topic Re: How to show regression equation and calculate predicted value for new observation? in Statistical Procedures

How to show regression equation and calculate predicted value for new observation?

bigban777 — Wed, 30 Mar 2016 01:07:51 GMT

so,fo example i have this results (PROC REG). now i have to show regresson equaton (which is y=0.33096x+1028.57177) on my graph. Moreover, i need find "y" for different x?

Thank you.

Goal: Displaying Regression Equations in Fit Plots and use this equation to find "y" for certain x

Re: How to show regresson equaton and substitute?

Reeza — Wed, 30 Mar 2016 01:05:01 GMT

How are you making your graph? Where do you want to include equation?

Look at score and/or proc score to calculate predictions.

Re: How to show regression equation and calculate predicted value for new observation?

PGStats — Wed, 30 Mar 2016 02:24:13 GMT

If you are plotting using SGPLOT, use INSET statement to show the equation. If you want the predicted y values for your data x values, then use an OUTPUT statement in PROC REG. You can also create the SAS code for the calculation of predicted values in a separate data step with the CODE statement in PROC REG.

Re: How to show regression equation and calculate predicted value for new observation?

Ksharp — Wed, 30 Mar 2016 03:30:54 GMT


1) " calculate predicted value for new observation"
Put your train table and test table together, then you will magically find SAS has already done it for you .
2) "show regression equation "
Save these parameter and use proc sgplot get it .

I remember proc gplot can directly get the fitted function no need save these parameter. But I can't recall that .




data train;
 set sashelp.class(keep=weight height);
run;

data test;
 height=71;output;
 height=72;output;
run;

data have;
 set train test;
run;

proc reg data=have outest=est noprint;
model weight=height;
output out=want predicted=predicted;
run;
proc print data=want noobs;run;
data _null_;
 set est;
 call symputx('func',cats('weight=',intercept,'+',height,'*height'));
run;
proc sgplot data=train aspect=1;
reg x=height y=weight/ cli clm;
inset "&func"/ position=topleft textattrs=graphdata1(size=12);
run;

Re: How to show regression equation and calculate predicted value for new observation?

Rick_SAS — Wed, 30 Mar 2016 13:06:00 GMT

You didn't say what version of SAS you are using, but here how to use PROC SGPLOT to display the slope and intercept of a regression line.

If you want to get REALLY fancy, you can use string concatenation to construct an "equation" and display the equation.

There are many ways to score a regression model. See examples and explanations in this article: Techniques for scoring a regression model in SAS