dfuller是不能用于面板数据的

那要用LLC检验吗

那要用LLC检验面板数据吗

Title

    [XT] xt -- Introduction to xt commands


Syntax

        xtcmd ...


Description

    The xt series of commands provide tools for analyzing panel data (also known as longitudinal
    data or in some disciplines as cross-sectional time series when there is an explicit time
    component).  Panel datasets have the form x_[it], where x_[it] is a vector of observations
    for unit i and time t.  The particular commands (such as xtdescribe, xtsum, and xtreg) are
    documented in alphabetical order in the entries that follow this entry.  If you do not know
    the name of the command you need, try browsing the second part of this description section,
    which organizes the xt commands by topic.  Remarks and examples of [XT] xt describes
    concepts that are common across commands.

    The xtset command sets the panel variable and the time variable; see [XT] xtset.  Most xt
    commands require that the panel variable be specified, and some require that the time
    variable also be specified.  Once you xtset your data, you need not do it again.  The xtset
    information is stored with your data.

    If you have previously tsset your data by using both a panel and a time variable, these
    settings will be recognized by xtset, and you need not xtset your data.

    If your interest is in general time-series analysis, see [U] 26.17 Models with time-series
    data and the Time-Series Reference Manual.  If your interest is in multilevel mixed-effects
    models, see the Multilevel Mixed-Effects Reference Manual.

    Setup

        xtset        Declare data to be panel data


    Data management and exploration tools

        xtdescribe   Describe pattern of xt data
        xtsum        Summarize xt data
        xttab        Tabulate xt data
        xtdata       Faster specification searches with xt data
        xtline       Line plots with xt data


    Linear regression estimators

        xtreg        Fixed-, between- and random-effects, and population-averaged linear models
        xtregar      Fixed- and random-effects linear models with an AR(1) disturbance
        xtgls        Panel-data models using GLS
        xtpcse       Linear regression with panel-corrected standard errors
        xthtaylor    Hausman-Taylor estimator for error-components models
        xtfrontier   Stochastic frontier models for panel data
        xtrc         Random-coefficients regression
        xtivreg      Instrumental variables and two-stage least squares for panel-data models


    Unit-root tests

        xtunitroot   Panel-data unit-root tests


    Dynamic panel-data estimators

        xtabond      Arellano-Bond linear dynamic panel-data estimation
        xtdpd        Linear dynamic panel-data estimation
        xtdpdsys     Arellano-Bover/Blundell-Bond linear dynamic panel-data estimation


    Censored-outcome estimators

        xttobit      Random-effects tobit models
        xtintreg     Random-effects interval-data regression models


    Binary-outcome estimators

        xtlogit      Fixed-effects, random-effects, & population-averaged logit models
        xtprobit     Random-effects and population-averaged probit models
        xtcloglog    Random-effects and population-averaged cloglog models


    Ordinal-outcome estimators

        xtologit      Random-effects ordered logistic models
        xtoprobit     Random-effects ordered probit models


    Count-data estimators

        xtpoisson    Fixed-effects, random-effects, & population-averaged Poisson models
        xtnbreg      Fixed-effects, random-effects, & population-averaged negative binomial
                          models


    Generalized estimating equations estimator

        xtgee        Population-averaged panel-data models using GEE


    Utilities

        quadchk      Check sensitivity of quadrature approximation

自己查帮助或者手册
看有没有命令，不能猜测命令啊


Title

    [XT] xtunitroot -- Panel-data unit-root tests


Syntax

    Levin-Lin-Chu test

        xtunitroot llc varname [if] [in] [, LLC_options]


    Harris-Tzavalis test

        xtunitroot ht varname [if] [in] [, HT_options]


    Breitung test

        xtunitroot breitung varname [if] [in] [, Breitung_options]


    Im-Pesaran-Shin test

        xtunitroot ips varname [if] [in] [, IPS_options]


    Fisher-type tests (combining p-values)

        xtunitroot fisher varname [if] [in], {dfuller | pperron} lags(#) [Fisher_options]


    Hadri Lagrange multiplier stationarity test

        xtunitroot hadri varname [if] [in] [, Hadri_options]


    LLC_options            Description
    --------------------------------------------------------------------------------------------
    trend                  include a time trend
    noconstant             suppress panel-specific means
    demean                 subtract cross-sectional means
    lags(lag_spec)         specify lag structure for augmented Dickey-Fuller (ADF) regressions
    kernel(kernel_spec)    specify method to estimate long-run variance
    --------------------------------------------------------------------------------------------
    lag_spec is either a nonnegative integer or one of aic, bic, or hqic followed by a positive
      integer.
    kernel_spec takes the form kernel maxlags, where kernel is one of bartlett, parzen, or
      quadraticspectral and maxlags is either a positive number or one of nwest or llc.


