Problems with generating Probability Distribution Function (PDF) in R
Hi I am using R to analyze data from output of my simulation. I am using hist function to generate pdf's the exact command i give is
hist(data_delay$delay,freq=F)
In my understanding the values the y axis of the chart should be less then 1, all the counts on Y-Axis should add up to 1. But unfortunately 开发者_运维技巧I am not getting random range at Y-Axis, sometimes values in 1000's.
I am attaching my sample input file. In this the Y-Axis values are in the range of 0 to 100.
Thank you for all the help you can provide.
My data is as follows http://www.mediafire.com/?twyoseg8bai0dr7
According to the hist
documentation, when freq=FALSE
, "the histogram has a total area of one". It does not say that the height of every bar should be less than one. The histogram created with your command and data does have a total area of 1.
> data_delay <- read.csv("PATH_TO_DATA_FILE")
> h <- hist(data_delay$delay, plot=F)
> h
$breaks
[1] 0.000 0.005 0.010 0.015 0.020 0.025 0.030 0.035 0.040 0.045 0.050 0.055
[13] 0.060 0.065 0.070
[SNIP]
$density
[1] 112.47892074 13.36706015 3.91231029 5.98088814 10.35413153
[6] 11.21978640 11.80438449 6.55424396 14.14277684 2.63069140
[11] 5.53119730 1.31534570 0.69702080 0.01124227
[SNIP]
The breaks are equally spaced 0.005 apart, so we can see the total area in the histogram by doing the following.
> sum(h$density * 0.005)
[1] 1
You might prefer ?density
as in
foo<-density(rnorm(1000)) ; plot(foo)
精彩评论