As the first step in the decommissioning of sasCommunity.org the site has been converted to read-only mode.


Here are some tips for How to share your SAS knowledge with your professional network.


Difference between revisions of "Tip of the Day:August 30"

From sasCommunity
Jump to: navigation, search
m (Scheduled Use The SAS Sample Program Libraries)
(Scheduled Corrected Sum of Squares in PROC NLIN)
 
Line 5: Line 5:
 
sasCommunity Tip of the Day
 
sasCommunity Tip of the Day
 
</h1><div style="padding:10px;">
 
</h1><div style="padding:10px;">
{{Tips:Use The SAS Sample Program Libraries}}
+
{{Tips:Corrected Sum of Squares in PROC NLIN}}
 
<div style="width:100%"><hr></div>
 
<div style="width:100%"><hr></div>
Feel free to [[Tips Talk:Use The SAS Sample Program Libraries|comment]] on this tip.
+
Feel free to [[Tips Talk:Corrected Sum of Squares in PROC NLIN|comment]] on this tip.
 
</div>
 
</div>
 
</td></tr>
 
</td></tr>

Latest revision as of 21:43, 28 August 2010

sasCommunity Tip of the Day

When you are using the PROC NLIN to estimate the models, the corrected sum of squares is not reported when the intercept is not defined. To get the corrected sum of squares, one can use PROC MEANS to calculate it.

In the following steps, the CSS option in PROC MEANS requests the corrected sum of squares for the response, Y:

proc nlin data = a;
    parms b0 = 0
          b1 = .01;
    model y = b0 * (1 - exp(-b1 * x));
run;
 
proc means data = a css;
    var y;
run;

Submitted by Murphy Choy. Contact me at my Discussion Page.




Feel free to comment on this tip.


Prior tip - Next tip - Random Tip

Submit a Tip