The Academy of Economic Studies Doctoral School of Finance and Banking MSc Student: DRĂGOI IONUŢ Supervisor: Professor MOISĂ ALTĂR Monetary policy: analysis of a SVAR model for Romania
Jan 20, 2016
The Academy of Economic StudiesDoctoral School of Finance and Banking
MSc Student: DRĂGOI IONUŢ
Supervisor: Professor MOISĂ ALTĂR
Monetary policy: analysis of a SVAR model for Romania
CONTENTS Literature review
The Data
The SVAR approach
Impulse responses and variance decomposition
Conclusions
References
LITERATURE REVIEW Vector autoregressive models (VARs) were popularised in
econometrics by Sims (1980) as a natural generalisation of univariate autoregressive models
The main purpose of structural VAR (SVAR) estimation is to obtain non-recursive orthogonalization of the error terms for impulse response analysis. This alternative to the recursive Cholesky orthogonalization requires the imposition of enough restrictions to identify the orthogonal (structural) components of the error terms
Andrea Brischetto and Graham Voss (1999) use a structural vector autoregression model to analyse the monetary policy in australia
Kim and Roubini (1999), hereafter KR use a common structural model to identify the effects of monetary policy for the G7 economies
LITERATURE REVIEW For the considered countries, they find no evidence of the puzzles
that have been identified in the SVAR literature: the price, exchange rate, liquidity and forward discount bias puzzles.
The OECD used structural VAR models (SVAR) based on short-run restrictions as well as a block exogeneity assumption to examine whether some countries differ significantly in their responses to shocks
Similarly, Cushman and Zha (1997), and Dungey and Pagan (2000) used structural VAR models based on short-run restrictions as well as a block exogeneity assumption, following the methodology described in the seminal papers of Bernanke (1986), Blanchard and Watson (1986) and Sims (1986).
The Dataquarterly series 1999:01-2008:01 from Eurostat databases and Insse
Net export (net_exp): the net export realized by Romania with EU
The average of the real GDP achieved in European Union (eur_gdp)
Interest rate (irt): monetary policy rate
Monetary aggregate M2 (r_m2): monetary aggregate M2 deflated with the IPC
Real exchange rate (r_ert): the real effective exchange rate for ron/eur
Real GDP (r_gdp): real GDP of Romania
Inflation (inf): calculated as log(hcpi)(1) – log(hcpi), where hcpi represent the harmonised annual average consumer price index
The external sector is present through the variables net_exp and eur_gdp.
The internal sector is present through the variables irt, r_m2, r_ert, r_gdp and inf.
Romania is a small open economy. It’s degree of financial and commercial openness exceeded
70% in the last 8 years.
Main trading partner is the European Union (over 70% of the total for exports, and more than 60% of the total imports).
Trading currency: more than 60% settlement of exports and imports in euro, and approx. 30%in US dollar.
The inclusion of net export has been found to help resolve the ‘price puzzle’ in VARs, that is, the finding that the price level tends to increase in response to a contractionary monetary policy shock.
Inflation is included, following Dungey and Pagan (2000), rather than the price level as in Brischetto and Voss (1999).
There are no nominal level variables in the model and so the rate of change of prices seems to be a more logical variable to interact with real variables and an interest rate. In particular, for over half of the sample the objective of monetary policy has been an inflation target.
THE SVAR APROACH
The SVAR methodology is used because it can account for endogenous relationships, and can summarise the empirical relationships without placing too many restrictions on the data.
Structural shocks in a SVAR can be identified by placing some restrictions on contemporaneous relationships.
The restrictions placed on the contemporaneous relationships among the variables are characterised by equation (1) (this is the form for AB models proposed by Amisano and Giannini in 1997):
1 0 0 0 net_exp
1 0 0 0 0 eur_gdp
0 1 0 0 0 0 irt
1 0 0 0 r_m2_sa
1 0 0 r_ert
1 0 r_gdp_sa
1 inf
t
NA NA NA
NA NA
NA
B NA NA NA
NA NA NA NA
NA NA NA NA NA
NA NA NA NA NA NA
(1)
Unit roots tests Unit root tests suggest that most of the variables included in
the model are non-stationary, I(1), processes. This raises the issue of the appropriate estimation methodology.
I followed the existing literature which typically estimates VARs in levels even when the variables are I(1). Indeed, of the VAR studies referenced in this paper, only Haug et al (2003) use a vector error-correction model.
