Geoscience Reference
In-Depth Information
0.4725
stats =
W: 4903
Wstar: -0.7184
We can use the same script to test whether the two samples in
organicmatter_
four.mat
come from the same distribution (
null hypothesis
), or from
distributions with the same median and shape but dif erent dispersions
(
alternative hypothesis
). We clear the workspace and load the data.
clear
load('organicmatter_four.mat');
We use the function
ansaribradley
to perform the Ansari-Bradley test by
typing
[h,p,stats] = ansaribradley(corg1,corg2)
which yields
h =
0
p =
0.7448
stats =
W: 1861
Wstar: 0.3254
h eresult
h=0
means that we cannot reject the null hypothesis without another
cause at a 5% signii cance level. h e
p
-value of 0.7448 or ~74% (which is
greater than the signii cance level) means that the chances of observing
either the same result or a more extreme result from similar experiments in
which the null hypothesis is true would be 7,448 in 10,000.
3.13 Distribution Fitting
In Section 3.9 we computed the mean and standard deviation of our sample
and designed a normal distribution based on these two parameters. We then
used the ˇ
2
-test to test the hypothesis that our data indeed follow a Gaussian or
normal distribution. Distribution i tting functions contained in the Statistics
Toolbox provide powerful tools for estimating the distributions directly from
the data. Distribution i tting functions for supported distributions all end
with
fit
, as in
binofit
, or
expfit
. h e function to i t normal distributions to
