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

unlink—519

c

One step iteration of the coefficient vector after one step

 

of the weighting matrix.

 

 

l=number

Set maximum number of iterations on the first-stage

 

iteration to get one-step weighting matrix.

 

 

Examples

eq1.tsls y_d c cpi inc ar(1) @ lw(-1 to -3)

estimates EQ1 using TSLS regression of Y_D on a constant, CPI, INC with AR(1) using a constant, LW(-1), LW(-2), and LW(-3) as instruments.

param c(1) .1 c(2) .1

eq1.tsls(s,m=500) y_d=c(1)+inc^c(2) @ cpi

estimates a nonlinear TSLS model using a constant and CPI as instruments. The first line sets the starting values for the nonlinear iteration algorithm.

sys1.tsls

estimates the system object using TSLS.

pool1.tsls y? c x? @inst z?

estimates TSLS on the pool specification using common instruments Z?

Cross-references

See “Two-stage Least Squares” on page 471 and “Two-Stage Least Squares” on page 695 of the User’s Guide for details on two-stage least squares estimation in single equations and systems, respectively. “Instrumental Variables” on page 865 discusses estimation using pool objects, while “Instrumental Variables Estimation” on page 902 discusses estimation in panel structured workfiles.

See also ls (p. 345). For estimation of weighted TSLS in systems, see wtsls (p. 547).

unlink

Command || Model Proc

 

 

Break links in series objects or models.

Syntax

Command:

unlink link_names

Model Proc:

object.unlink spec

520—Appendix B. Command Reference

When used as a command, unlink converts link objects to ordinary series or alphas. Follow the keyword with a list of names of links to be converted to ordinary series (values). The list of links may include wildcard characters.

Used as a model proc, unlink breaks equation links in the model. Follow the name of the model object by a period, the keyword, and a specification for the variables to unlink.

The spec may contain either a list of the endogenous variables to be unlinked, or the keyword “@ALL”, instructing EViews to unlink all equations in the model.

Note: if a link is to another model or a system object, more than one endogenous variable may be associated with the link. If the spec contains any of the endogenous variables in a linked model or system, EViews will break the link for all of the variables found in the link.

Examples

unlink gdp income

converts the link series GDP and INCOME to ordinary series.

unlink *

breaks all links in the current workfile page.

Used as a model proc, the expressions:

mod1.unlink @all

mod2.unlink z1 z2

unlink all of equations in MOD1, and all of the variables associated with the links for Z1 and Z2 in MOD2.

Cross-references

See Chapter 8, “Series Links”, on page 175 for a detailed description of link objects. See also link (p. 338) and linkto (p. 339).

See Chapter 26, “Models”, on page 775 of the User’s Guide for a discussion of specifying and solving models in EViews. See also append (p. 205), merge (p. 368) and solve (p. 475).

update

Model Proc

 

 

Update model specification.

Recompiles the model and updates all links.

updatecoefs—521

Syntax

Model Proc:

model.update

Follow the name of the model object by a period and the keyword update.

Examples

mod1.update

recompiles and updates all of the links in MOD1.

Cross-references

See Chapter 26, “Models”, on page 775 of the User’s Guide for a discussion of specifying and solving models in EViews. See also append (p. 205), merge (p. 368) and solve (p. 475).

updatecoefs

Equation Proc | Logl Proc | Pool Proc | Sspace Proc | System Proc

 

 

Update coefficient object values from estimation object.

Copies coefficients from the estimation object into the appropriate coefficient vector or vectors.

Syntax

Object Proc: object.updatecoef

Follow the name of the estimation object by a period and the keyword updatecoef.

Examples

equation eq1.ls y c x1 x2 x3

equation eq2.ls z c z1 z2 z3

eq1.updatecoef

places the coefficients from EQ1 in the default coefficient vector C.

coef(3) a

equation eq3.ls y=a(1)+z1^c(1)+log(z2+a(2))+exp(c(4)+z3/a(3))

equation eq2.ls z c z1 z2 z3

eq3.updatecoef

updates the coefficient vector A and the default vector C so that both contain the coefficients from EQ3.

