# runmed

0th

Percentile

##### Running Medians -- Robust Scatter Plot Smoothing

Compute running medians of odd span. This is the ‘most robust’ scatter plot smoothing possible. For efficiency (and historical reason), you can use one of two different algorithms giving identical results.

Keywords
robust, smooth
##### Usage
runmed(x, k, endrule = c("median", "keep", "constant"),
algorithm = NULL, print.level = 0)
##### Arguments
x
numeric vector, the ‘dependent’ variable to be smoothed.
k
integer width of median window; must be odd. Turlach had a default of k <- 1 + 2 * min((n-1)%/% 2, ceiling(0.1*n)). Use k = 3 for ‘minimal’ robust smoothing eliminating isolated outliers.
endrule
character string indicating how the values at the beginning and the end (of the data) should be treated. Can be abbreviated. Possible values are:
"keep"
keeps the first and last $k_2$ values at both ends, where $k_2$ is the half-bandwidth k2 = k %/% 2, i.e., y[j] = x[j] for $j \in \{1,\ldots,k_2; n-k_2+1,\ldots,n\}$;
"constant"
copies median(y[1:k2]) to the first values and analogously for the last ones making the smoothed ends constant;
"median"
the default, smooths the ends by using symmetrical medians of subsequently smaller bandwidth, but for the very first and last value where Tukey's robust end-point rule is applied, see smoothEnds.

algorithm
character string (partially matching "Turlach" or "Stuetzle") or the default NULL, specifying which algorithm should be applied. The default choice depends on n = length(x) and k where "Turlach" will be used for larger problems.
print.level
integer, indicating verboseness of algorithm; should rarely be changed by average users.
##### Details

Apart from the end values, the result y = runmed(x, k) simply has y[j] = median(x[(j-k2):(j+k2)]) (k = 2*k2+1), computed very efficiently. The two algorithms are internally entirely different:

"Turlach"
is the H<U+00E4>rdle--Steiger algorithm (see Ref.) as implemented by Berwin Turlach. A tree algorithm is used, ensuring performance $O(n \log k)$ where n = length(x) which is asymptotically optimal.
"Stuetzle"
is the (older) Stuetzle--Friedman implementation which makes use of median updating when one observation enters and one leaves the smoothing window. While this performs as $O(n \times k)$ which is slower asymptotically, it is considerably faster for small $k$ or $n$.
Currently long vectors are only supported for algorithm = "Steutzle".

##### Value

vector of smoothed values of the same length as x with an attribute k containing (the ‘oddified’) k.

##### References

H<U+00E4>rdle, W. and Steiger, W. (1995) [Algorithm AS 296] Optimal median smoothing, Applied Statistics 44, 258--264. Jerome H. Friedman and Werner Stuetzle (1982) Smoothing of Scatterplots; Report, Dep. Statistics, Stanford U., Project Orion 003. Martin Maechler (2003) Fast Running Medians: Finite Sample and Asymptotic Optimality; working paper available from the author.