STATA作面板脉冲响应函数的编程是怎么做的
答案:1 悬赏:40 手机版
解决时间 2021-03-27 10:41
- 提问者网友:不要迷恋哥
- 2021-03-26 22:58
STATA作面板脉冲响应函数的编程是怎么做的
最佳答案
- 五星知识达人网友:拾荒鲤
- 2021-03-27 00:33
Title
[XT] pvar -- Panel Vector Autoregressive Models
Syntax
pvar depvarlist [if] [in][, gmm options]
options description
-------------------------------------------------------------------------
Model
gmm estimates the model coefficients using gmm
(required option; ust be specified as the first
option); gmm calls sgmm.ado; if not specified,
estimates from the previous run are taken from
the memory
lag(numlist) specifies the number of lags in the underlying VAR;
default is 1; numlist has to be integer >0
impulse generates numerical impulse-responses without error
bands
list_imp generates a table with impulse-responses (use after
impulse)
gr_imp generates graphical impulse-responses (witout error
bands)
monte [#] generates error bands for impulse-responses using
monte-carlo simulations; # is the desired number
of repetitions, default 200; if using monte[#]
for standard errors - no need specify impulse
list_mon lists a table containing impulse-responses and
standard errors (use after monte)
decomp [#] generates a table containing
variance-decompositions; # is the max. number of
periods, default is 20; to use different number,
use double quotes (e.g. "decomp 30"); note that
decomp prints only every 10th
-------------------------------------------------------------------------
You must tsset or xtset your data before using pvar, see help tsset or
xtset. depvarlist may contain time series operators. See depvarlist.
Description
pvar will estimate a PVAR model as described in Holtz et al. (1988). The
data has to be helmert transformed prior to estimation in order to remove
the fixed effects (see help helm). It is recommended that the original
variables should be time-demeaned before using helm. The model uses
untransformed variables as instruments for the helmert-transformed
variables in the model. In case one wants to estimate the model using a
different transformation (e.g. first differences), the easiest way is to
name the transformed variables h_y1 h_y2 ... To estimate the model
without fixed effects, create a copies of the original var amed h_y1
h_y2... The program will use the original variables as both, regressors
and instruments (i.e. system OLS without a constant).
depvarlist is the list with variable names in the desired order.
Different orderings will yield different responses. Note that when using
monte the maximum number of variables in depvarlist is 6.
Examples
. webuse grunfeld, clear
. rename company id
. xtset id year
. helm invest mvalue kstock
. pvar kstock invest mvalue, lag(3) gmm monte 500 "decomp 30"
[XT] pvar -- Panel Vector Autoregressive Models
Syntax
pvar depvarlist [if] [in][, gmm options]
options description
-------------------------------------------------------------------------
Model
gmm estimates the model coefficients using gmm
(required option; ust be specified as the first
option); gmm calls sgmm.ado; if not specified,
estimates from the previous run are taken from
the memory
lag(numlist) specifies the number of lags in the underlying VAR;
default is 1; numlist has to be integer >0
impulse generates numerical impulse-responses without error
bands
list_imp generates a table with impulse-responses (use after
impulse)
gr_imp generates graphical impulse-responses (witout error
bands)
monte [#] generates error bands for impulse-responses using
monte-carlo simulations; # is the desired number
of repetitions, default 200; if using monte[#]
for standard errors - no need specify impulse
list_mon lists a table containing impulse-responses and
standard errors (use after monte)
decomp [#] generates a table containing
variance-decompositions; # is the max. number of
periods, default is 20; to use different number,
use double quotes (e.g. "decomp 30"); note that
decomp prints only every 10th
-------------------------------------------------------------------------
You must tsset or xtset your data before using pvar, see help tsset or
xtset. depvarlist may contain time series operators. See depvarlist.
Description
pvar will estimate a PVAR model as described in Holtz et al. (1988). The
data has to be helmert transformed prior to estimation in order to remove
the fixed effects (see help helm). It is recommended that the original
variables should be time-demeaned before using helm. The model uses
untransformed variables as instruments for the helmert-transformed
variables in the model. In case one wants to estimate the model using a
different transformation (e.g. first differences), the easiest way is to
name the transformed variables h_y1 h_y2 ... To estimate the model
without fixed effects, create a copies of the original var amed h_y1
h_y2... The program will use the original variables as both, regressors
and instruments (i.e. system OLS without a constant).
depvarlist is the list with variable names in the desired order.
Different orderings will yield different responses. Note that when using
monte the maximum number of variables in depvarlist is 6.
Examples
. webuse grunfeld, clear
. rename company id
. xtset id year
. helm invest mvalue kstock
. pvar kstock invest mvalue, lag(3) gmm monte 500 "decomp 30"
我要举报
如以上问答信息为低俗、色情、不良、暴力、侵权、涉及违法等信息,可以点下面链接进行举报!
大家都在看
推荐资讯