522—Appendix B. Command Reference

Cross-references

See also coef (p. 243).

uroot

Command || Group View | Pool View | Series View

 

 

Carries out unit root tests on a single series, pool series, group of series, or panel structured series.

The ordinary, single series unit root tests include Augmented Dickey-Fuller (ADF), GLS detrended Dickey-Fuller (DFGLS), Phillips-Perron (PP), Kwiatkowski, et. al. (KPSS), Elliot, Rothenberg, and Stock (ERS) Point Optimal, or Ng and Perron (NP) tests for a unit root in the series (or its first or second difference).

If used on a series in a panel structured workfile, or with a pool series, or group of series, the procedure will perform panel unit root testing. The panel unit root tests include Levin, Lin and Chu (LLC), Breitung, Im, Pesaran, and Shin (IPS), Fisher - ADF, Fisher - PP, and Hadri tests on levels, or first or second differences.

Syntax

Command:

uroot(options) series_name

Group View:

group_name.uroot(options)

Pool View:

pool_name.uroot(options) pool_series

Series View:

series_name.uroot(options)

Tests on a single series may be carried out in two ways: as a command, or as a procedure off of the series. Accordingly, you may enter the keyword followed by the individual series name, or you may enter the series name followed by a period and the keyword.

For other cases, you should enter the object name followed by a period, the keyword, and in the case of pool testing, the name of a pool “?” series.

Options

Basic Specification Options

You should specify the exogenous variables and order of dependent variable differencing in the test equation using the following options:

const (default)

Include a constant in the test equation.

 

 

trend

Include a constant and a linear time trend in the test

 

equation.

uroot—523

none

Do not include a constant or time trend (only available

 

for the ADF and PP tests).

 

 

dif=integer

Order of differencing of the series prior to running the

(default=0)

test. Valid values are {0, 1, 2}.

For backward compatibility, the shortened forms of these options, “c”, “t”, and “n”, are presently supported. For future compatibility we recommend that you use the longer forms.

For ordinary (non-panel) unit root tests, you should specify the test type using one of the following keywords:

adf (default)

Augmented Dickey-Fuller.

 

 

dfgls

GLS detrended Dickey-Fuller (Elliot, Rothenberg, and

 

Stock).

 

 

pp

Phillips-Perron.

 

 

kpss

Kwiatkowski, Phillips, Schmidt, and Shin.

 

 

ers

Elliot, Rothenberg, and Stock (Point Optimal).

 

 

np

Ng and Perron.

For panel testing, you may use one of the following keywords to specify the test:

sum (default)

Summary of all of the panel unit root tests.

 

 

llc

Levin, Lin, and Chu.

 

 

breit

Breitung.

 

 

ips

Im, Pesaran, and Shin.

 

 

adf

Fisher - ADF.

 

 

pp

Fisher - PP.

 

 

hadri

Hadri.

 

 

Options for ordinary (non-panel) unit root tests

In addition, the following panel specific options are available:

524—Appendix B. Command Reference

hac=arg

Method of estimating the frequency zero spectrum: “bt”

 

(Bartlett kernel), “pr” (Parzen kernel), “qs” (Quadratic

 

Spectral kernel), “ar” (AR spectral), “ardt (AR spectral -

 

OLS detrended data), “argls” (AR spectral - GLS

 

detrended data).

 

Applicable to PP, KPSS, ERS, and NP tests. The default

 

settings are test specific (“bt” for PP and KPSS, “ar” for

 

ERS, “argls” for NP).

 

 

band = arg,

Method of selecting the bandwidth: “nw” (Newey-West

b=arg

automatic variable bandwidth selection), “a” (Andrews

(default=“nw”)

automatic selection), “number” (user specified band-

 

width).

 

Applicable to PP, KPSS, ERS, and NP tests when using

 

kernel sums-of-covariances estimators (where “hac=”

 

is one of {bt, pz, qs}).

 

 

lag=arg

Method of selecting lag length (number of first differ-

(default=“a”)

ence terms) to be included in the regression: “a” (auto-

 

matic information criterion based selection), or

 

integer” (user-specified lag length).

