lisahoward Tracker

Re: Statistical significance differences syntax

lisahoward — Thu, 27 Aug 2015 16:15:36 GMT

9.2

Re: Statistical significance differences syntax

lisahoward — Thu, 27 Aug 2015 15:58:47 GMT

Thank you for your quick response when you mention 'Read the documentation - specifically the Examples section for each, they have worked through examples.' Where will I find this?

Statistical significance differences syntax

lisahoward — Thu, 27 Aug 2015 15:10:36 GMT

Hello I wondered if I could get some help me get started with the correct SAS syntax required to perform the following tests on my data.

using the example Cohort/variables I have made up below .

Statistical significance of differences Continuous variables - Wilcoxon rank sum tests prior to matching .

Statistical significance of differences Continuous variables - Wilcoxon signed-rank tests post-match.

Statistical significance of differences Categorical variables,prior to matching will be assessed using chi-squared tests.

Statistical significance of differences Categorical variables, after matching using McNemar’s tests.

Disease Cohort Control Cohort

Cat Variables Diabetes(yes/no) 1 0

Gender 1 2

Continuous Variable Age 80 30

Once I understand the basic syntax I can then incorporate it into a macro to run over all my categorical and continuous variables.

Many thanks in advance.

SAS proc report to PDF , truncating text

lisahoward — Tue, 11 Aug 2015 11:39:44 GMT

I am trying to output to the following proc report to a PDF file using the following code. However my narrative variable gets truncated if it is longer than one PDF page. One page is fine but if it spans over two pages it is truncated at the end of the first page. Does anyone have any help on how to stop the truncation of the narrative field.

Many thanks.

proc report data=patient headline headskip split='\' nowd;

where casenumber=&casenum;

column casenumber narrative comment_text abbrev_narrative seriousness_desc serious_notes causality

agent_notes listedness listedness_notes outcome_desc;

define casenumber / order id noprint;

define narrative / display width=50 'Narrative' flow;

define comment_text / display width=50 Analysis Statement' flow;

define abbrev_narrative / display width=40 Comment' flow page;

define seriousness_desc / display width=20 'Case Seriousness';

define serious_notes / display width=20 'Notes' flow;

define causality / display width=10 'Case Causality';

define agent_notes / display width=20 'Notes' flow;

define listedness / display width=14 'Listedness Determination';

define listedness_notes / display width=20 'Notes' flow;

define outcome_desc / display width=20 'Case Outcome' page;

compute before _page_;

line @3 'CASE ASSESSMENT';

line @4 ' ';

endcomp;

ods pdf startpage=now;

%macro loop(list=);

%if %sysfunc(exist(work.check1)) %then %do;

%* Initialize loop;

%let i=1;

%let casei=%scan(&list,&i,str(,));

%* Run loop;

%do %while (&casei ne);

dm 'odsresults; clear';

ods listing close;

options papersize=a4 leftmargin=3.5 cm rightmargin=3.5 cm;

ods pdf file = "C:\temp\CaseNumber &casei..pdf" style = sasweb;

ods escapechar='~';

footnote1 j=c 'Page ~{thispage} of ~{lastpage} ';

footnote2 j=r 'Report Generated on ' &sysdate9;

ods pdf startpage=no;

%* Do processing for this iteration of the loop;

%put PROCESSING CASE NUMBER &casei;

%casereport(casenum=&casei);

%* Prepare for next iteration of the loop;

%let i=%eval(&i+1);

%let casei=%scan(&list,&i,str(,));

ods pdf close;

ods listing;

%end;

%else %do;

%display logonerror;

%end;

dm 'odsresults; clear';

%mend loop;

Re: Hazard Ratio Plot

lisahoward — Mon, 01 Jun 2015 10:14:23 GMT

I am not sure how to attach a file, so have copied and pasted the information from the dataset HR&infile created by the proc phreg procedure

Parameter Standard Hazard 95% Hazard Ratio

Parameter DF Estimate Error Chi-Square Pr > ChiSq Ratio Confidence Limits Label

Exposure 0 1 -12.89787 0.26728 2328.6241 <.0001 0.000 0.000 0.000 Exposure 0

Age_At_Index 1 0.04090 0.00188 473.8845 <.0001 1.042 1.038 1.046

trtt 1 -2.24461 0.04631 2349.3378 <.0001 0.106 0.097 0.116

Hazard Ratio Plot

lisahoward — Mon, 01 Jun 2015 09:23:20 GMT

Hello,

I am trying to create a line graph showing Hazard Ratio over time using the following axis below:

Hazard Ratio 6

0 20 40 60 80 100 120 140

Time

I have create the hazard ratios for the tables but am unsure now how to plot them and what procedure I need to use to create the plot. If anyone can help to get me started that would be great.

