plotscore {scoring} | R Documentation |
Given parameters for a two-alternative scoring rule, plot the hypothetical scores that would be obtained for each forecast/outcome combination.
plotscore(param = c(2, 0.5), fam = "pow", bounds, reverse = FALSE, legend = TRUE, ...)
param |
Numeric vector of length 2, containing the parameters for
|
fam |
scoring rule family. |
bounds |
Lower and upper bounds supplied to |
reverse |
|
legend |
Should a legend be displayed? Defaults to |
... |
Other arguments to |
For more information on the scoring rule families and the bounds
and reverse
arguments, see the details of calcscore()
.
Returns the result of a plot()
call that graphs the scoring rule.
Ed Merkle
Buja, A., Stuetzle, W., & Shen, Y. (2005). Loss functions for binary class probability estimation and classification: Structure and applications. (Obtained from http://stat.wharton.upenn.edu/~buja/PAPERS/)
Jose, V. R. R., Nau, R. F., & Winkler, R. L. (2008). Scoring rules, generalized entropy, and utility maximization. Operations Research, 56, 1146–1157.
Jose, V. R. R., Nau, R. F., & Winkler, R. L. (2009). Sensitivity to distance and baseline distributions in forecast evaluation. Management Science, 55, 582–590.
Merkle, E. C. & Steyvers, M. (in press). Choosing a strictly proper scoring rule. Decision Analysis.
## Plot Brier score from power family with natural bounds plotscore(c(2,.5), fam="pow") ## Plot Brier score from beta family with bounds of 0 and 1 plotscore(c(1,1), fam="beta", bounds=c(0,1)) ## Plot log score plotscore(c(0,0), fam="beta") ## Score from pseudospherical family with ## baseline of .3 and (0,1) bounds plotscore(c(3, .3), fam="sph", bounds=c(0,1))