Plotting Segmented regression analysis of interrupted time series data

[sumitraybardhan]

Hello!

I was wondering how best to tackle the following dataset regarding antibiotic utilization and a policy intervention:

Date            Abx_Utilization       Intervention   Time

Feb2013           365                         0                 1

.

.

.

Jan2017           456                         1                 48

The antibiotic utlization is a rate, the intervention was implemented on Feb 2016 - i have coded '0' for time before intervention and '1' as time after intervention.

I would like to plot abx_utilization*time and show the trendline without the intervention and the trendline with the intervention. Similar to this example listed previously by a user (Figure 1a https://www.cdc.gov/pcd/issues/2013/12_0268.htm)

Many thanks for the insights!

[DanH_sas]

Try something like this:

proc sgplot data=intervention;

reg x=date y=abx_utilization / nomarkers group=intervention;

series x=date y=abx_utilization / markers markerattrs=(symbol=circlefilled);

run;

You will probably want to format 0 and 1 to some meaningful text for the legend.

Hope this helps!

Dan