[R] "Graphics (for goodness of fit)" Question
Mohammad Ehsanul Karim
wildscop at yahoo.com
Sun Mar 20 16:46:13 CET 2005
Dear List,
Suppose, I have some observed and expected
frequencies, such as following.
I need to draw a graph where plots of observed and
expected frequencies are merged into one.
------------------------------------------------
m <- c(1,2,3,4,5,6,7,8,9,10,12,13,17)
k <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 19)
ExpWW <- c(0.309330628803245, 0.213645190887434,
0.147558189649435, 0.101913922060107,
0.0703888244654489, 0.0486154051328303,
0.0335771712935674, 0.0231907237838939,
0.0160171226134196, 0.0110625360037919,
0.00764055478558038, 0.00527709716935116,
0.000395627498345897)
ExpDD <- c(0.420249653259362, 0.243639882194748,
0.141250306182253, 0.0818899139863827,
0.0474757060281664, 0.0275240570315860,
0.0159570816077711, 0.00925112359507395,
0.00536334211198462, 0.00310939944911175,
0.00104510169329968, 0.00060589806906972,
6.84484529305126e-05)
ObjDD <- c(0.468646864686469, 0.198019801980198,
0.151815181518152, 0.0759075907590759,
0.0396039603960396, 0.0198019801980198,
0.0165016501650165, 0.0099009900990099,
0.0033003300330033, 0.0033003300330033,
0.0033003300330033, 0.0066006600660066,
0.0033003300330033)
ObjWW <- c(0.373770491803279, 0.150819672131148,
0.127868852459016, 0.0721311475409836,
0.0885245901639344, 0.0622950819672131,
0.039344262295082, 0.0327868852459016,
0.0360655737704918, 0.00327868852459016,
0.00655737704918033, 0.00327868852459016,
0.00327868852459016)
------------------------------------------------
par(mfrow=c(2,2))
plot(k,ObjWW, type="l") # Plot 1
plot(k,ExpWW, type="l") # Plot 2
plot(m,ObjDD, type="l") # Plot 3
plot(m,ExpDD, type="l") # Plot 4
------------------------------------------------
# I need to see plot 1 and 2 in same axis, and plot 3
and 4 in another
# (i.e., 3, 4 both in same axis too, but not with 1
and 2's).
# How can i use different types of legends in the same
graph??
------------------------------------------------
sum(((ObjWW-ExpWW)^2)/ExpWW) # Chi-Squared Goodness
of Fit Test
sum(((ObjDD-ExpDD)^2)/ExpDD) # Chi-Squared Goodness
of Fit Test
------------------------------------------------
# Also, is there any other convenient way of doing
chi-squared goodness of fit test (any function or
package may be, to do this directly)?
# And how can i find the P-values of the respective
chi-squared tests in R?
------------------------------------------------
Any suggestion, direction, references, help, replies
will be highly appreciated.
Thank you for your time.
________________________________
Mohammad Ehsanul Karim
Web: http://snipurl.com/ehsan
Institute of Statistical Reseach and Training
University of Dhaka, Dhaka - 1000, Bangladesh
More information about the R-help
mailing list