Geoscience Reference
In-Depth Information
modii ed as follows. At er the histogram of the angles is computed in line 57
using the function
histc
, add a line with the command
nn = sqrt(nn)
, which
computes the square root of the frequencies
nn
. Save the modii ed function
as i le
rose_sqrt.m
and apply the new function to the data set.
Movie
10.1
rose_sqrt(data_radians_1,12)
view(90,-90)
h is plot satisi es all conventions in geosciences (Fig. 10.3).
10.3 Empirical Distributions
h is section introduces statistical measures used to describe empirical
distributions of directional data. h e characteristics of directional data
are described by measures of central tendency and dispersion, similar to
the statistical characterization of univariate data sets (Chapter 3). Assume
that we have collected a number of angular measurements such as fossil
alignments. h e collection of data can be written as
containing
N
observations ʸ
i
. Sine and cosine values are computed for each
direction ʸ
i
to compute the
resultant
or
mean direction
for the set of angular
data (Fisher 1993, Mardia and Jupp 2000).
h e resultant direction of the data set is
−
1
θ =
tan (
xy
/
)
r
r
h e length of the resultant is
h e resultant length clearly depends on the dispersion of the data.
Normalizing the resultant length to the number of observations yields the
mean resultant length.
