{smcl}
{* 19oct2004}{...}
{hline}
help for {hi:modlpr}
{hline}
{title:Estimate long memory in a timeseries via Modified Log-Periodogram Regression}
{p 8 17}{cmd:modlpr}
{it:varname}
[{cmd:if} {it:exp}]
[{cmd:in} {it:range}]
[{cmd:,} {cmdab:powers(}{it:numlist}{cmd:)}
[
{cmdab:not:rend}
]
{p 4 4}{cmd:modlpr} is for use with time-series data.
You must {cmd:tsset} your data before using {cmd:modlpr}; see help {cmd:tsset}.
{cmd:modlpr} supports the {cmd:by} prefix, which may be used to operate on each
time series in a panel. Alternatively, the {cmd:if} qualifier may be used to specify
a single time series in a panel.
{title:Description}
{p 4 4}{cmd:modlpr}
computes a modified form of the Geweke/Porter-Hudak (GPH, 1983)
estimate of the long memory (fractional integration) parameter, {it:d}, of a
timeseries, proposed by Phillips (1999, 2007). If a series
exhibits long memory, it is neither stationary (I[0]) nor is it a unit
root (I[1]) process; it is an I({it:d}) process, with {it:d} a real number. However,
distinguishing unit-root behavior from fractional integration may be
problematic, given that the GPH estimator is inconsistent against {it:d}>1
alternatives. {p_end}
{p 4 4}
This weakness of the GPH estimator (see {cmd:gphudak^}) is solved by Phillips'
Modified Log Periodogram Regression estimator, in which the dependent
variable is modified to reflect the distribution of {it:d} under the null
hypothesis that {it:d}=1. The estimator gives rise to a test statistic for {it:d}=1
which is a standard normal variate under the null. Phillips suggests (p.11)
that deterministic trends should be removed from the series before application
of the estimator. By default, a linear trend is extracted from the series.
This may be suppressed with the {cmd:notrend} option.{p_end}
{p 4 4}
A choice must be made of the number of harmonic ordinates to be included
in the spectral regression. The regression slope estimate is an estimate of
the slope of the series' power spectrum in the vicinity of the zero
frequency; if too few ordinates are included, the slope is calculated from
a small sample. If too many are included, medium and high-frequency components
of the spectrum will contaminate the estimate. A choice of root(T), or
{cmd:power} = 0.5 is often employed. To evaluate the robustness of the estimates,
a range of power values (from 0.4 - 0.75) is commonly calculated as well.
{cmd:modlpr} uses the default power of 0.5. A {it:numlist} of powers may be given.{p_end}
{p 4 4}
The command displays the d estimate, number of ordinates, conventional
standard error and P-value, as well as the test statistic ({cmd:zd}) for
the test of {it:d}=1, and its p-value. These values are returned in a matrix,
e(modlpr), formatted for display. {cmd: ereturn list} for details. If {cmd:modlpr}
is used in a panel context and the returned results are to be saved,
the {cmd:if} qualifier should be used rather than the {cmd:by} prefix to loop
over panels.{p_end}
{title:Examples}
{p 4 8}{stata "use http://fmwww.bc.edu/ec-p/data/Mills2d/fta.dta, clear" :. use http://fmwww.bc.edu/ec-p/data/Mills2d/fta.dta, clear}{p_end}
{p 4 8}{stata "modlpr ftap" :. modlpr ftap}{p_end}
{p 4 8}{stata "modlpr ftap, power( 0.5 0.55:0.8)" :. modlpr ftap, power( 0.5 0.55:0.8)}{p_end}
{p 4 8}{stata "webuse grunfeld, clear" :. webuse grunfeld, clear}{p_end}
{p 4 8}{stata "modlpr invest if company==6" :. modlpr invest if company==6}{p_end}
{p 4 8}{stata "by company: modlpr invest" :. by company: modlpr invest}{p_end}
{title:Authors}
{p 4 4}Christopher F. Baum, Boston College, USA{break}
baum@bc.edu
{p 4 4}Vince Wiggins, StataCorp LP{break}
vwiggins@stata.com
{title:References}
{p}Geweke, J. and Porter-Hudak, S., The Estimation and Application
of Long Memory Time Series Models, J. of Time Series Analysis,
1983, 221-238.{p_end}
{p}Phillips, Peter C.B., Discrete Fourier Transforms of Fractional
Processes, 1999. Unpublished working paper No. 1243, Cowles
Foundation for Research in Economics, Yale University.
http://cowles.econ.yale.edu/P/cd/d12a/d1243.pdf{p_end}
{p}Phillips, Peter C.B., Unit Root Log Periodogram Regression,
Journal of Econometrics, 2007, 138:104-124. Also available as
Unpublished working paper No. 1244, Cowles Foundation for
Research in Economics, Yale University.
http://cowles.econ.yale.edu/P/cd/d12a/d1244.pdf{p_end}
{title:Also see}
{p 4 13}On-line: {help regress}, {help time}, {help tsset}, {help ac},
{help corrgram} {help gphudak} (if installed), {help roblpr} (if installed)