partialAR (version 1.0.3)

which.hypothesis.partest: Returns the preferred hypothesis when testing for partial autoregression

Description

Returns the preferred hypothesis when testing for partial autoregression

Usage

which.hypothesis.partest(AT)

Arguments

AT

An object of class "partest" returned from a previous call to test.par.

Value

• One of the following strings:
• "RW"
  The preferred hypothesis is a pure random walk
• "AR1"
  The preferred hypothesis is a pure AR(1) series
• "PAR"
  The preferred hypothesis is a partially autoregressive series
• "RRW"
  The preferred hypothesis is a random walk with t-distributed innovations
• "RAR1"
  The preferred hypothesis is a pure AR(1) series with t-distributed innovations
• "RPAR"
  The preferred hypothesis is a partially autoregressive model with t-distributed innovations

Details

Based upon the critical value alpha used in the call to test.par, and based upon the statistics computed by test.par, selects a preferred explanatory hypothesis for the data and returns a string representing the chosen hypothesis.

References

Matthew Clegg (2015): Modeling Time Series with Both Permanent and Transient Components using the Partially Autoregressive Model. Available at SSRN: http://ssrn.com/abstract=2556957.

See Also

fit.par test.par

Examples

set.seed(1)
which.hypothesis.partest(test.par(rpar(1000, 0, 1, 0)))  # -> "AR1"
which.hypothesis.partest(test.par(rpar(1000, 0, 0, 1)))  # -> "RW"
which.hypothesis.partest(test.par(rpar(1000, 0, 1, 1)))  # -> "PAR"

which.hypothesis.partest(test.par(rpar(1000, 0, 1, 0), robust=TRUE))   # -> "RAR1"
which.hypothesis.partest(test.par(rpar(1000, 0, 0, 1), robust=TRUE))   # -> "RRW"
which.hypothesis.partest(test.par(rpar(1000, 0.5, 1, 1), robust=TRUE)) # -> "RPAR"

Run the code above in your browser using DataCamp Workspace