 

Applicable to ADF and DFGLS tests, and for the other

 

tests when using AR spectral density estimators (where

 

“hac=” is one of {ar, ardt, argls}).

 

 

info=arg

Information criterion to use when computing automatic

(default=“sic”)

lag length selection: “aic” (Akaike), “sic” (Schwarz),

“hqc” (Hannan-Quinn), “msaic” (Modified Akaike),

 

 

“msic” (Modified Schwarz), “mhqc” (Modified Han-

 

nan-Quinn).

 

Applicable to ADF and DFGLS tests, and for other tests

 

when using AR spectral density estimators (where

 

“hac=” is one of {ar, ardt, argls}).

maxlag=integer

Maximum lag length to consider when performing

 

automatic lag length selection:

 

default= int((12T 100)0.25)

Applicable to ADF and DFGLS tests, and for other tests when using AR spectral density estimators (where “hac=” is one of {ar, ardt, argls}).

uroot—525

Options for panel unit root tests

The following panel specific options are available:

balance

Use balanced (across cross-sections or series) data

 

when performing test.

 

 

hac=arg

Method of estimating the frequency zero spectrum: “bt”

(default=“bt”)

(Bartlett kernel), “pr” (Parzen kernel), “qs” (Quadratic

 

Spectral kernel).

 

Applicable to “Summary”, LLC, Fisher-PP, and Hadri

 

tests.

 

 

band = arg,

Method of selecting the bandwidth: “nw” (Newey-West

b=arg

automatic variable bandwidth selection), “a” (Andrews

(default=“nw”)

automatic selection), number (user-specified common

 

bandwidth), vector_name (user-specified individual

 

bandwidth).

 

Applicable to “Summary”, LLC, Fisher-PP, and Hadri

 

tests.

 

 

lag=arg

Method of selecting lag length (number of first differ-

 

ence terms) to be included in the regression: “a” (auto-

 

matic information criterion based selection), integer

 

(user-specified common lag length), vector_name (user-

 

specific individual lag length).

 

If the “balance” option is used,

 

1

if (T

min

60)

 

 

 

 

 

 

2

if (60 < T

 

100)

default=

min

 

 

if (Tmin >

 

 

4

100)

where Tmin is the length of the shortest cross-section or series, otherwise default=“a”.

Applicable to “Summary”, LLC, Breitung, IPS, and

Fisher-ADF tests.

526—Appendix B. Command Reference

info=arg

(default=“sic”)

maxlag=arg

Other options

Information criterion to use when computing automatic lag length selection: “aic” (Akaike), “sic” (Schwarz), “hqc” (Hannan-Quinn), “msaic” (Modified Akaike), “msic” (Modified Schwarz), “mhqc” (Modified Han- nan-Quinn).

Applicable to “Summary”, LLC, Breitung, IPS, and Fisher-ADF tests.

Maximum lag length to consider when performing automatic lag length selection, where arg is an integer (common maximum lag length) or a vector_name (individual maximum lag length)

default= int(mini(12, Ti 3) (Ti 100)0.25) where Ti is the length of the cross-section or series.

p

Print output from the test.

 

 

Examples

The command:

gnp.uroot(adf,const,lag=3,save=mout)

performs an ADF test on the series GDP with the test equation including a constant term and three lagged first-difference terms. Intermediate results are stored in the matrix MOUT.

ip.uroot(dfgls,trend,info=sic)

runs the DFGLS unit root test on the series IP with a constant and a trend. The number of lagged difference terms is selected automatically using the Schwarz criterion.

unemp.uroot(kpss,const,hac=pr,b=2.3)

runs the KPSS test on the series UNEMP. The null hypothesis is that the series is stationary around a constant mean. The frequency zero spectrum is estimated using kernel methods (with a Parzen kernel), and a bandwidth of 2.3.

sp500.uroot(np,hac=ardt,info=maic)

runs the NP test on the series SP500. The frequency zero spectrum is estimated using the OLS AR spectral estimator with the lag length automatically selected using the modified AIC.

Соседние файлы в папке Docs