BookmarkSubscribeRSS Feed
abudyak
Calcite | Level 5

Can anyone explain why I keep getting this note: 

NOTE: c1 is not estimable.
NOTE: CONTRAST c1 is not estimable.
It will not print out the contrast because of this. I tried other contrasts and I get the same result even though it worked before.
data car;
infile cards expandtabs;
input mm year mpg @@;
cards;
1	2005	26.5
2	2005	24.5
3	2005	27.5
4	2005	30.5
5	2005	20.5
6	2005	26.5
7	2005	29
8	2005	26.5
1	2010	23.5
2	2010	22.5
3	2010	27.5
4	2010	28.5
5	2010	21.5
6	2010	23.5
7	2010	27.5
8	2010	27
1	2015	26.5
2	2015	26
3	2015	32.5
4	2015	30
5	2015	25
6	2015	26
7	2015	30
8	2015	28.5
1	2020	23.5
2	2020	25
3	2020	33.5
4	2020	28.5
5	2020	25
6	2020	27
7	2020	35
8	2020	32
;

proc glm data=car;
	class mm year;
	model mpg= mm year;
	output out=car1 predicted=ypred residual=res;
	means mm year;
run;

proc univariate data=car1 plot normal;
	var res;
run;

proc glm data=car1;
	class mm year;
	model mpg= mm year;
	estimate 'c1' mm 0 0 1 -1 0 0 -1 0;
	contrast 'c1' mm 0 0 1 -1 0 0 -1 0;
run;
1 REPLY 1
PGStats
Opal | Level 21

The values of the linear hypothesis vector should sum up to zero, for example:

 

proc glm data=car1;
	class mm year;
	model mpg= mm year;
	estimate 'c1' mm 0 0 2 -1 0 0 -1 0;
	contrast 'c1' mm 0 0 2 -1 0 0 -1 0;
run;
PG

hackathon24-white-horiz.png

The 2025 SAS Hackathon has begun!

It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.

Latest Updates

How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 1 reply
  • 859 views
  • 0 likes
  • 2 in conversation