svar.hlp

是一个经济学管理应用软件 很难找的 但是经济学学生又必须用到

{center:{space 4}{c |} 1     0  {c |}}
{center:{space 4}{c BLC}{space 10}{c BRC}}

{pmore2}
   Specifying, {cmd:acns(A)} in a two-equation SVAR constrains
   {bf:A}[2,1]={bf:A}[1,2], {bf:A}[2,2]=0 while leaving {bf:A}[1,1] free.

{phang2}
{opt bconstraints(constraints_a)} specifies a {it:{help numlist}} of
   previously defined Stata constraints to be applied to {bf:B} during
   estimation.

{phang2}
{opt beq(matrix_beq)} specifies a matrix that defines a set of
   equality constraints.  This matrix must be square with dimension equal to
   the number of equations in the underlying VAR.  The elements of this matrix
   must be either {it:missing} or real numbers.  The syntax of implied
   constraints is analogous to the one described in {opt aeq()}, except it
   applies to {bf:B} rather than to {bf:A}.

{phang2}
{opt bcns(matrix_bcns)} specifies a matrix that defines a set of
   exclusion or cross-parameter equality constraints on {bf:B}.  This matrix
   must be square with dimension equal to the number of equations in the
   underlying VAR.  Each element of this matrix must be {it:missing}, 0, or a
   positive integer.  The format of the implied constraints is the same as the
   one described in the {opt acns()} option above.

{phang}
{opt lrconstraints(constraints_lr)},
{opt lreq(matrix_lreq)},
{opt lrcns(matrix_lrcns)}{p_end}
{pmore}
   These options specify the long-run constraints in an SVAR.  To specify a
   long-run SVAR model, you must specify at least one of these options.  The
   list of options specifies constraints on the parameters of the long-run
   {bf:C} matrix.  None of these options may be specified with any of the
   options that define short-run constraints.

{phang2}
{opt lrconstraints(constraints_lr)} specifies a {it:{help numlist}} of
   previously defined Stata constraints to be applied to {bf:C} during
   estimation.

{phang2}
{opt lreq(matrix_lreq)} specifies a matrix that defines a set
   of equality constraints on the elements of {bf:C}.  This matrix must be
   square with dimension equal to the number of equations in the underlying
   VAR.  The elements of this matrix must be either {it:missing} or real
   numbers.  The syntax of implied constraints is analogous to the one
   described in option {opt aeq()} above except it applies to {bf:C}.

{phang2}
{opt lrcns(matrix_lrcns)} specifies a matrix that defines a set
   of exclusion or cross-parameter equality constraints on {bf:C}.  This
   matrix must be square with dimension equal to the number of equations in
   the underlying VAR.  Each element of this matrix must be {it:missing}, 0,
   or a positive integer.  The syntax of the implied constraints is the same
   as the one described for the {opt acns()} option above.

{phang}
{opth lags(numlist)} specifies the lags to be included in the underlying VAR
   model.  Note that this option takes a {it:numlist} and not simply an
   integer for the maximum lag.  For instance, {cmd:lags(2)} would include
   only the second lag in the model, while {cmd:lags(1/2)} would include both
   the first and second lags in the model.  See {it:{help numlist}} and
   {bind:{bf:[U] 13.8 Time-series operators}} for further discussion of
   {it:numlist}s and lags.

{dlgtab:Model 2}

{phang}
{opth "exog(varlist:varlist_exog)"} specifies a list of exogenous variables to
be included in the underlying VAR.

{phang}
{opt varconstraints(constraints_v)} specifies a list of constraints to
    be applied to the coefficients in the underlying VAR.  Since {opt svar}
    estimates multiple equations, the constraints must specify the equation
    name for all but the first equation.

{phang}
{opt noislog} prevents {opt svar} from displaying the iteration log from the
   iterated seemingly unrelated regression algorithm.  When the
   {opt varconstraints()} option is not specified, the VAR coefficients are
   estimated via OLS, a noniterative procedure.  As a result, {opt noislog}
   may only be specified with {opt varconstraints()}.  Similarly,
   {opt noislog} may not be combined with {opt noisure}.

{phang}
{opt isiterate(#)} sets the maximum number of iterations for the iterated,
   seemingly unrelated regression algorithm.  The default limit is 1600.
   When the {opt varconstraints()} option is not specified, the VAR
   coefficients are estimated via OLS, a noniterative procedure.  As a result,
   {opt isiterate()} may only be specified with {opt varconstraints()}.
   Similarly, {opt isiterate()} may not be combined with {opt noisure}.