    HT_options             Description
    --------------------------------------------------------------------------------------------
    trend                  include a time trend
    noconstant             suppress panel-specific means
    demean                 subtract cross-sectional means
    altt                   make small-sample adjustment to T
    --------------------------------------------------------------------------------------------


    Breitung_options       Description
    --------------------------------------------------------------------------------------------
    trend                  include a time trend
    noconstant             suppress panel-specific means
    demean                 subtract cross-sectional means
    robust                 allow for cross-sectional dependence
    lags(#)                specify lag structure for prewhitening
    --------------------------------------------------------------------------------------------


    IPS_options            Description
    --------------------------------------------------------------------------------------------
    trend                  include a time trend
    demean                 subtract cross-sectional means
    lags(lag_spec)         specify lag structure for ADF regressions
    --------------------------------------------------------------------------------------------
    lag_spec is either a nonnegative integer or one of aic, bic, or hqic followed by a positive
      integer.


    Fisher_options         Description
    --------------------------------------------------------------------------------------------
    * dfuller              use ADF unit-root tests
    * pperron              use Phillips-Perron unit-root tests
    * lags(#)              specify lag structure for prewhitening
      demean               subtract cross-sectional means
      dfuller_opts         any options allowed by the dfuller command
      pperron_opts         any options allowed by the pperron command
    --------------------------------------------------------------------------------------------
    * Either dfuller or pperron is required.
    * lags(#) is required.


    Hadri_options          Description
    --------------------------------------------------------------------------------------------
    trend                  include a time trend
    demean                 subtract cross-sectional means
    robust                 allow for cross-sectional dependence
    kernel(kernel_spec)    specify method to estimate long-run variance
    --------------------------------------------------------------------------------------------
    kernel_spec takes the form kernel [#], where kernel is one of bartlett, parzen, or
      quadraticspectral and # is a positive number.

    varname may contain time-series operators; see tsvarlist.


Menu

    Statistics > Longitudinal/panel data > Unit-root tests


Description

    xtunitroot performs a variety of tests for unit roots (or stationarity) in panel datasets.
    The Levin-Lin-Chu (2002), Harris-Tzavalis (1999), Breitung (2000; Breitung and Das 2005),
    Im-Pesaran-Shin (2003), and Fisher-type (Choi 2001) tests have as the null hypothesis that
    all the panels contain a unit root.  The Hadri (2000) Lagrange multiplier (LM) test has as
    the null hypothesis that all the panels are (trend) stationary.  The top of the output for
    each test makes explicit the null and alternative hypotheses.  Options allow you to include
    panel-specific means (fixed effects) and time trends in the model of the data-generating
    process.


Options

    LLC_options

    trend includes a linear time trend in the model that describes the process by which the
        series is generated.

    noconstant suppresses the panel-specific mean term in the model that describes the process
        by which the series is generated.  Specifying noconstant imposes the assumption that the
        series has a mean of zero for all panels.

    lags(lag_spec) specifies the lag structure to use for the ADF regressions performed in
        computing the test statistic.

        Specifying lags(#) requests that # lags of the series be used in the ADF regressions.
        The default is lags(1).

        Specifying lags(aic #) requests that the number of lags of the series be chosen such
        that the Akaike information criterion (AIC) for the regression is minimized.  xtunitroot
        llc will fit ADF regressions with 1 to # lags and choose the regression for which the
        AIC is minimized.  This process is done for each panel so that different panels may use
        ADF regressions with different numbers of lags.

        Specifying lags(bic #) is just like specifying lags(aic #), except that the Bayesian
        information criterion (BIC) is used instead of the AIC.

        Specifying lags(hqic #) is just like specifying lags(aic #), except that the
        Hannan-Quinn information criterion is used instead of the AIC.

    kernel(kernel_spec) specifies the method used to estimate the long-run variance of each
        panel's series.  kernel_spec takes the form kernel maxlags.  kernel is one of bartlett,
        parzen, or quadraticspectral.  maxlags is a number, nwest to request the Newey and West
        (1994) bandwidth selection algorithm, or llc to request the lag truncation selection
        algorithm in Levin, Lin, and Chu (2002).

        Specifying, for example, kernel(bartlett 3) requests the Bartlett kernel with 3 lags.

        Specifying kernel(bartlett nwest) requests the Bartlett kernel with the maximum number
        of lags determined by the Newey and West bandwidth selection algorithm.

        Specifying kernel(bartlett llc) requests the Bartlett kernel with the maximum number of
        lags determined by the method proposed in Levin, Lin, and Chu's (2002) article:

            maxlags = int(3.21*T^(1/3))

        where T is the number of observations per panel.  This is the default.

    demean requests that xtunitroot first subtract the cross-sectional averages from the series.
        When specified, for each time period xtunitroot computes the mean of the series across
        panels and subtracts this mean from the series.  Levin, Lin, and Chu suggest this
        procedure to mitigate the impact of cross-sectional dependence.