[R] Help producing plot for assessing forecasting accuracy
Jay Ulfelder
ulfelder at gmail.com
Fri Oct 9 16:22:01 CEST 2009
Dear colleagues,
I'm trying (and failing) to write the script required to generate a
chart that would help me assess the forecasting accuracy of a logistic
regression model by plotting the cumulative proportion of observed
events occurring in cases across the range of possible predicted
probabilities. In other words, let:
x = any value on 0-1 scale
phat_i = predicted probability of event Y from logit model for case i
y_i = observed outcome (0/1) for case i
Y_cond = sum(y_i) conditional on phat_i <= x
Y_tot = total number of events observed in sample
What I'm trying to plot is (Y_cond)/(Y_tot) across all values of x. I
would be grateful for any guidance you can offer, and I'm sorry if
I've overlooked some really simple solution; I'm fairly new to R and
learning by doing.
Regards,
Jay
--
Jay Ulfelder, Ph.D.
Research Director
Political Instability Task Force
Science Applications International Corp. (SAIC)
jay_ulfelder at stanfordalumni.org
(301) 588-8478 [home office]
(301) 580-8736 [mobile]
More information about the R-help
mailing list