Plot the data precisely?

Author: Xuanqian Xie

The plots were prepared for Zheng etal 2013, but the final publication dropped it out.

One figure used the increment of 0.2 cm and the other one used the increment of 0.5 cm. The smaller increments plot is precise, but I feel that increment of 0.5 is better, as it illustrate the patter of the distribution. Sometimes, “precise” crude results have many noises, and then the trend of data is not easy to be visualized.

 

Reference:

Zheng J, Alsaadi T, Blaichman J, Xie X, Omeroglu A, Meterissian S, Mesurolle B. Invasive ductal carcinoma of the breast: correlation between tumor grade determined by ultrasound-guided core biopsy and surgical pathology. AJR Am J Roentgenol. 2013; 200(1):W71-4  Link: http://www.ncbi.nlm.nih.gov/pubmed/23255773

 

A few line SAS program of the plot:

proc univariate data=biopsy freq normal;

   var Size; label Size="Tumor size (cm)";

   histogram size / normal(noprint color=(red) w=3 )

                      BARLABEL=COUNT

                      midpoints=0 to 8 by 0.5 ;

   inset normal(mu sigma) / pos=ne ;

run;

 

proc univariate data=biopsy freq normal;

   var Size; label Size="Tumor size (cm)";

   histogram size / normal(noprint color=(red) w=3 )

                      BARLABEL=COUNT

                      midpoints=0 to 8 by 0.2

                      vaxis=0 to 18 by 2;

   inset normal (mu sigma)/ pos=ne ;

run;

 

proc univariate data=biopsy freq normal;

   var Size; label Size="Tumor size";

   histogram size /

                      BARLABEL=COUNT

                      midpoints=0 to 8 by 0.5 ;

run;