Miroslav Lichvar
53b661b59d
regress: remove unused struct declaration
2016-12-02 14:53:03 +01:00
Miroslav Lichvar
27d59e54cc
regress: add linear regression with two independent variables
2016-08-11 10:45:48 +02:00
Miroslav Lichvar
f7b8cd1a09
regress: save arrays of constants in single-precision
...
No need to waste space on double precision. Also, declare them as const.
2016-08-11 10:45:48 +02:00
Miroslav Lichvar
75efa5174c
Convert disabled log messages to debug or remove them
2014-06-27 10:17:35 +02:00
Miroslav Lichvar
ae104b5c28
regress: make minimum number of samples for regression public
2014-04-10 17:15:13 +02:00
Miroslav Lichvar
726cf84e19
Check array index before reading
2014-02-04 16:02:21 +01:00
Miroslav Lichvar
7261d11bb0
Add assert for parameter m in RGR_FindBestRegression()
2013-10-10 16:37:40 +02:00
Miroslav Lichvar
3d1be1cd75
Replace bzero with memset
2013-06-14 13:48:16 +02:00
Miroslav Lichvar
6ca73bf670
Cleanup including of system headers
2013-06-14 13:41:16 +02:00
Miroslav Lichvar
6d2fb9f782
Add minsamples and maxsamples directives
...
Allow configuration of the maximum and minimum number of samples per
source.
2013-06-13 16:23:32 +02:00
Miroslav Lichvar
359d444343
Remove unncessary return statements
2013-05-21 15:08:34 +02:00
Miroslav Lichvar
b14689d59b
Fix crash and hangs in RGR_FindBestRobustRegression
2012-11-29 16:23:22 +01:00
Miroslav Lichvar
b485051b65
Fix reported number of runs to correspond to reported number of samples
2011-11-28 11:19:48 +01:00
Miroslav Lichvar
da2c8d9076
Use config.h
2011-05-24 18:07:06 +02:00
Miroslav Lichvar
66c7ac4d24
Revert using unweighted variance in weight calculation
...
This reverts commit 165e6805ab
2011-04-29 13:29:24 +02:00
Miroslav Lichvar
70735d8d79
Ignore extra samples in reported nruns
2011-04-18 12:36:02 +02:00
Miroslav Lichvar
165e6805ab
In weight calculation use unweighted variance from last regression
...
This fixes a positive feedback where weights could reach inf.
Also change the SD_TO_DIST_RATIO constant to get close to the original
response.
2011-04-13 18:43:25 +02:00
Miroslav Lichvar
e8c5d15690
Remove CVS headers
2011-01-28 12:56:09 +01:00
Miroslav Lichvar
e63cba05b2
Update copyright
2011-01-27 13:05:26 +01:00
Miroslav Lichvar
5344028c40
Use 5% critical region for number of runs
...
This results in more samples used in regression and slightly improved
response with high jitters.
2010-08-17 17:52:19 +02:00
Miroslav Lichvar
e591e3622b
Extend runs test
...
Double the number of samples that are used in the runs test. E.g. with 64
samples in regression the runs test will be tried over the 64 samples and
up to 64 previous samples. The minimum number of samples in now 4.
This improves the response with low-mid jitters by about 50%.
2010-08-17 16:40:25 +02:00
Miroslav Lichvar
6b0198c2d7
Replace all CROAK calls with assert or LOG_FATAL
...
Remove croak() and use assert() or LOG_FATAL() everywhere. Hopefully
the problems with debugging mentioned in the croak() comment are long gone.
2010-08-12 14:30:05 +02:00
Miroslav Lichvar
2a64b75893
Regenerate critical values for number of runs
...
Generate more values to allow regression with 128 samples. Possibly a
different approach was used to generate the values, or the previous table
was actually using 11% critical region and had an extra value in the
12th place.
2010-08-11 18:50:23 +02:00
Miroslav Lichvar
034e172033
Assert number of points in regress functions
2010-08-11 18:25:32 +02:00
Miroslav Lichvar
3b4e4b785d
Change length of resid buffer to MAX_POINTS
2010-08-06 14:51:37 +02:00
Miroslav Lichvar
b9b0326d15
Reduce noise in refclock sample dispersions
...
Use the estimated dispersion only if it's higher than long-term average.
This should improve performance with short polling intervals.
2010-03-02 14:23:50 +01:00
Miroslav Lichvar
4097ab29c7
Don't read past buffer in find_ordered_entry_with_flags
2009-11-18 15:46:55 +01:00
Miroslav Lichvar
8e23110aec
Update COPYING and FSF address
2009-10-28 17:53:33 +01:00
richard
6672f045c2
Update copyright to 2003
2006-01-19 21:37:13 +00:00
Richard P. Curnow
8884034104
Equivalent to V1.19.99.1
...
This is a verbatim copy of the files at that stage of the repository that was
built from the CVS import. It allows future development to see a bit of recent
history, but without carrying around the baggage going back to 1997. If that
is really required, git grafts can be used.
2006-01-19 21:34:28 +00:00
