📄 nstat_z.html
字号:
<html><head><title>nstat_z</title></head><body bgcolor=white><h1 align=center>Description of the program: <font color=Blue>nstat_z</font></h1><hr>This program seeks for nonstationarity in a time series by dividing itinto a number of segments and calculating the cross-forecast errorsbetween the different segments. The model used for the forecast iszeroth order model as proposed by <ahref="../chaospaper/citation.html#statio">Schreiber</a>.<p> Since the usage of some (two) of the flags of this program is a bitpeculiar, here some more detailed information about them. Say, thenumber of segments chosen is <font color=blue>N</font>. Then for allpossible combinations of the <font color=blue>N</font> segments theforecast errors are calculated. Means for <fontcolor=blue>N<sup>2</sup></font> combinations. Since this can be alarge number and one might be only interested in some of all possiblecombinations, the combinations can be reduced with the <fontcolor=red>-1</font> and the <font color=red>-2</font> flags. Thevalues these options can take are either single numbers, or rangesseparated by commas. A range looks like <fontcolor=blue>n<sub>1</sub>-n<sub>2</sub></font> or like <fontcolor=blue>+n</font>. To give some examples:<ul><li><font color=blue>nstat_z file -# 10 -1 1</font><br> means: Divide the data into 10 segments and use the first segment to forecast all segments.<li><font color=blue>nstat_z file -# 10 -1 1,3,7-9</font><br> means: Divide the data into 10 segments and use the first, the third and the seventh to the ninth segments to forecast all segments</br><li><font color=blue>nstat_z file -# 10 -1 +2</font><br> means: Divide the data into 10 segments and forecast all segments <font color=red>I</font> using segments <font color=red>I-2</font> to <font color=red>I+2</font>. </ul>Inother words the <font color=blue>+n</font> defines a time windowaround to segment to be forecasted and only segments lying in thiswindow are used for the forecast. If the <font color=blue>+n</font> syntax is chosen, it can not be combinedwith other ranges or a number.The same works for the <font color=red>-2</font> flag, which specifieswhich segments are forecasted.<hr><h2 align=center>Usage:</h2><center><font color=Red>nstat_z -# [other options]</font><p>Everything not being a valid option will be interpreted as a potential datafile name. Given no datafile at all, means read stdin. Also <font color=Red>-</font> means stdin<p>Possible options are:<p><table border=2><tr><th>Option<th>Description<th>Default</tr><tr bgcolor="pink"><th>-##<td>number of segments the data should be divided into<td>no default. has to be given</tr><tr><th>-l#<td>number of points to use<td>whole file</tr><tr><th>-x#<td>number of lines to be ignored<td>0</tr><tr><th>-c#<td><a href=../general.html#column>column to be read</a><td>1</tr><tr><th>-m#<td>embedding dimension<td>3</tr><tr><th>-d#<td>delay for the embedding<td>1</tr><tr><th>-1#<td>which segments should be used to forecast the others<td>1-(# of segments) (all)</tr><tr><th>-2#<td>which segments should be forecasted by the others<td>1-(# of segments) (all)</tr><tr><th>-n#<td>for how many reference points should the error be calculated<td>all</tr><tr><th>-k#<td>minimal numbers of neighbors for the fit<td>30</tr><tr><th>-r#<td>neighborhood size to start with<td>(data interval)/1000</tr><tr><th>-f#<td>factor to increase the neighborhood size<br> if not enoughneighbors were found<td>1.2</tr><tr><th>-s#<td>step to be forecasted x<sub>n+step</sub>=av(x<sub>i+step</sub>)<td>1</tr><tr><th>-C#<td><a href="causality.html">width of causality window</a><td>steps to be forecasted</tr><tr><th>-o[#]<td><a href=../general.html#outfile>output file name</a><td>without file name: 'datafile'.nsz<br>(or stdin.nsz if stdin was read)<br>If no -o is given stdout is used</tr><tr><th>-V#<td><a href=../general.html#verbosity>verbosity level</a><br> 0: only panic messages<br> 1: add input/output messages<br><td>1</tr><tr><th>-h<td>show these options<td>none</tr></table></center><hr><h2 align=center>Description of the Output</h2>The output consists of a number of lines each of which consists ofthree columns:<br><font color=blue>first column</font>: The index of the segment used forthe forecast</br><font color=blue>second column</font>: The index of the segment that wasforecasted<br><font color=blue>third column</font>: The cross-forecast errornormalized to the standard deviation of the segment that wasforecasted.<p>Before increasing the first index, an empty line is added to thefile. Thus the file has a block structure which can be used to make 3dplots in gnuplot. Furthermore, the output format is suitable forclustering by <a href="../docs_f/cluster.html">cluster</a>.<hr>View the <a href="../../source_c/nstat_z.c"> C-sources</a>.<hr><a href=../contents.html>Table of Contents</a> * <a href="../../index.html" target="_top">TISEAN home</a></body></html>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -