Dear R users,
I am comparing two data sets (CO2 observation vs. CO2 simulation, during
1993-2002).
In order to do it I am calculating Root-Mean-Square(RMS) difference
with following formula:
> sqrt(sum((observed_residual - simulated_residual)^2)/n) # 'n' is
number of
observations
Residuals are computed by fitting a harmonic function on both the
data:>testfit<-lm(co2obs~1+time+I(time^2)+sin(2*pi*time)+cos(2*pi*time)+sin(4*pi*time)+cos(4*pi*time)+sin(6*pi*time)+cos(6*pi*time)+sin(8*pi*time)+cos(8*pi*time),data=file)
#
>testfit1<-lm(co2model~1+time+I(time^2)+sin(2*pi*time)+cos(2*pi*time)+sin(4*pi*time)+cos(4*pi*time)+sin(6*pi*time)+cos(6*pi*time)+sin(8*pi*time)+cos(8*pi*time),data=file)#
'time' is time of observation
testfit$residuals # observed.residuals # (saved in seperate file by
write.table)
testfit1$residuals # modeled.residuals# (saved in seperate file by
write.table)
I am interested to to see climatology of RMS difference (all Jan months, all
Feb months, all March months,.............,all Dec months),
So I am computing like following:
time_span <- file[(file$mo==1),] # for 'Jan' month (similarly for
other
months)
time_span
sub_seaobs <- (time_span$observed. residual)
sub_seaobs
sub_seatm3 <- (time_span$modeled.residual)
sub_seatm3
sqrt(sum((sub_seaobs-sub_seatm3)^2)/n) # 'n' is number of observation in
particular month
QUESTION:
I want to know if I am doing right and is it best way of computing
clomatology of Root-Mean-Square difference between two data sets.
--
Yogesh K. Tiwari (Dr.rer.nat),
Scientist,
Indian Institute of Tropical Meteorology,
Homi Bhabha Road,
Pashan,
Pune-411008
INDIA
Phone: 0091-99 2273 9513 (Cell)
: 0091-20-258 93 600 (O) (Ext.250)
Fax : 0091-20-258 93 825
[[alternative HTML version deleted]]