{phang}
{opt istolerance(#)} specifies the convergence tolerance of the iterated,
   seemingly unrelated regression algorithm.  The default tolerance is
   {cmd:1e-6}.  When the {opt varconstraints()} option is not specified, the
   VAR coefficients are estimated via OLS, a noniterative procedure.  As a
   result, {opt istolerance()} may only be specified with {opt varconstraints()}.
   Similarly, {opt istolerance()} may not be combined with
   {opt noisure}.

{phang}
{opt noisure} specifies that the VAR coefficients be estimated via one-step
   seemingly unrelated regression when {opt varconstraints()} is specified.
   By default, {opt svar} estimates the coefficients in the VAR via iterated,
   seemingly unrelated regression when {opt varconstraints()} is specified.
   When the {opt varconstraints()} option is not specified, the VAR
   coefficient estimates are obtained via OLS, a noniterative procedure.  As a
   result, {opt noisure} may only be specified with {opt varconstraints()}.

{phang}
{opt dfk} specifies that a small-sample degrees-of-freedom adjustment
   be used when estimating the covariance matrix of the VAR disturbances.
   Specifically, 1/(T-mparms) is used instead of the large sample 1/T, where
   mparms is the average number of parameters in the functional form for y_t
   over the K equations.

{phang}
{opt small} causes {opt svar} to calculate and report small-sample t and
   F statistics instead of the large-sample normal and chi-squared
   statistics.

{phang}
{opt noidencheck} requests that the Amisano and Giannini check for local
   identification not be performed.  This check is local to the starting
   values used.  Because of this dependence on the starting values, you may
   wish to suppress this check by specifying the {opt noidencheck} option.
   However, be careful in specifying this option.  Models that are not
   structurally identified can still converge, thereby producing meaningless
   results that only appear to have meaning.

{phang}
{opt nobigf} requests that {opt var} not compute the estimated parameter
   vector that incorporates coefficients that have been implicitly constrained
   to be zero, such as when some lags have been omitted from a model.
   {cmd:e(bf_var)} is used for computing asymptotic standard errors in the
   postestimation commands {helpb irf create} and {helpb fcast}.  Therefore,
   specifying {opt nobigf} implies that the asymptotic standard errors will
   not be available from the {opt irf create} and {opt fcast} postestimation
   routines.  See {it:Fitting models with some lags excluded} in {bf:[TS] var}
   for details.

{dlgtab:Reporting}

{phang}
{opt level(#)}; see {help estimation options##level():estimation options}.

{phang}
{opt full} shows constrained parameters in table.

{phang}
{opt var} specifies that the output from {opt var} also be displayed.
By default, the underlying VAR is fit {helpb quietly}.

{phang}
{opt lutstats} specifies that the L{c u:}tkepohl versions of the lag-order
   selection statistics be computed.  See Methods and Formulas in
   {bf:[TS] varsoc} for a discussion of these statistics.

{marker maximize_options}{...}
{dlgtab:Max options}

{phang}
{it:maximize_options}:
{opt diff:icult},
{opt tech:nique(algorithm_spec)},
{opt iter:ate(#)},
[{cmdab:no:}]{opt lo:g},
{opt tr:ace},
{opt grad:ient},
{opt showstep},
{opt hess:ian},
{opt shownr:tolerance},
{opt tol:erance(#)},
{opt ltol:erance(#)},
{opt gtol:erance(#)},
{opt nrtol:erance(#)},
{opt nonrtol:erance(#)},
{opt from(init_specs)};
see {help maximize}.
These options are seldom used.


{title:Examples}

{phang}{cmd:. matrix A = (1, 0 ,0\ ., 1, 0\ ., ., 1)}{p_end}
{phang}{cmd:. matrix B = (., 0 ,0\ 0, ., 0\ 0, 0, .)}{p_end}
{phang}{cmd:. svar dlinvestment dlincome dlconsumption, aeq(A) beq(B)}{p_end}

{phang}{cmd:. matrix C = (., 0\ 0, .)}{p_end}
{phang}{cmd:. svar dlnm dlngdp, lreq(C)}{p_end}


{title:Also see}

{psee}
Manual:  {bf:[TS] var svar}

{psee}
Online:  {help svar postestimation};{break}
{helpb arch},
{helpb arima},
{helpb reg3},
{helpb regress},
{helpb sureg},
{helpb tsset},
{helpb var}, 
{helpb varbasic},
{helpb vec}
{p_end}