Добавил:
Upload Опубликованный материал нарушает ваши авторские права? Сообщите нам.
Вуз: Предмет: Файл:
Eviews5 / EViews5 / Docs / EViews 5 Command Ref.pdf
Скачиваний:
91
Добавлен:
23.03.2015
Размер:
5.23 Mб
Скачать

268—Appendix B. Command Reference

Follow the dbpack keyword by a database name. You may include a path name to pack a database not in the default path.

Examples

dbpack findat

packs the database named FINDAT in the default path.

Cross-references

See “Packing the Database” on page 286 of the User’s Guide for additional discussion.

See also dbrebuild (p. 268) and dbrepair (p. 269)

dbrebuild Command

Rebuild an existing database.

Rebuild a seriously damaged database into a new database file.

Syntax

Command: dbrebuild [path\]source_name [path\]dest_name

Follow the dbrebuild keyword by the name of the database to be rebuilt, and then a new database name.

Examples

If you issue the command:

dbrebuild testdat fixed_testdat

EViews will attempt to rebuild the database TESTDAT into the database FIXED_TESTDAT in the default directory.

Cross-references

Note that dbrepair may be able to repair the existing database if the damage is not particularly serious. You should attempt to repair the database before rebuilding. See “Maintaining the Database” on page 285 of the User’s Guide for a discussion.

See also dbpack (p. 267) and dbrepair (p. 269).

dbrepair—269

dbrename Command

Rename an existing database.

dbrename renames all files associated with the specified database.

Syntax

Command: dbrename [path\]old_name [path\]new_name

Follow the dbrename keyword with the current name of an existing database and the new name for the database.

Examples

dbrename testdat mydat

Renames all files associated with the TESTDAT database in the specified directory to MYDAT in the default directory.

Cross-references

See Chapter 10, “EViews Databases”, on page 259 of the User’s Guide for a discussion of EViews databases.

See also db (p. 263) and dbcreate (p. 265). See also dbcopy (p. 264) and dbdelete (p. 266).

dbrepair Command

Repair an existing database.

This command is used to repair a damaged database.

Syntax

Command: dbrepair [path\]db_name

Follow the dbrepair keyword by the name of the database to repair. You should include a path name to repair a database not in the default path.

Examples

dbrepair testdat

EViews will attempt to repair the database TESTDAT in the default directory.

270—Appendix B. Command Reference

Cross-references

If the database is so damaged that it cannot be repaired, you may have to rebuild it into a new database using the dbrebuild (p. 268) command. See “Maintaining the Database” on page 285 of the User’s Guide for a discussion of EViews database maintenance.

See also dbpack (p. 267) and dbrebuild (p. 268).

decomp

Var View

 

 

Variance decomposition in VARs.

Syntax

 

Var View:

var_name.decomp(n, options) series_list [@ @ ordering]

List the series names in the VAR whose variance decomposition you would like to compute. You may optionally specify the ordering for the factorization after two “@”-signs.

You must specify the number of periods n over which to compute the variance decompositions.

Options

g (default)

Display combined graphs, with the decompositions for

 

each variable shown in a graph.

 

 

m

Display multiple graphs, with each response-shock pair

 

shown in a separate graph.

 

 

t

Show numerical results in table.

 

 

imp=arg

Type of factorization for the decomposition: “chol”

(default=“chol”)

(Cholesky with d.f. correction), “mlechol” (Cholesky

 

without d.f. correction), “struct” (structural).

 

The structural factorization is based on the estimated

 

structural VAR. To use this option, you must first esti-

 

mate the structural decomposition; see svar (p. 494).

 

The option “imp=mlechol” is provided for backward

 

compatibility with EViews 3.x and earlier.

 

 

se=mc

Monte Carlo standard errors. You must specify the num-

 

ber of replications with the “rep=” option.

 

Currently available only when you have specified the

 

Cholesky factorization (using the “imp=chol” option).

 

 

 

 

decomp—271

 

 

 

 

 

rep=integer

Number of Monte Carlo replications to be used in com-

 

 

puting the standard errors. Must be used with the

 

 

“se=mc” option.

 

 

 

 

matbys=name

Save responses by shocks (impulses) in named matrix.

 

 

 

The first column is the response of the first variable to

 

 

 

the first shock, the second column is the response of

 

 

 

the second variable to the first shock, and so on.

 

 

 

 

 

 

matbyr=name

Save responses by response series in named matrix.

 

 

The first column is the response of the first variable to

 

 

the first shock, the second column is the response of

 

 

the first variable to the second shock, and so on.

 

 

 

 

p

Print results.

 

 

 

 

 

If you use the “matbys=” or “matbyr=” options to store the results in a matrix, two matrices will be returned. The matrix with the specified name contains the variance decompositions, while the matrix with “_FSE” appended to the name contains the forecast standard errors for each response variable. If you have requested Monte Carlo standard errors, there will be a third matrix with “_SE” appended to the name which contains the variance decomposition standard errors.

Examples

var var1.ls 1 4 m1 gdp cpi

var1.decomp(10,t) gdp

The first line declares and estimates a VAR with three variables and lags from 1 to 4. The second line tabulates the variance decompositions of GDP up to 10 periods using the ordering as specified in VAR1.

var1.decomp(10,t) gdp @ @ cpi gdp m1

performs the same variance decomposition as above using a different ordering.

Cross-references

See “Variance Decomposition” on page 729 of the User’s Guide for additional details.

See also impulse (p. 324).

Соседние файлы в папке Docs