-------------------------------------------------------------------------------
help for lomackinlay
-------------------------------------------------------------------------------

Perform Lo-MacKinlay variance ratio test

        lomackinlay varname [if exp] [in range] [, q(numlist) gaps robust ]

    lomackinlay is for use on time series data, which must be tsset.  It may
    be applied to a single panel of a panel (xt) data set using an if
    qualifier.  lomackinlay also supports the by: prefix.

Description

    lomackinlay computes a overlapping variance-ratio test on a timeseries.
    The timeseries should be in level form; e.g., to test that stock returns
    vary randomly around a constant mean, you consider the null hypothesis
    that the log price series is a random walk with drift. The log price
    series would then be given in the varlist. If the assumption of
    homoskedastic errors in the process generating the differenced series is
    not reasonable, the robust option may be used to calculate a variance
    ratio test statistic robust to arbitrary heteroskedasticity.


Options 

    q(numlist) optionally specifies a numlist of values for the span of
        differencing. If not provided, the numlist of 2 4 8 16 is applied.

    gaps is used to indicate that gaps in the timeseries are allowed.

    robust specifies that a heteroskedasticity-robust test statistic should
        be computed.


Examples

    . webuse wpi1
    . lomackinlay ln_wpi
    . lomackinlay ln_wpi, robust
    . lomackinlay ln_wpi, q(2 3 5 7 9)


References


Campbell, J. Y., Lo, A. W. and A. C. MacKinlay, The Econometrics of Financial M
> arkets. 
Princeton: Princeton University Press, 1997.

Lo, A. and MacKinlay, A. C., "Stock market prices do not follow random walks: e
> vidence
 from a simple specification test", Review of Financial Studies 1:1, 1988. 
 
Lo, A. W. and A. C. MacKinlay, A Non-Random Walk Down Wall Street. 
Princeton: Princeton University Press, 1999. http://www.pupress.princeton.edu/b
> ooks/lo/

Tse, Ng and Zhang, "A small-sample overlapping variance-ratio test",
 available from www.mysmu.edu/faculty/yktse/JTSA_R.pdf 
 
 

Author 

    Christopher F Baum, Boston College
    baum@bc.edu


Acknowledgements 

    Tomasz Stepniak's query to Statalist suggested this problem. I am very
    grateful to Allin Cottrell for pointing out several corrections required
    in the code and providing corrected code. Brian Fryd also pointed out an
    error in the routine and provided a fix, for which I thank him.


Also see

    On-line: help for lomodrs (if installed)