Performance measures - Revision history

Wbuytaert at 15:08, 15 September 2008

2008-09-15T15:08:24Z

Wbuytaert at 17:48, 3 August 2008

2008-08-03T17:48:01Z

Wbuytaert at 17:47, 3 August 2008

2008-08-03T17:47:13Z

Wbuytaert at 04:38, 5 May 2008

2008-05-05T04:38:57Z

Wbuytaert at 04:38, 5 May 2008

2008-05-05T04:38:48Z

Wbuytaert at 04:37, 5 May 2008

2008-05-05T04:37:42Z

New page

[[Category:Projects]]
[[Category:Hydrology in R]]
==Introduction==

Here is a selection of measures you can use for assessing the performance of your model.

===Nash-Sutcliffe efficiency===

This one is implemented as NSeff() in the topmodel package, and takes two vectors, containing the simulated (Qsim) and observed (Qobs) discharge:

NSeff <- function (Qobs, Qsim)
{
Qsim <- Qsim[!is.na(Qobs)]
Qobs <- Qobs[!is.na(Qobs)]
Qobs <- Qobs[!is.na(Qsim)]
Qsim <- Qsim[!is.na(Qsim)]
NS <- 1 - (sum((Qobs - Qsim)^2)/sum((Qobs - mean(Qobs))^2))
return(NS)
}

Eff <- NSeff(Qobs,Qsim)

@@ Line 33: / Line 33: @@
 ===Root mean squared error===
-The [http://en.wikipedia.org/wiki/Root_mean_square_deviation root mean squared error] is the square root of the variance:
+As the name suggests, the root mean squared error is the square root of the [http://en.wikipedia.org/wiki/Mean_squared_error mean squared error]:
-    RMSE <- cov(Qobs, Qsim, use="complete.obs")^0.5
+    RMSE <- (mean((Qobs - Qsim)^2))^0.5

@@ Line 28: / Line 28: @@
 The [http://en.wikipedia.org/wiki/R-squared coefficient of determination] is the square of the Pearson's product-moment correlation coefficient. Note that the COD only evaluates linear relations between variables!
-    COD <- cor(Qobs,Qsim, use="complete.obs")^2
+    COD <- cor(Qobs, Qsim, use="complete.obs")^2
@@ Line 35: / Line 35: @@
 The [http://en.wikipedia.org/wiki/Root_mean_square_deviation root mean squared error] is the square root of the variance:
-    RMSE <- cov(Qobs,Qsim, use="complete.obs")^0.5
+    RMSE <- cov(Qobs, Qsim, use="complete.obs")^0.5

@@ Line 4: / Line 4: @@
 Here is a selection of measures you can use for assessing the performance of your model.
 ===Nash-Sutcliffe efficiency===
-This one is implemented as NSeff() in the topmodel package, and takes two vectors, containing the simulated (Qsim) and observed (Qobs) discharge:
+The [http://en.wikipedia.org/wiki/Nash-Sutcliffe_efficiency_coefficient Nash-Sutcliffe efficiency] is a widely used performance measure based on the error variance. It is implemented as ''NSeff()'' in the topmodel package. It takes two vectors, containing the simulated (Qsim) and observed (Qobs) discharge:
     NSeff <- function (Qobs, Qsim){
@@ Line 17: / Line 22: @@
        return(NS)
+    }
-    Eff <- NSeff(Qobs,Qsim)