Here is the syntax used to create ratios:

Proc phreg data=&infile;

class exposure;

Model personyrs*outcome(0) = exposure &covariates trtt /RISKLIMITS;;

trtt = exposure*log(PersonTime);

test_proportionality: TEST trtt;

ods output ParameterEstimates=HR&infile;

title1 "Proc PHREG for adjusted";

run;

Re: Selecting colours for plot lines by grouping variable

lisahoward — Thu, 14 May 2015 13:56:39 GMT

great thank you.

Re: Selecting colours for plot lines by grouping variable

lisahoward — Thu, 14 May 2015 13:32:03 GMT

Hi do you know if It is possible to combine my proc template and the macro ?

proc template;

define style myfont;

parent=styles.default;

style GraphFonts /

'GraphFootnoteFont' = ("Arial",10pt,bold)

'GraphTitleFont' = ("Arial",6pt,bold)

'GraphValueFont' = ("Arial",8pt)

'GraphAnnoFont' =("Arial", 10pt)

'GraphUnicodeFont'=("Arial", 10pt)

'GraphLabelFont'=("Arial", 10pt)

'GraphDataFont'=("Arial", 10pt);

end;

run;

and

%modstyle(

parent=statistical,

name=plotmod,

type=CLM,

colors=red blue,

fillcolors=colors,

markers=triangefilled circlefilled

);

Re: Selecting colours for plot lines by grouping variable

lisahoward — Thu, 14 May 2015 12:57:42 GMT

great thank you for your help. I wanted to use minor tickmarks on the horizontal axis and offset the graoh slighty on the left so there was some space between the graph and the border but I am unsure how to do this. In terms of the label on the vertical axess i would like to rotate it 90 degrees but again am unsure of the syntax.I will take a look at the blog mentioned above to see if I can find the answer. thank you again for all your help.

Re: Selecting colours for plot lines by grouping variable

lisahoward — Thu, 14 May 2015 11:50:47 GMT

9.2.

I am also trying to figure out how to get minor tick marks on the horizontal axis and rotate the label on the vertical access.

Many thanks in advance, SAS graph is new to me

Re: Selecting colours for plot lines by grouping variable

lisahoward — Thu, 14 May 2015 11:12:28 GMT

Hi I decided et go with Sgplot and use the code below:

proc sgplot data=DM_Work.All_Rates;

series x=TIME y=IR / group=TestRx markers lineattrs=(pattern=solid ) ;

REFLINE 1 2 3 4 ;

		XAXIS TYPE = DISCRETE;
		yaxis label = 'AMI Rate per 1000' ;

xaxis label = 'Time in Days ' grid values = (-360 to 360 by 30);

run

However I want to change the markers so they are filled triangle and filled Circle. How do I do this when using the group = option ?

Many thanks in advance.

Lucy

Selecting colours for plot lines by grouping variable

lisahoward — Wed, 13 May 2015 09:41:22 GMT

Hello,

I have the following syntax:

proc gplot data=DM_Work.All_Rates;

plot ir*time=testrx / vaxis = axis1 haxis=axis2

legend=legend1;

run;

I would like to specify the colour for the grouping variable TestRX. TestRX groups treated v untreated. I am not sure how to make one line blue and one line red.

Any help with the syntax would be greatly appreciated.

Creating a graph showing incidence rate

lisahoward — Tue, 12 May 2015 15:10:44 GMT

I am trying to create graph plotting incidence rate of headache at -30 day intervals prior to baseline date

I am unsure how to calculate the negative person time for each time point to create the rate.

My graph will have the following x and y axis -365-0 for the time points and rates per 1000.

rate per 1000
1
0.5
0
-365	-330	-300	-270
timepoint

I have the following variables in my SAS dataset, Patient ID, baseline date (which will be represented be the 0 time point on my graph), headache (0/1), and headache date. A patient can only have one headache max which is the earliest within the prior baseline 365 days. Any help in calculating the rate for each negative timepoint and then plotting it as a graph would be great.

Many thanks,

Lisa.

Re: Proc GENMOD Class question

lisahoward — Sun, 26 Apr 2015 11:44:31 GMT

Thank you again for all your help. I am doing both Cox and Poisson.

Re: Proc GENMOD Class question

lisahoward — Sun, 26 Apr 2015 09:25:07 GMT

I have not included a scale option. I just want your advice if this is correct. I have been reading about PSCALE and DSCALE this morning before bothering you again and tried to understand if I needed this option , but am still unclear. Many thanks.

Re: Proc GENMOD Class question

lisahoward — Sun, 26 Apr 2015 05:34:47 GMT

Thank you Jacob I created an offset variable and then included it in my procedure:

proc genmod data=IRsforCohort;

class Exposure &covariates ;

model outcome=Exposure &covariates Age_At_Index IndexYear / dist = poisson offset=myoffset link=log type3;

Estimate ' 1 Vs 0' Exposure 1 -1 ;

ods output Estimates=RR&infile._adj;

title1 "Proc GENMOD for Adjusted &infile &time";

run;

I changed the IR variable I had created in a previous data step and now use the Outcome variable instead so have outcome=Exposure.

