commit cb0a691b33f756c1995ced455c91d31a54989b49
parent 8f70fb0ac553546fd5cac1e7b96682213740e421
Author: Ivan Gankevich <igankevich@ya.ru>
Date: Sun, 11 Jun 2017 09:53:56 +0300
Add second experiment.
Diffstat:
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/arma-thesis.org b/arma-thesis.org
@@ -2136,13 +2136,18 @@ surface, three realisations were generated:
- realisation with skew normal distribution.
The seed of PRNG was set to be the same for all progrmme executions to make ARMA
model produce the same values for eahc realisation. Standing wave ACF was used
-in all experiments.
+in the first experiment.
The results of the experiment are twofold: while the experiment showed that
applying NIT with GCS-based distribution makes wave profiles steeper, the same
is not true for skew normal distribution (fig.\nbsp{}[[fig-nonlinear]]. Using this
distribution results in wavy surface each \(z\)-coordinate of which is always
greater or equal to nought. So, skew normal distribution is unsuitable for NIT.
+In addition to this, NIT did not change wave asymmetry as expected, but this can
+be related to the fact that the wave is standing.
+
+In the second experiment the same benchmarks were repeated for propagating
+waves.
*** Non-physical nature of ARMA model
