Freq table output not running correctly

[ashb]

I want to run a frequency table that counts the number of observations with or without hypertension and displays them. My frequency table keeps coming out wrong and I am not sure how to fix it. Here is the code:

data bpx_j;
	set libref.bpx_j;
	AvgSystolic = MEAN(bpxsy1,bpxsy2,bpxsy3,bpxsy4);
	AvgDiastolic = MEAN(bpxdi1,bpxdi2,bpxdi3,bpxdi4);
	CountSystolic = N(bpxsy1,bpxsy2,bpxsy3,bpxsy4);
	CountDiastolic = N(bpxdi1,bpxdi2,bpxdi3,bpxdi4);
run;
proc freq data = work.bpx_j;
	tables CountSystolic CountDiastolic;
run;
proc means data = work.bpx_j;
	var AvgSystolic AvgDiastolic;
run;
proc print data = work.bpx_j;
run;
/*Part 2*/
proc format;
	value hypertensionD LOW -< 80 = 'No Hypertension'
						80 <- HIGH = 'Hypertension';
run;
proc format;
	value hypertensionS LOW -< 130 = 'No Hypertension'
						130 <- HIGH = 'Hypertension';
run;
proc freq data = work.bpx_j;
	tables AvgSystolic AvgDiastolic;
	Format AvgSystolic hypertensionS. AvgDiastolic hypertensionD.;
run;

This is what the output looks like:

[Reeza · Accepted solution]

Which category do you want 130 included in?

Try modifying your PROC FORMAT to the following and check how that works:

proc format;
value hypertensionD LOW - 80 = 'No Hypertension'
80 - HIGH = 'Hypertension';
value hypertensionS LOW - 130 = 'No Hypertension'
130 - HIGH = 'Hypertension';
run;

[ballardw]

Describe what is "wrong", exactly with the output.

You have an issue with your formats. Both of these have a value repeated in the ranges -< means "less than or equal",

   <- means "greater than or equal" , so "equal" is in both of these and yield unexpected results. Remove one of the - in each definition.

proc format;
	value hypertensionD LOW -< 80 = 'No Hypertension'
						80 <- HIGH = 'Hypertension';
run;
proc format;
	value hypertensionS LOW -< 130 = 'No Hypertension'
						130 <- HIGH = 'Hypertension';
run;

.

[Reeza]

And show the log...that output is definitely weird.

[ashb]

Here is the log:

NOTE: There were 8704 observations read from the data set LIBREF.BPX_J.
NOTE: The data set WORK.BPX_J has 8704 observations and 26 variables.
NOTE: DATA statement used (Total process time):
real time 0.11 seconds
cpu time 0.07 seconds

110 proc freq data = work.bpx_j;
111 tables CountSystolic CountDiastolic;
112 run;

NOTE: There were 8704 observations read from the data set WORK.BPX_J.
NOTE: PROCEDURE FREQ used (Total process time):
real time 0.06 seconds
cpu time 0.01 seconds

113 proc means data = work.bpx_j;
114 var AvgSystolic AvgDiastolic;
115 run;

NOTE: There were 8704 observations read from the data set WORK.BPX_J.
NOTE: PROCEDURE MEANS used (Total process time):
real time 0.06 seconds
cpu time 0.04 seconds

116 proc print data = work.bpx_j;
117 run;

NOTE: There were 8704 observations read from the data set WORK.BPX_J.
NOTE: PROCEDURE PRINT used (Total process time):
real time 13.07 seconds
cpu time 13.18 seconds

118 /*Part 2*/
119 proc format;
120 value hypertensionD LOW -< 80 = 'No Hypertension'
121 80 <- HIGH = 'Hypertension';
NOTE: Format HYPERTENSIOND is already on the library WORK.FORMATS.
NOTE: Format HYPERTENSIOND has been output.
122 run;

NOTE: PROCEDURE FORMAT used (Total process time):
real time 0.02 seconds
cpu time 0.01 seconds

123 proc format;
124 value hypertensionS LOW -< 130 = 'No Hypertension'
125 130 <- HIGH = 'Hypertension';
NOTE: Format HYPERTENSIONS is already on the library WORK.FORMATS.
NOTE: Format HYPERTENSIONS has been output.
126 run;

NOTE: PROCEDURE FORMAT used (Total process time):
real time 0.02 seconds
cpu time 0.01 seconds

127 proc freq data = work.bpx_j;
128 tables AvgSystolic AvgDiastolic;
129 Format AvgSystolic hypertensionS. AvgDiastolic hypertensionD.;
130 run;

NOTE: There were 8704 observations read from the data set WORK.BPX_J.
NOTE: PROCEDURE FREQ used (Total process time):
real time 0.08 seconds
cpu time 0.03 seconds

[ashb]

Thanks everyone! It finally worked after changing some things around.