I get the following results. In your opinion you think I should use the Mean rather than the LBeta variables to show relative risk for

Treatment Difference in Headache rate during 90 days follow-up period for treated and untreated group

Contrast Estimate Results

Mean Mean L'Beta Standard L'Beta Chi-

Label Estimate Confidence Limits Estimate Error Alpha Confidence Limits Square Pr > ChiSq

1 Vs 0 0.9714 0.5534 1.7049 -0.0291 0.2870 0.05 -0.5916 0.5335 0.01 0.9194

Re: Proc GENMOD Class question

lisahoward — Sat, 25 Apr 2015 16:40:15 GMT

Sorry to bother you again. I put the syntaxwith outcome=EXPOSURE instead or IR=EXPOSURE to the left of =, But i think i have the 'offset=log(PersonYrs'' bit wrong as I get an error. Please can you help, I have created PersonYrs so this variable exists in the IRsforCohort dataset.

thanks.

proc genmod data=IRsforCohort;

class EXPOSURE &covariates ;

model outcome=EXPOSURE &covariates Age_At_Index IndexYear / dist = poisson offset=log(PersonYrs) link=log type3;

Estimate ' 1 Vs 0' EXPOSURE 1 -1 ;

ods output Estimates=RR&infile._adj;

title1 "Proc GENMOD for Adjusted &infile &time";

run;

ERROR: Variable LOG not found.

ERROR 22-322: Syntax error, expecting one of the following: ;, A, AGGREGATE, ALPH, ALPHA, CICONV, CL, CLCONV, CODING, CONVERGE, CONVH,

CORRB, COVB, D, DIAGNOSTICS, DIST, DSCALE, ERR, ERROR, EXPECTED, ID, INFLUENCE, INITIAL, INTERCEPT, ITPRINT, LINK, LOGNB,

LRCI, LRCL, MAXIT, MAXITER, NOINT, NOLOGNB, NOPRINTCL, NOSCALE, OBSTAT, OBSTATS, OFFSET, P, PRED, PREDICTED, PSCALE, R,

RESIDUAL, RORDER, SCALE, SCORING, SINGULAR, TYPE1, TYPE3, TYPE3WALD, WALD, WALDCI, WALDCL, XVARS.

Re: Proc GENMOD Class question

lisahoward — Sat, 25 Apr 2015 16:07:11 GMT

Great thank you so much I am very appreciatl=ive of the time you have taken to answer my questions. I already created person years in a previous data step so that I could calculate the Incidence rate of the outcome. I use the IR in the model statement:

IR=Exposure . So I will include the Person years variable in the offset option. I presume I am correct in ssuming it should be IR=Exposure and not Outcome=Exposure as the spec wording I am going off in the protocol is :

Unadjusted model: Headace rate = Exposure;

Adjusted model: AMI rate =Exposure Group + Age+ indexyear + baseline risk factors

I am assuming Headache rate is Incidence Rate and not Outcome .?

Re: Proc GENMOD Class question

lisahoward — Sat, 25 Apr 2015 15:43:40 GMT

Hi ,

How would I go about creating offset=log(personyears).

This is my current syntax:

ods listing;

proc genmod data=IRsforCohort;

class TestRx &covariates ;

model IR=TestRX &covariates Age_At_Index IndexYear / dist = poisson link=log type3;

Estimate ' 1 Vs 0' testrx 1 -1 ;

ods output Estimates=RR&infile._adj;

title1 "Proc GENMOD for Adjusted &infile &time";

run;

Do I just add (in bold):

ods listing;

proc genmod data=IRsforCohort;

class TestRx &covariates ;

model IR=TestRX &covariates Age_At_Index IndexYear / dist = poisson offset= personyears link=log type3;

Estimate ' 1 Vs 0' testrx 1 -1 ;

ods output Estimates=RR&infile._adj;

title1 "Proc GENMOD for Adjusted &infile &time";

run;

Re: Proc GENMOD Class question

lisahoward — Sat, 25 Apr 2015 14:57:21 GMT

Dear Jacob,

Thank you so much for your help.

I will modify the syntax to include all categorical variables in the class statement only and then in the model statement i will include the categorical variables + age and year of index. I appreciate your help.

Could I ask your advice on the offset option please. Should I include this , I am unsure what and how this will effect the RR. The question I am trying to answer or the RR I am trying to get is based on the following:

Treatment Difference in the Diagnosis (Headache) Incidence rate , during the follow-up period (defined as 90 days) between treated and untreated group.

I am doing both unadjusted and adjusted Relative Rates.

Also should I be displaying the LBETA estimate value or the mean estimate value in my report to represent the RR value? I apologise I am not a statistician so any advice is truly appreciated.

Many thanks in advance.