[R] How to calculate the predicted value by using GAMs?

pigpigmeow glorykwok at hotmail.com
Sun Jun 24 11:06:35 CEST 2012


I really want to know how to calculate the predicted valued when I use
gam.predict .
my model is:
newSO2 ~ s(pressure, bs = "cr") + s(maxtemp, bs = "cr") + mintemp + 
    RH + solar + s(windspeed, bs = "cr") + s(transport, bs = "cr")
> my new dataset is :
pressure: -7.056847826	
maxtemp: 2.737507877	
mintemp:	3.51959342	
RH: 8.772944565	
Solar:0.200563855	
Windspeed: -6.319313706	
Transport:-380.5588726

the coefficient of formula is:
> coef(so2e)
   (Intercept)        mintemp             RH          solar  s(pressure).1 
s(pressure).2  s(pressure).3  s(pressure).4  s(pressure).5  s(pressure).6 
s(pressure).7  s(pressure).8  s(pressure).9   s(maxtemp).1   s(maxtemp).2 
    0.91148590     0.20798857     0.15072713     0.17296204     0.46080941    
0.23503683     0.09166914     0.06353043    -0.83130850    -1.36714869   
-0.84320333    -0.48964922    -4.85825675     0.55672881     0.26108141 
  s(maxtemp).3   s(maxtemp).4   s(maxtemp).5   s(maxtemp).6   s(maxtemp).7  
s(maxtemp).8   s(maxtemp).9 s(windspeed).1 s(windspeed).2 s(windspeed).3
s(windspeed).4 s(windspeed).5 s(windspeed).6 s(windspeed).7 s(windspeed).8 
    0.11775489     0.52515021    -0.47438941    -1.23068993    -1.01401703   
-0.97945967    -3.47972451     2.59486238     0.80366715     0.87556554    
0.88319105     1.64710232     1.39131761     1.03058868     1.10496623 
s(windspeed).9 s(transport).1 s(transport).2 s(transport).3 s(transport).4
s(transport).5 s(transport).6 s(transport).7 s(transport).8 s(transport).9 
    0.86143533    -0.92804349    -0.81012945    -1.75752608    -1.20780659   
-1.00271267    -1.79162143    -1.77980726    -1.80950105    -1.32644421 

the predict value is:

15531.17181



does anyone can help me and let me know how to calculate this predict
value?!
I really want to know!
Thank!
	

--
View this message in context: http://r.789695.n4.nabble.com/How-to-calculate-the-predicted-value-by-using-GAMs-tp4634317.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list