{smcl}
{* *! version 1 agu2013}{...}
{cmd:help dfsummary}
{hline}
{title:Title}
{p2colset 8 21 21 2}{...}
{p2col:{hi:dfsummary} {hline 2}}Performs the (Augmented) Dickey-Fuller unit-root test and reports a summary table for different lags.{p_end}
{p2colreset}{...}
{title:Syntax}
{p 8 18 2}
{cmd:dfsummary}
{varname}
{ifin}
[{cmd:,} {it:options}]
{synoptset 14 tabbed}{...}
{synopthdr}
{synoptline}
{syntab:Main}
{synopt:{opt nocon:stant}}suppress constant term in regression{p_end}
{synopt:{opt t:rend}}include trend term in regression{p_end}
{synopt:{opt s:easonal}}include seasonal dummies in regression{p_end}
{synopt:{opt reg:ress}}display regression table{p_end}
{synopt:{opt l:ag(#)}}include {it:#} lagged differences{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}
You must {opt tsset} your data before using {opt dfsummary}; see
{manhelp tsset TS}.
{p_end}
{p 4 6 2}
{it:varname} may contain time-series operators; see {help tsvarlist}.
{p_end}
{title:Description}
{pstd}
{cmd:dfsummary} performs the augmented Dickey-Fuller test that a variable follows a unit-root process.
The null hypothesis is that the variable contains a unit root, and the alternative is that the variable was generated by a stationary process.
You may optionally exclude the constant, include a trend term, include seasonal dummies and include lagged values of the difference
of the variable in the regression. {cmd:dfsummary} reports a summary table for different lags of the difference
of the variable in the regression {bf:(see Definitions)}.
{title:Definitions}
The default summary table report for the sequence of ADF(n)...ADF(0) tests, for j=n,...,0:
t-adf the t-value of the corresponding ADF test
beta Y_1 the coefficient on the lagged level
\sigma Root MSE of the regression
lag the number of lagged differences
t-DY_lag t-value of the longest lag difference
t-prob significance of the longest lag difference (P > |t|)
F-prob significance level of the F-test on the lags dropped up to that point
AIC Akaike's Bayesian information criteria
BIC Schwarz's Bayesian information criteria
{bf:Note:} Critical values are given (MacKinnon approximate p-value if there is a constant or trend in associated regression).
Significance of the ADF test is marked by asterisks: * indicates significance at 5%, ** at 1%.
{title:Options}
{dlgtab:Main}
{phang}
{opt noconstant} suppresses the constant term (intercept) in the
model and indicates that the process under the null hypothesis is a random
walk without drift. {opt noconstant} cannot be used with the {opt trend}
or {opt seasonal} option.
{phang}
{opt trend} specifies that a trend term be included in the associated
regression and that the process under the null hypothesis is a random walk,
perhaps with drift. This option may not be used with the {opt noconstant} option.
{phang}
{opt seasonal} include seasonal dummies in regression {bf:(weekly, monthly, quarterly, halfyearly, frequency data only)}.
This option may not be used with the {opt noconstant} option.
{phang}
{opt regress} specifies that the associated regression table appear in the
output. By default, the regression table is not produced.
{phang}
{opt lags(#)} specifies the number of lagged difference terms to include in
the covariate list {bf:(must be an integer >= 1)}.
{title:Examples}
{phang}{cmd:. dfsummary varname}{p_end}
{phang}{cmd:. dfsummary varname, lag(5) s t reg}{p_end}
{title:Saved results}
{synoptset 15 tabbed}{...}
{p2col 5 15 19 2: Matrix}{p_end}
{synopt:{cmd:r(results)}}summary table{p_end}
{p2colreset}{...}
{title:Author}
Maximo Sangiacomo
{hi:Email: {browse "mailto:msangia@hotmail.com":msangia@hotmail.com}}