| jitter {base} | R Documentation |
‘Jitter’ (Add Noise) to Numbers
Description
Add a small amount of noise (“jitter”) to a numeric vector.
Usage
jitter(x, factor = 1, amount = NULL)
Arguments
x |
numeric vector to which jitter should be added. |
factor |
numeric; used in calculation of |
amount |
number or |
Details
The result of r <- x + amount * runif(n, -1, 1)
where n <- length(x).
When amount is NULL (the default)
amount <- factor * d/5 where d is about the smallest
difference between adjacent unique (up to fuzz) x values.
If amount == 0, amount <- factor * (max(x) - min(x))/50,
(using only finite x values), which is the same as in S and the
references.
In the above cases, the final amount is always ensured to be positive.
The short jitter() function is itself a succinct definition.
Value
jitter(x, ...) returns a numeric of the same length as
x, but with an amount of noise added in order to break
ties.
Author(s)
Werner Stahel and Martin Maechler, ETH Zurich
References
Chambers J. M., Cleveland W. S., Kleiner B., Tukey P. A. (1983). Graphical Methods for Data Analysis. Wadsworth & Brooks/Cole. ISBN 0871504138. (Figures 2.8, 4.22, 5.4.).
Chambers J. M., Hastie T. J. (1992). Statistical Models in S. Chapman & Hall, London. ISBN 9780412830402.
See Also
rug which you may want to combine with jitter.
Examples
round(jitter(c(rep(1, 3), rep(1.2, 4), rep(3, 3))), 3)
## These two had failed with S-plus 3.x: max(x) - min(x) == 0
jitter(rep(0, 7))
jitter(rep(10000, 5))