PACKAGE |STAT Data Manipulation and Analysis, by Gary Perlman
NAME ts - time series analysis
SYNOPSIS ts [-aeps] [-b base] [-c lag] [-i interval] [-l length] [-P style] [-n number] [-w width]
DESCRIPTION ts performs a variety of time series analyses on ordered data read from the standard input.
OPTIONS
-a
requests no axes around plot.
-b base
set the base label of the time series.
-c lag
print (auto)correlation of lags 1:lag. These can be useful for detecting cycles and other trends within the data. The output for a lag of zero is the correlation of the time series with the numbers 1 through the length of the time series.
-e
echo the time series (may be useful with the -l option).
-i size
set the interval size for plot labels.
-l length
sets the length of the time series. This can be useful for summarizing, or for comparing time series of different lengths.
-n N
number the output lines of plots every N points.
-p
requests a time series plot. A vertical mean line is used for the center of the plot.
-P plotnum
Plot type. The default (type 1) plots points as deviations from the mean. Plot type 2 plots points as lines above the minimum. A line plot of the range indicating the mean and standard deviation surround plots.
-s
Print summary statistics.
-w width
Plot width (default: 70).
The following standard help options are supported. The program exits after displaying the help.
-L
Display limits
-O
Display options and values
-V
Display version number and date
EXAMPLES Side-by-side plots can compare trends in series of different lengths: 
ts -p -w 20 -l 30 < data1 > plot1
ts -p -w 20 -l 30 < data2 > plot2
pr -m plot1 plot2
LIMITS Use the -L option to determine the program limits.
MISSING VALUES Missing data values (NA) are counted but not included in the analysis.
SEE ALSO stats for simple univariate statistics.
desc for univariate descriptive statistics and analysis.
UPDATED January 20, 1987