R help - Jun 2011 - histogram - density on y axis and restriction to interval [0, 1]

Hello,

To indicate probability densities instead of counts on a histogram, I 
specify freq = FALSE.

However, I expect that summing all top y coordinates over all the 
intervals of the histogram will provide 1.

1)
v <- c(0.2885, 0.2988, 0.3139, 0.2615, 0.3179, 0.3163, 0.2583, 0.3052, 
0.2527, 0.3147, 0.3235, 0.2408, 0.2480, 0.3108, 0.3577, 0.2829, 0.2694, 
0.3275, 0.3314, 0.2639, 0.3076, 0.3346, 0.2933, 0.3585, 0.2678, 0.3338)

hist(v, freq = FALSE)

With the above example, roughly, I obtain 3 * 8 + 10 + 14 + 4 = 52

Besides, I do not understand the units on the y axis. I would have 
expected decimals.

2) In contrast, I am satisfied with the units on the y axis with the 
example below :
  v <- 
c(1,1,1,1,1,2,2,2,2,2,3,3,3,3,3,4,4,4,4,4,5,5,5,5,5,6,6,6,6,6,6,6,6,6,6,7,7,7,7,7,8,8,8,8,8,9,9,9,9,9)

hist(v, freq = FALSE)


3) Again, with the example below, I wonder why the unit axis does not 
show the interval [0,1] (or maybe [0%,100%]). Proportions are correct 
but the indication 1.4 is not usual.

v <- c(1,2,2,3,3,3,4,4,4,4,4,4,4,4,4,4,4,4,4,4)
 > hist(v, freq = FALSE)


I thank you in advance for any explanation about the way to force the y 
axis to restrain to interval [0,1] on an histogram.

Best regards,

Christine Sinoquet

Did you read the help for hist?

    freq: logical; if ?TRUE?, the histogram graphic is a representation
          of frequencies, the ?counts? component of the result; if
          ?FALSE?, probability densities, component ?density?, are
          plotted (so that the histogram has a total area of one).
          Defaults to ?TRUE? _if and only if_ ?breaks? are equidistant
          (and ?probability? is not specified).

freq=FALSE isn't doing what you think it is.

But what I think you want is easy enough to accomplish.
v.hist <- hist(v, plot=FALSE)
v.hist$counts <- v.hist$counts/sum(v.hist$counts)
plot(v.hist)

Sarah

On Thu, Jun 9, 2011 at 12:22 PM, Christine SINOQUET
<christine.sinoquet at univ-nantes.fr> wrote:
> Hello,
>
> To indicate probability densities instead of counts on a histogram, I
> specify freq = FALSE.
>
> However, I expect that summing all top y coordinates over all the intervals
> of the histogram will provide 1.
>
> 1)
> v <- c(0.2885, 0.2988, 0.3139, 0.2615, 0.3179, 0.3163, 0.2583, 0.3052,
> 0.2527, 0.3147, 0.3235, 0.2408, 0.2480, 0.3108, 0.3577, 0.2829, 0.2694,
> 0.3275, 0.3314, 0.2639, 0.3076, 0.3346, 0.2933, 0.3585, 0.2678, 0.3338)
>
> hist(v, freq = FALSE)
>
> With the above example, roughly, I obtain 3 * 8 + 10 + 14 + 4 = 52
>
> Besides, I do not understand the units on the y axis. I would have expected
> decimals.
>
> 2) In contrast, I am satisfied with the units on the y axis with the
example
> below :
> ?v <-
>
c(1,1,1,1,1,2,2,2,2,2,3,3,3,3,3,4,4,4,4,4,5,5,5,5,5,6,6,6,6,6,6,6,6,6,6,7,7,7,7,7,8,8,8,8,8,9,9,9,9,9)
> hist(v, freq = FALSE)
>
>
> 3) Again, with the example below, I wonder why the unit axis does not show
> the interval [0,1] (or maybe [0%,100%]). Proportions are correct but the
> indication 1.4 is not usual.
>
> v <- c(1,2,2,3,3,3,4,4,4,4,4,4,4,4,4,4,4,4,4,4)
>> hist(v, freq = FALSE)
>
>
> I thank you in advance for any explanation about the way to force the y
axis
> to restrain to interval [0,1] on an histogram.
>
> Best regards,
>
> Christine Sinoquet
>
> __________
-- 
Sarah Goslee
http://www.functionaldiversity.org