![]() #Sas fitplot codeI will write up a detailed article with the code once SAS 9.4 is released. To do this, I have to merge the summary data with the original data. In the example below, I have created a custom box plot using the technique above, and then added display of all the values using jittering. We have received many requests on this topic so jittering will be supported with SAS 9.4. The code is shown in the program file attached.įinally, here is another sneak preview of a SAS 9.4 feature: Jittering. Then, we added a label to show the value of the mean in each box. So, have to use two highlow line plots, one from P90 to Q3 and one from Q1 to p10. In this example, we lightened the fill color by making it 50% transparent. In this example, we have added the display of the mean value above each mean marker. Since this graph is made up of all "Basic" plots, we can overlay any other basic plot we may want to display other features. This graph looks very similar to the standard VBOX except for the whiskers and outliers.The scatter plot draws the mean marker.The third high low plot of type=bar draws the lower quartile.The second high low plot of type=bar draws the upper quartile.The first high low plot of type=line (default) plots the whisker from P10 to P90.Grouporder=ascending clusterwidth= 0.7 markerattrs= (size= 9 ) Scatter x=type y= mean / group=origin groupdisplay=cluster ![]() Highlow x=type high=median low=q1 / group=origin type=bar Groupdisplay=cluster grouporder=ascending clusterwidth= 0.7 Highlow x=type high=q3 low=median / group=origin type=bar ![]() Highlow x=type high=p90 low=p10 / group=origin groupdisplay=cluster Proc sgplot data=CarsMeanMileage nocycleattrs ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |