ARDL GoodSlides PDF
ARDL GoodSlides PDF
ARDL GoodSlides PDF
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 1/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
1
Another commonly used abbreviation is ADL.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 2/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 3/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
5
1960 1965 1970 1975 1980
log consumption
log income
log investment
Data: National accounts, West Germany, seasonally adjusted, quarterly, billion DM, Lütkepohl (1993, Table E.1).
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 4/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
ARDL model
ARDL(p, q, . . . , q) model:
p q
β 0i xt−i + ut ,
X X
yt = c0 + c1 t + φi yt−i +
i=1 i=0
ARDL(4,1,0) regression
------------------------------------------------------------------------------
ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ln_consump |
L1. | .4568483 .1064085 4.29 0.000 .2450887 .6686079
L2. | .3250994 .1127767 2.88 0.005 .1006666 .5495322
L3. | .1048324 .1092992 0.96 0.340 -.11268 .3223449
L4. | -.1632413 .0853844 -1.91 0.059 -.3331616 .0066791
|
ln_inc |
--. | .4629184 .078421 5.90 0.000 .3068557 .6189812
L1. | -.202756 .0965775 -2.10 0.039 -.3949513 -.0105607
|
ln_inv | .0080284 .0118391 0.68 0.500 -.0155322 .0315889
_cons | .0373585 .0143755 2.60 0.011 .0087504 .0659667
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 6/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
lagcombs[12,4]
ln_consump ln_inc ln_inv aic
r1 1 0 0 -585.22447
r2 1 1 0 -585.39189
r3 1 2 0 -583.88179
r4 2 0 0 -590.66282
r5 2 1 0 -592.6904
r6 2 2 0 -591.62792
r7 3 0 0 -588.69069
r8 3 1 0 -590.83183
r9 3 2 0 -589.67101
r10 4 0 0 -590.03466
r11 4 1 0 -592.73282
r12 4 2 0 -592.15636
. estat ic
-----------------------------------------------------------------------------
Model | Obs ll(null) ll(model) df AIC BIC
-------------+---------------------------------------------------------------
. | 88 -64.51057 304.3747 8 -592.7495 -572.9308
-----------------------------------------------------------------------------
Note: N=Obs used in calculating BIC; see [R] BIC note.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 7/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ln_consump |
L1. | .3068554 .0958427 3.20 0.002 .1160853 .4976255
L2. | .325385 .0789039 4.12 0.000 .1683307 .4824393
|
ln_inc | .3682844 .041534 8.87 0.000 .285613 .4509558
|
ln_inv |
--. | .0656722 .0180596 3.64 0.000 .0297255 .1016189
L1. | -.0375288 .0225036 -1.67 0.099 -.0823212 .0072636
L2. | .0228142 .0228968 1.00 0.322 -.0227607 .0683892
L3. | -.0129321 .0226411 -0.57 0.569 -.0579981 .0321339
L4. | -.0528173 .0184696 -2.86 0.005 -.0895801 -.0160544
|
_cons | .0469399 .0110639 4.24 0.000 .0249178 .068962
------------------------------------------------------------------------------
. timer off 1
. timer list 1
1: 0.01 / 1 = 0.0150
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 8/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ln_consump |
L1. | .3068554 .0958427 3.20 0.002 .1160853 .4976255
L2. | .325385 .0789039 4.12 0.000 .1683307 .4824393
|
ln_inc | .3682844 .041534 8.87 0.000 .285613 .4509558
|
ln_inv |
--. | .0656722 .0180596 3.64 0.000 .0297255 .1016189
L1. | -.0375288 .0225036 -1.67 0.099 -.0823212 .0072636
L2. | .0228142 .0228968 1.00 0.322 -.0227607 .0683892
L3. | -.0129321 .0226411 -0.57 0.569 -.0579981 .0321339
L4. | -.0528173 .0184696 -2.86 0.005 -.0895801 -.0160544
|
_cons | .0469399 .0110639 4.24 0.000 .0249178 .068962
------------------------------------------------------------------------------
. timer off 2
. timer list 2
2: 0.75 / 1 = 0.7520
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 9/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
ARDL(2,0,4) regression
------------------------------------------------------------------------------
ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ln_consump |
L1. | .30383 .0942165 3.22 0.002 .1161411 .491519
L2. | .3195318 .0776321 4.12 0.000 .1648808 .4741828
|
ln_inc | .3767587 .0389267 9.68 0.000 .2992128 .4543046
|
ln_inv |
--. | .0581759 .0170736 3.41 0.001 .0241635 .0921884
L1. | -.0185484 .0214624 -0.86 0.390 -.0613036 .0242068
L2. | .01012 .021505 0.47 0.639 -.0327202 .0529602
L3. | -.0146641 .0213098 -0.69 0.493 -.0571154 .0277872
L4. | -.0488136 .0174121 -2.80 0.006 -.0835003 -.0141269
|
_cons | .0416317 .0107782 3.86 0.000 .0201603 .063103
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 10/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
EC representation
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 12/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
D.ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ADJ |
ln_consump |
L1. | -.3677596 .0406085 -9.06 0.000 -.4485888 -.2869304
-------------+----------------------------------------------------------------
LR |
ln_inc | 1.001427 .0265233 37.76 0.000 .9486337 1.05422
ln_inv | -.0402213 .0309082 -1.30 0.197 -.1017424 .0212999
-------------+----------------------------------------------------------------
SR |
ln_consump |
LD. | -.325385 .0789039 -4.12 0.000 -.4824393 -.1683307
|
ln_inv |
D1. | .080464 .0187106 4.30 0.000 .0432214 .1177066
LD. | .0429352 .0193931 2.21 0.030 .0043342 .0815361
L2D. | .0657494 .0181592 3.62 0.001 .0296045 .1018943
L3D. | .0528173 .0184696 2.86 0.005 .0160544 .0895801
|
_cons | .0469399 .0110639 4.24 0.000 .0249178 .068962
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 13/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
D.ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ADJ |
ln_consump |
L1. | -.3677596 .0406085 -9.06 0.000 -.4485888 -.2869304
-------------+----------------------------------------------------------------
LR |
ln_inc |
L1. | 1.001427 .0265233 37.76 0.000 .9486337 1.05422
|
ln_inv |
L1. | -.0402213 .0309082 -1.30 0.197 -.1017424 .0212999
-------------+----------------------------------------------------------------
SR |
ln_consump |
LD. | -.325385 .0789039 -4.12 0.000 -.4824393 -.1683307
|
ln_inc |
D1. | .3682844 .041534 8.87 0.000 .285613 .4509558
|
ln_inv |
D1. | .0656722 .0180596 3.64 0.000 .0297255 .1016189
LD. | .0429352 .0193931 2.21 0.030 .0043342 .0815361
L2D. | .0657494 .0181592 3.62 0.001 .0296045 .1018943
L3D. | .0528173 .0184696 2.86 0.005 .0160544 .0895801
|
_cons | .0469399 .0110639 4.24 0.000 .0249178 .068962
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 14/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
D.ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ADJ |
ln_consump |
L1. | -.3788728 .0420886 -9.00 0.000 -.4626481 -.2950975
-------------+----------------------------------------------------------------
LR |
ln_inc | .9669152 .0039557 244.44 0.000 .9590416 .9747889
-------------+----------------------------------------------------------------
SR |
ln_consump |
LD. | -.346926 .0806726 -4.30 0.000 -.5075007 -.1863512
L2D. | -.1074193 .0790118 -1.36 0.178 -.2646883 .0498497
|
ln_inv |
D1. | .0758713 .0176989 4.29 0.000 .0406425 .1111002
LD. | .0422224 .0191523 2.20 0.030 .0041008 .080344
L2D. | .0678568 .0185208 3.66 0.000 .030992 .1047216
L3D. | .0485441 .0179609 2.70 0.008 .0127938 .0842944
|
_cons | .0504873 .0114518 4.41 0.000 .027693 .0732816
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 15/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
EC representation: Interpretation
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 16/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 17/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
3 Pq
The test is not directly performed on the long-run coefficients θ = βj /α.
j=0
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 18/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 19/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
4
The number of short-run coefficients only affects the finite-sample but not the asymptotic critical values
(Cheung and Lai, 1995; Kripfganz and Schneider, 2018). The elements of ω in the ec1 parameterization for
variables that have 0 lags in the ARDL model do not count towards this number.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 20/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
Test decisions:
Do not reject H0F or H0t , respectively, if the test statistic is
closer to zero than the lower bound of the critical values.
Reject the H0F or H0t , respectively, if the test statistic is more
extreme than the upper bound of the critical values.
The first two steps of the bounds test are implemented in the
ardl postestimation command estat ectest.
By default, finite-sample critical values for the 1%, 5%, and
10% significance levels are provided. Asymptotic critical values
are displayed with option asymptotic. Alternative significance
levels can be specified with option siglevels(numlist ).
The test statistics in step 3 have the usual asymptotic
standard normal (or χ2 ) distributions irrespective of the
integration order of the independent variables.5
5
The OLS estimator for the long-run coefficients θ of I(1) independent variables is “super-consistent” with
√
convergence rate T instead of T (Pesaran and Shin, 1998; Hassler and Wolters, 2006).
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 21/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
. estat ectest
| 10% | 5% | 1% | p-value
| I(0) I(1) | I(0) I(1) | I(0) I(1) | I(0) I(1)
---+------------------+------------------+------------------+-----------------
F | 4.032 4.831 | 4.958 5.843 | 7.070 8.119 | 0.000 0.000
t | -2.550 -2.899 | -2.861 -3.225 | -3.470 -3.854 | 0.000 0.000
do not reject H0 if
both F and t are closer to zero than critical values for I(0) variables
(if p-values > desired level for I(0) variables)
reject H0 if
both F and t are more extreme than critical values for I(1) variables
(if p-values < desired level for I(1) variables)
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 22/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
D.ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ADJ |
ln_consump |
L1. | -.341178 .0431316 -7.91 0.000 -.4270464 -.2553096
-------------+----------------------------------------------------------------
LR |
ln_inc | 1.14358 .0782318 14.62 0.000 .9878321 1.299327
qtr | -.0036516 .0016171 -2.26 0.027 -.006871 -.0004322
-------------+----------------------------------------------------------------
SR |
ln_consump |
LD. | -.4362663 .0851 -5.13 0.000 -.6056874 -.2668452
L2D. | -.1899566 .0825977 -2.30 0.024 -.354396 -.0255172
|
ln_inv |
D1. | .0842961 .0173889 4.85 0.000 .0496775 .1189146
LD. | .0517241 .0188448 2.74 0.008 .0142069 .0892412
L2D. | .0726232 .017972 4.04 0.000 .0368437 .1084027
L3D. | .0482872 .0173383 2.79 0.007 .0137693 .0828051
|
_cons | -.3188651 .1422961 -2.24 0.028 -.602155 -.0355753
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 23/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
. estat ectest
| 10% | 5% | 1% | p-value
| I(0) I(1) | I(0) I(1) | I(0) I(1) | I(0) I(1)
---+------------------+------------------+------------------+-----------------
F | 4.066 4.582 | 4.784 5.351 | 6.396 7.057 | 0.000 0.000
t | -3.107 -3.384 | -3.412 -3.704 | -4.014 -4.327 | 0.000 0.000
do not reject H0 if
both F and t are closer to zero than critical values for I(0) variables
(if p-values > desired level for I(0) variables)
reject H0 if
both F and t are more extreme than critical values for I(1) variables
(if p-values < desired level for I(1) variables)
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 24/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 25/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
Postestimation commands
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 26/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
Postestimation commands
6
estat dwatson is not valid for ARDL / EC models because the lagged dependent variable is not strictly
exogenous by construction.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 27/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 28/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
. estat hettest
chi2(1) = 0.26
Prob > chi2 = 0.6067
chi2(54) = 52.03
Prob > chi2 = 0.5508
---------------------------------------------------
Source | chi2 df p
---------------------+-----------------------------
Heteroskedasticity | 52.03 54 0.5508
Skewness | 12.24 9 0.2000
Kurtosis | 0.02 1 0.8967
---------------------+-----------------------------
Total | 64.29 64 0.4664
---------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 29/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
. sktest resid
. qnorm resid
. pnorm resid
.02 1.00
.01 0.75
0 0.50
−.01 0.25
−.02 0.00
−.02 −.01 0 .01 .02 0.00 0.25 0.50 0.75 1.00
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 30/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
−2
−4
1961 1966 1971 1976 1981
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 31/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
−1
−2
1961 1966 1971 1976 1981
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 32/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
Number of obs = 88
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 33/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
Number of obs = 88
Note: This is a test for a structural break in the speed-of-adjustment and long-run coefficients.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 34/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
Further topics
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 35/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
ARDL(4) regression
------------------------------------------------------------------------------
D.dln_inv | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ADJ |
dln_inv |
L1. | -.755277 .2295731 -3.29 0.001 -1.211971 -.2985831
-------------+----------------------------------------------------------------
LR |
_cons | .015006 .0060544 2.48 0.015 .0029618 .0270501
-------------+----------------------------------------------------------------
SR |
dln_inv |
LD. | -.4633003 .2005284 -2.31 0.023 -.8622152 -.0643855
L2D. | -.4938993 .1577325 -3.13 0.002 -.8076796 -.180119
L3D. | -.3133117 .1029967 -3.04 0.003 -.5182049 -.1084184
------------------------------------------------------------------------------
Note: The aim is to test whether dln inv, the first difference of ln inv, is nonstationary.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 36/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
. estat ectest
| 10% | 5% | 1% | p-value
| I(0) I(1) | I(0) I(1) | I(0) I(1) | I(0) I(1)
---+------------------+------------------+------------------+-----------------
F | 3.823 3.812 | 4.677 4.659 | 6.644 6.601 | 0.026 0.025
t | -2.565 -2.569 | -2.869 -2.874 | -3.463 -3.472 | 0.017 0.017
do not reject H0 if
both F and t are closer to zero than critical values for I(0) variables
(if p-values > desired level for I(0) variables)
reject H0 if
both F and t are more extreme than critical values for I(1) variables
(if p-values < desired level for I(1) variables)
Note: The null hypothesis is that dln inv follows a unit root process (without drift).
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 37/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
D.dln_inv | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
dln_inv |
L1. | -.755277 .2295731 -3.29 0.001 -1.211971 -.2985831
LD. | -.4633003 .2005284 -2.31 0.023 -.8622152 -.0643855
L2D. | -.4938993 .1577325 -3.13 0.002 -.8076796 -.180119
L3D. | -.3133117 .1029967 -3.04 0.003 -.5182049 -.1084184
|
_cons | .0113337 .0060208 1.88 0.063 -.0006437 .023311
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 38/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
1981q1: ...........
1981q2: ...........
1981q3: ...........
1981q4: ...........
1982q1: ...........
1982q2: ..........
1982q3: ..........
1982q4: ...........
7.75
7.7
7.65
7.6
7.55
1979 1980 1981 1982
Note: The forecast period (1981q1 – 1982q4) is excluded from the estimation period (1961q1 – 1980q4).
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 40/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
| Newey-West
ln_consump | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ln_consump |
L1. | .2225557 .0931767 2.39 0.019 .0370552 .4080562
L2. | .2463097 .1003579 2.45 0.016 .0465125 .4461068
L3. | .1899566 .1013927 1.87 0.065 -.0119008 .3918141
|
ln_inc | .3901642 .0400174 9.75 0.000 .3104956 .4698327
|
ln_inv |
D1. | .0842961 .0258047 3.27 0.002 .0329229 .1356693
LD. | .0517241 .0158053 3.27 0.002 .0202582 .08319
L2D. | .0726232 .0156803 4.63 0.000 .0414061 .1038404
L3D. | .0482872 .017342 2.78 0.007 .013762 .0828124
|
qtr | -.0012458 .000383 -3.25 0.002 -.0020083 -.0004833
_cons | -.3188651 .1104624 -2.89 0.005 -.5387789 -.0989513
------------------------------------------------------------------------------
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 41/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
------------------------------------------------------------------------------
ln_consump | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_nl_1 | 1.14358 .0691576 16.54 0.000 1.008033 1.279126
------------------------------------------------------------------------------
Note: This is the same long-run coefficient as earlier but with Newey-West standard errors.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 42/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
help ardl
help ardl postestimation
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 43/44
Introduction ARDL model EC representation Bounds testing Postestimation Further topics Summary
References
Cheung, Y.-W., and K. S. Lai (1995). Lag order and critical values of the augmented Dickey-Fuller test.
Journal of Business & Economic Statistics 13(3): 277–280.
Engle, R. F., and C. W. J. Granger (1987). Co-integration and error correction: representation, estimation,
and testing. Econometrica 55(2): 251–276.
Hassler, U., and J. Wolters (2006). Autoregressive distributed lag models and cointegration. Allgemeines
Statistisches Archiv 90(1): 59–74.
Kripfganz, S., and D. C. Schneider (2018). Response surface regressions for critical value bounds and
approximate p-values in equilibrium correction models. Manuscript, University of Exeter and Max Planck
Institute for Demographic Research, www.kripfganz.de.
Lütkepohl, H. (1993). Introduction to Multiple Time Series Analysis (2nd edition), Berlin, New York:
Springer.
Narayan, P. K (2005). The saving and investment nexus for China: evidence from cointegration tests.
Applied Economics 37(17): 1979–1990.
Pesaran, M. H., and Y. Shin (1998). An autoregressive distributed-lag modelling approach to cointegration
analysis. In Econometrics and Economic Theory in the 20th Century. The Ragnar Frisch Centennial
Symposium, ed. S. Strøm, chap. 11, 371–413. Cambridge: Cambridge University Press.
Pesaran, M. H., Y. Shin, and R. Smith (2001). Bounds testing approaches to the analysis of level
relationships. Journal of Applied Econometrics 16(3): 289–326.
S. Kripfganz and D. C. Schneider ardl: Estimating autoregressive distributed lag and equilibrium correction models 44/44