Stata Technical Bulletin
39
Saved Results
dfgls saves the following scalars in r():
r(N)
number of observations
|
r(optlag) |
optimal lag order Schwarz criterion at lag n DF-GLS statistic at lag n |
kpss saves the following scalars in r():
r(N) number of observations
r(dftn) KPSS statistic at lag n
Acknowledgments
I acknowledge useful conversations with Serena Ng, James Stock, and Vince Wiggins. The KPSS code was adapted from
John Barkoulas’ RATS code for that test. Thanks also to Richard Sperling for tracking down a discrepancy between published
work and the dfgls output and alerting me to the Cheung and Lai estimates. Any remaining errors are my own.
References
Cheung, Y. W. and K.-S. Lai. 1995. Lag order and critical values of a modified Dickey-Fuller test. Oxford Bulletin of Economics and Statistics 57:
411-419.
Elliott, G., T. J. Rothenberg, and J. H. Stock. 1996. Efficient tests for an autoregressive unit root. Econometrica 64: 813-836.
Kwiatkowski, D., P. C. Phillips, P. Schmidt, and Y. Shin. 1992. Testing the null hypothesis of stationarity against the alternative of a unit root: How
sure are we that economic time series have a unit root? Journal of Econometrics 54: 159-178.
Lee, D. and P. Schmidt. 1996. On the power of the KPSS test of stationarity against fractionally-integrated alternatives. Journal of Econometrics 73:
285-302.
Ng, S. and P. Perron. 1995. Unit root tests in ARMA models with data-dependent methods for the selection of the truncation lag. Journal of the
American Statistical Association 90: 268 -281.
Schwert, G. W. 1989. Tests for unit roots: A Monte Carlo investigation. Journal of Business and Economic Statistics 7: 147-160.
Stock, J. H. 1994. Unit roots, structural breaks and trends. In Handbook of Econometrics IV, ed. R. F. Engle and D. L. McFadden. Amsterdam:
Elsevier.
sts16 Tests for long memory in a time series
Christopher F. Baum, Boston College, [email protected]
Vince Wiggins, Stata Corporation, [email protected]
Abstract: Implements the Geweke/Porter-Hudak log periodogram estimator (1983), the Phillips modified log periodogram
estimator (1999b) and the Robinson log periodogram estimator (1995) for the diagnosis of long memory, or fractional
integration, in a time series. The Robinson estimator may be applied to a set of time series.
Keywords: fractional integration, long memory, stationarity, time series.
Syntax
gphudak varname [if exp [in range] [, powers (numlisι) ]
modlpr varname [if exp [in range] [, powers (mιιniitl) notrend ]
roblpr varlisl [if exp [in range] [, powers (numlist) 1(#) J (#) constraints (numlist) ]
These tests are for use with time series data; you must tsset your data before using these tests; see [R] tsset. varname or varlisl may contain time
series operators; see [U] 14.4.3 Time-series varlists.
Options
powers (numlist) indirectly specifies the number of ordinates to be included in the regression. A number of ordinates equal
to the integer part of T raised to the powers (numlitt) will be used. Powers ranging from 0.50 to 0.75 are commonly
employed for gphudak and modlpr. These routines use the default power of 0.5. roblpr uses the default power of 0.9.
For roblpr, multiple powers may only be specified if a single variable appears in varlisl.
notrend specifies that detrending is not to be applied by modlpr. By default, a linear trend will be removed from the series.