全部版块 我的主页
› 论坛 › 计量经济学与统计论坛 五区 › 计量经济学与统计软件 › Stata专版
关于豪斯曼检验的结果
xiaoxiangsz
80386 28
2012-08-02
做固定效应与随即效应的检验时，出现以下结果：
不太明白了

. hausman re fe

                 ---- Coefficients ----
             |      (b)          (B)            (b-B)     sqrt(diag(V_b-V_B))
             |       re           fe         Difference          S.E.
-------------+----------------------------------------------------------------
      lnpgdp |   -.0502868    -.1667916        .1165048               .
      lnind2 |   -.4981768     -.431718       -.0664588               .
    lntrade2 |   -.0308525    -.0482005         .017348               .
       lnfdi |    .0247837     .0306919       -.0059082               .
     lnstate |    -.034464    -.0600596        .0255956               .
       lntec |   -.0802212     .0073916       -.0876127               .
     lnfind2 |    .0127908     .1228647       -.1100739               .
     lnfisd1 |   -.0345988    -.0601249         .025526               .
  find2fisd1 |    .0002225    -.0067063        .0069287               .
        lnpg |   -.0945389    -.0816623       -.0128766               .
------------------------------------------------------------------------------
                           b = consistent under Ho and Ha; obtained from xtreg
            B = inconsistent under Ha, efficient under Ho; obtained from xtreg

    Test:  Ho:  difference in coefficients not systematic

                 chi2(10) = (b-B)'[(V_b-V_B)^(-1)](b-B)
                          =   -55.00    chi2<0 ==> model fitted on these
                                        data fails to meet the asymptotic
                                        assumptions of the Hausman test;
                                        see suest for a generalized test
二维码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

全部回复
蓝色
2012-8-2 18:44:11
你看过hausman的命令的帮助吗
二维码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

蓝色
2012-8-2 18:45:08
Title

    [R] hausman -- Hausman specification test


Syntax

        hausman name-consistent [name-efficient] [, options]

    options                   Description
    -------------------------------------------------------------------------------------------------------
    Main
      constant                include estimated intercepts in comparison; default is to exclude
      alleqs                  use all equations to perform test; default is first equation only
      skipeqs(eqlist)         skip specified equations when performing test
      equations(matchlist)    associate/compare the specified (by number) pairs of equations
      force                   force performance of test, even though assumptions are not met
      df(#)                   use # degrees of freedom
      sigmamore               base both (co)variance matrices on disturbance variance estimate from
                                efficient estimator
      sigmaless               base both (co)variance matrices on disturbance variance estimate from
                                consistent estimator

    Advanced
      tconsistent(string)     consistent estimator column header
      tefficient(string)      efficient estimator column header
    -------------------------------------------------------------------------------------------------------

    where name-consistent and name-efficient are names under which estimation results were saved via
        estimates store.
    A period (.) may be used to refer to the last estimation results, even if these were not already
        stored.
    Not specifying name-efficient is equivalent to specifying the last estimation results as ".".


Menu

    Statistics > Postestimation > Tests > Hausman specification test


Description

    hausman performs Hausman's specification test.  To use hausman, perform the following steps.

      (1) obtain an estimator that is consistent whether or not the hypothesis is true;
      (2) store the estimation results under name-consistent by using estimates store;
      (3) obtain an estimator that is efficient (and consistent) under the hypothesis that you are testing,
          but inconsistent otherwise;
      (4) store the estimation results under name-efficient by using estimates store;
      (5) use hausman to perform the test

              hausman name-consistent name-efficient [, options]

    The order of computing the two estimators may be reversed. You have to be careful, though, to specify
    to hausman the models in the order "always consistent" first and "efficient under H0" second. It is
    possible to skip storing the second model and refer to the last estimation results by a period (.).

    hausman may be used in any context.  The order in which you specify the regressors in each model does
    not matter, but you must ensure that the estimators and models are comparable and that they satisfy the
    theoretical conditions (see (1) and (3) above).


Options

        +------+
    ----+ Main +-------------------------------------------------------------------------------------------

    constant specifies that the estimated intercept(s) be included in the model comparison; by default,
        they are excluded.  The default behavior is appropriate for models in which the constant does not
        have a common interpretation across the two models.

    alleqs specifies that all the equations in the models be used to perform the Hausman test; by default,
        only the first equation is used.

    skipeqs(eqlist) specifies in eqlist the names of equations to be excluded from the test.  Equation
        numbers are not allowed in this context, because the equation names, along with the variable names,
        are used to identify common coefficients.

    equations(matchlist) specifies, by number, the pairs of equations that are to be compared.

