Object Reference : Object View and Procedure Reference : Series
  
 
trendtests
Perform tests on the existence of a trend in the series.
Calculate the linear t-test, squared F-test, Mann-Kendall test, seasonal Mann-Kendall test, Cox-Stuart test and the Wang, Akritas and Van Keilegom (WAVK) test for time series trends.
Syntax
series_name.trendtests(options)
Options
 
noboot
Do not calculate bootstrapped p-values.
simple
Use the simple bootstrap. By default, the sieve bootstrap is used.
mle
Calculate the bootstrap AR estimates using MLE. Default is to use the HVK estimates.
iter=arg
Number of bootstrap simulations.
seed=int
Set the random number generator seed.
rng=arg
Set random number generator type. Available types are: improved Knuth generator (“kn”), improved Mersenne Twister (“mt”), Knuth’s (1997) lagged Fibonacci generator used in EViews 4 (“kn4”), L’Ecuyer’s (1999) combined multiple recursive generator (“le”), Matsumoto and Nishimura’s (1998) Mersenne Twister used in EViews 4 (“mt4”).
out=name
Specify the name of the matrix containing the test statistics and p-values.
Examples
gdpc1.trendtests(iter=19999, out=ttstats)
Performs a trend test on the GDPC1 series, performing 19,999 bootstraps using HVK estimates in a sieve bootstrap, and saving the test statistics and p-values into a matrix object named TTSTATS.
Cross-references
See “Trend Tests” for discussion