK000000FF 'ginitial' = CMYK000000FF 'gcother' = CMYK000000FF 'gother' = CMYK000000FF 'gcmiss' = CMYK000000FF 'gmiss' = CMYK000000FF 'gablock' = CMYK000000FF 'gblock' = CMYK000000FF 'gcclipping' = CMYK000000FF 'gclipping' = CMYK000000FF 'gcstars' = CMYK000000FF 'gstars' = CMYK000000FF 'gcruntest' = CMYK000000FF 'gruntest' = CMYK000000FF 'gccontrollim' = CMYK000000FF 'gcontrollim' = CMYK000000FF 'gcerror' = CMYK000000FF 'gerror' = CMYK000000FF 'gcpredictlim' = CMYK000000FF 'gpredictlim' = CMYK000000FF 'gcpredict' = CMYK000000FF 'gpredict' = CMYK000000FF 'gcconfidence2' = CMYK000000FF 'gcconfidence' = CMYK000000FF 'gconfidence2' = CMYK000000FF 'gconfidence' = CMYK000000FF 'gcfit2' = CMYK000000FF 'gcfit' = CMYK000000FF 'gfit2' = CMYK000000FF 'gfit' = CMYK000000FF 'gcoutlier' = CMYK000000FF 'goutlier' = CMYK000000FF 'gcdata' = CMYK000000FF 'gdata' = CMYK000000FF 'greferencelines' = CMYK000000FF 'gheader' = colors('docbg') 'gconramp3cend' = CMYK000000FF 'gconramp3cneutral' = CMYK00000000 'gconramp3cstart' = CMYK000000FF 'gramp3cend' = CMYK000000FF 'gramp3cneutral' = CMYK000000FF 'gramp3cstart' = CMYK000000FF 'gconramp2cend' = CMYK000000FF 'gconramp2cstart' = CMYK000000FF 'gramp2cend' = CMYK000000FF 'gramp2cstart' = CMYK000000FF 'gtext' = CMYK000000FF 'glabel' = CMYK000000FF 'gborderlines' = CMYK000000FF 'goutlines' = CMYK000000FF 'ggrid' = CMYK000000FF 'gaxis' = CMYK000000FF 'gshadow' = CMYK000000FF 'glegend' = CMYK00000000 'gfloor' = CMYK00000000 'gwalls' = CMYK00000000 'gcdata12' = CMYK000000FF 'gcdata11' = CMYK000000FF 'gcdata10' = CMYK000000FF 'gcdata9' = CMYK000000FF 'gcdata8' = CMYK000000FF 'gcdata6' = CMYK000000FF 'gcdata7' = CMYK000000FF 'gcdata4' = CMYK000000FF 'gcdata5' = CMYK000000FF 'gcdata3' = CMYK000000FF 'gcdata2' = CMYK000000FF 'gcdata1' = CMYK000000FF 'gdata12' = CMYK000000FF 'gdata11' = CMYK000000FF 'gdata10' = CMYK000000FF 'gdata9' = CMYK000000FF 'gdata8' = CMYK000000FF 'gdata6' = CMYK000000FF 'gdata7' = CMYK000000FF 'gdata4' = CMYK000000FF 'gdata5' = CMYK000000FF 'gdata3' = CMYK000000FF 'gdata2' = CMYK000000FF 'gdata1' = CMYK000000FF; style GraphAxisLines / ContrastColor=&color; style GraphData1 / ContrastColor=&color Linestyle=1 markersymbol = "Circle"; style GraphData2 / ContrastColor=&color Linestyle=4 markersymbol = "Square"; style GraphData3 / ContrastColor=&color Linestyle=2 markersymbol = "Diamond"; style GraphData4 / ContrastColor=&color Linestyle=1 markersymbol = "CircleFilled"; style GraphData5 / ContrastColor=&color Linestyle=4 markersymbol = "SquareFilled"; style GraphData6 / ContrastColor=&color Linestyle=2 markersymbol = "DiamondFilled"; end; run;   proc template; define statgraph Graphics.timechange_a; dynamic _title1 _title2 _title3 _footnote1 _footnote2 _footnote3 _xvar _xlabel _yvar1 _ylabel _group _displayopt ; mvar __nullrep; begingraph / border=0 ; /* layout lattice ;*/ /* Graph layout declaration */ layout overlay / pad=0 border = false walldisplay = none xaxisopts = ( label = ( "Week" ) labelattrs = (color=&color weight=normal size=&__fontsz family="&__font") tickvalueattrs = (color=&color weight=normal size=&__fontsz family="&__font") offsetmin = 0.05 offsetmax = 0.05 linearopts = (tickvaluesequence=(start=0 end=24 increment=6)) display = _displayopt ) yaxisopts = ( label = ( "Adjusted* Mean A1C (%) Change from Baseline") labelattrs = (color=&color weight=normal size=&__fontsz family="&__font") tickvalueattrs = (color=&color weight=normal size=&__fontsz family="&__font") offsetmin = 0.05 offsetmax = 0.05 linearopts = (tickvaluesequence=(start=-2.5 end=1.5 increment=0.5) tickvalueformat=4.1 viewmin=-2.0 viewmax=0.5) display = _displayopt ) opaque = false ; /* line - stepped */ seriesplot x=_xvar y=_yvar1 / connectorder = xvalues display = all lineattrs=(thickness=1px) group=_group name="seriesA"; discretelegend "seriesA" / location=outside across=1 valueattrs=(color=&color weight=normal size= 10pt family="&__font") halign=left valign=bottom backgroundcolor=white opaque=1 border=FALSE ; endlayout; /* Add titles and footnotes */ entryfootnote halign=left textattrs=(color=&color weight=normal size=&__fontsz family="&__font") _footnote1 / textfitpolicy=wrap; entryfootnote halign=left textattrs=(color=&color weight=normal size=&__fontsz family="&__font") _footnote2 / textfitpolicy=wrap; entryfootnote halign=left textattrs=(color=&color weight=normal size=&__fontsz family="&__font") _title1 / textfitpolicy=wrap pad=(top=3px); entryfootnote halign=left textattrs=(color=&color weight=normal size=&__fontsz family="&__font") _title2 / textfitpolicy=wrap; entryfootnote halign=right textattrs=(color=&color weight=normal size=&__fontsz family="&__font") _footnote3 / textfitpolicy=wrap; endgraph; end; run;   ODS LISTING STYLE=cmfm image_dpi=300 GPATH="\\client\C$\temp\test" ; ODS GRAPHICS ON / RESET=all IMAGENAME="adhoc12353_4" IMAGEFMT=pdf WIDTH=7.7cm NOBORDER ; /* Produce graph */ proc sgrender data=inplot template=Graphics.timechange_a object=CMF objectlabel="Time plot"; DYNAMIC _title1 =" " _title2 =" " _footnote1 = "" _footnote2 = "*Variables used in adjustment: Baseline A1C and prior use of OADs" _footnote3 = " " _xvar = "tptno" _yvar1 = "estimate" _group = "atrsort" _displayopt="all" ; format atrsort $_trt1v.; run;     ... View more