        The matchlist in equations() should follow the syntax

            #c:#e [,#c:#e[, ...]]

        where #c(#e) is an equation number of the always-consistent (efficient under H0) estimator.  For
        instance equations(1:1), equations(1:1, 2:2), or equations(1:2).

        If equations() is not specified, then equations are matched on equation names.

        equations() handles the situation in which one estimator uses equation names and the other does
        not.  For instance, equations(1:2) means that equation 1 of the always-consistent estimator is to
        be tested against equation 2 of the efficient estimator.  equations(1:1, 2:2) means that equation 1
        is to be tested against equation 1 and that equation 2 is to be tested against equation 2.  If
        equations() is specified, the alleqs and skipeqs options are ignored.

    force specifies that the Hausman test be performed, even though the assumptions of the Hausman test
        seem not to be met, for example, because the estimators were pweighted or the data were clustered.

    df(#) specifies the degrees of freedom for the Hausman test.  The default is the matrix rank of the
        variance of the difference between the coefficients of the two estimators.

    sigmamore and sigmaless specify that the two covariance matrices used in the test be based on a common
        estimate of disturbance variance (sigma2).

        sigmamore specifies that the covariance matrices be based on the estimated disturbance variance
            from the efficient estimator.  This option provides a proper estimate of the contrast variance
            for so-called tests of exogeneity and overidentification in instrumental-variables regression.

        sigmaless specifies that the covariance matrices be based on the estimated disturbance variance
            from the consistent estimator.

        These options can be specified only when both estimators save e(sigma) or e(rmse), or with the
        xtreg command.  e(sigma_e) is saved after the xtreg command with the fe or mle option.  e(rmse) is
        saved after the xtreg command with the re option.

        sigmamore or sigmaless are recommended when comparing fixed-effects and random-effects linear
        regression because they are much less likely to produce a non-positive-definite-differenced
        covariance matrix (although the tests are asymptotically equivalent whether or not one of the
        options is specified).

        +----------+
    ----+ Advanced +---------------------------------------------------------------------------------------

    tconsistent(string) and tefficient(string) are formatting options.  They allow you to specify the
        headers of the columns of coefficients that default to the names of the models.  These options will
        be of interest primarily to programmers.


Remark:  An alternative to hausman

    The assumption that one of the estimators is efficient (that is, has minimal asymptotic variance) is a
    demanding one.  It is violated, for instance, if your observations are clustered or pweighted, or if
    your model is somehow misspecified.  Moreover, even if the assumption is satisfied, there may be a
    "small sample" problem with the Hausman test.  Hausman's test is based on estimating the variance
    var(b-B) of the difference of the estimators by the difference var(b)-var(B) of the variances.  Under
    the assumptions (1) and (3), var(b)-var(B) is a consistent estimator of var(b-B), but it is not
    necessarily positive definite "in finite samples", that is, in your application.  If this is the case,
    the Hausman test is undefined.  Unfortunately, this is not a rare event.  Stata supports a generalized
    Hausman test that overcomes both of these problems.  See [R] suest for details.


Examples

    ---------------------------------------------------------------------------------------------------------
    Setup
        . webuse nlswork4
        . xtreg ln_wage age msp ttl_exp, fe
        . estimates store fixed
        . xtreg ln_wage age msp ttl_exp, re

    Test the appropriateness of the random-effects estimator (xtreg, re)
        . hausman fixed ., sigmamore

    ----------------------------------------------------------
二维码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

xiaoxiangsz
2012-8-2 20:36:27
蓝色 发表于 2012-8-2 18:45
Title

    [R] hausman -- Hausman specification test
谢谢斑竹。

主要是这里： Test:  Ho:  difference in coefficients not systematic

                 chi2(10) = (b-B)'[(V_b-V_B)^(-1)](b-B)
                          =   -55.00    chi2<0 ==> model fitted on these

出现的是负值，之后不能进行检验啊。不知道哪里出了问题了
二维码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

sewind_tj
2012-8-2 22:09:58
xiaoxiangsz 发表于 2012-8-2 20:36
谢谢斑竹。

主要是这里： Test:  Ho:  difference in coefficients not systematic
请看hausman的选项。出现负值一般选择固定效应模型。
二维码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

xiaoxiangsz
2012-8-3 14:19:25
sewind_tj 发表于 2012-8-2 22:09
请看hausman的选项。出现负值一般选择固定效应模型。
感谢，我知道哪里出了问题了。- -#
hausman检验后面的fe re顺序调换一下，就好了- -#
二维码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

点击查看更多内容…
相关推荐
栏目导航
热门文章
推荐文章

说点什么

分享

微信QQ空间QQ微博
扫码加好友，拉您进群
各岗位、行业、专业交流群