The preference for VARs in levels can be explained, at least in part, by a reluctance to impose possibly incorrect restrictions on the model. Even with I(1) variables, the residuals will be stationary because of the inclusion of lagged levels of the variables in the VAR. Nevertheless, the possibility of spurious relationships between the I(1) variables remains. Ensuring this is not the case is perhaps best achieved by confirming that the relationships summarised by the SVAR are plausible on economic grounds.
The main purpose of structural VAR (SVAR) estimation is to obtain non-recursive orthogonalization of the error terms for impulse response analysis.
This alternative to the recursive Cholesky orthogonalization requires the user to impose enough restrictions to identify the orthogonal (structural) components of the error terms.
The transmission of international shocks to the domestic economy can be very rapid. For example, an increase of the net export means an immediate increase of the value of Romanian exports, and hence domestic income.
Therefore, apart from two exceptions, it is assumed that all foreign variables affect all domestic variables contemporaneously.
The first exception prevents an immediate effect of eur_gdp on monetary policy (that is, the interest rate). This assumption reflects the informational lags faced by policy-makers and is also employed in an open-economy SVAR by Kim and Roubini (2000).
The second exception prevents an immediate effect of eur_gdp on inflation, since the domestic inflationary consequences of world economic activity would normally be thought to be transmitted indirectly through domestic activity.
The domestic variables are deemed not to affect the international variables, reflecting the relatively small size of Romania’s economy.
Romanian real GDP is assumed to be affected contemporaneously by inflation and the monetary aggregate M2. Output might respond contemporaneously to inflation because nominal incomes, and so spending, may be fixed in the short term. Alternatively, this assumption can be motivated by the Lucas-Phelps imperfect information model, in which producers face a signal extraction problem. Contemporaneously, producers only observe their own price, and so are unsure whether an increase in their price reflects inflationary pressures or an increase in demand.
As a result, they increase production, even if the price increase is purely inflationary. This increase in production could occur quite quickly.
The number of analyzed lags of the VAR model was chosed on the basis of information criteria (LR, Schwarz and Hannan-Quinn).
Impulse responses and variance decomposition
A shock to the i-th variable not only directly affects the i-th variable but is also transmitted to all of the other endogenous variables through the dynamic (lag) structure of the VAR.
An impulse response function traces the effect of a one-time shock to one of the innovations on current and future values of the endogenous variables. If the innovations are contemporaneously uncorrelated, interpretation of the impulse response is straightforward. The i-th innovation is simply a shock to the i-th endogenous variable
The obtained the impulse response functions are:
While impulse response functions trace the effects of a shock to one endogenous variable on to the other variables in the VAR, variance decomposition separates the variation in an endogenous variable into the component shocks to the VAR. Thus, the variance decomposition provides information about the relative importance of each random innovation in affecting the variables in the VAR.
As with the impulse responses, the variance decomposition based on the Cholesky factor can change dramatically if you alter the ordering of the variables in the VAR.
Conclusions The monetary shocks are isolated by estimating a reaction
function for the euro area. A more appropriate method to identify the policy shocks is to use the information set available at the moment the decision is made, i.e. survey data.
The number of observations used for the estimation may be inappropriate for the analyses of monetary transmission, knowing that the monetary decisions affect the economy only with lags.
In future work, I intend: to use alternative methods for identification of monetary
policy shocks (using the data-determined approach and the Blanchard and Quah decomposition).
to analyze the transmission of the identified monetary policy shocks in other countries except Romania, namely the new EU member countries.
References Berkelmans, Leon (2005), “Credit and Monetary Policy: An Australian
SVAR”, Reserve Bank of Australia, Research Discussion Paper
Brischetto, Andrea and Voss, Graham (1999), “A Structural Vector Autoregression Model of Monetary Policy in Australia”, Reserve Bank of Australia, Discussion Paper No 1999-11
Céspedes, Brisne J. V., Lima, Elcyon C. R. and Maka, Alexis (2005), „Monetary Policy, Inflation and the Level of Economic Activity in Brazil After the Real Plan: Stylized Facts from SVAR Models”, Discusion Paper 1101
Christiano, Lawerence J., Martin Eichenbaumand and R. J. Vigfusson (2006), “Assessing Structural VARs”, Board of Governors of the Federal Reserve System, International Finance Discussion Papers number 866
Claeys, Peter (2004) “Monetary and Budgetary Policy Interaction: An SVAR Analysis of Stabilization Policies in Monetary Union”, European University Institute, Working Paper ECQ No. 22
Dungey, Mardi and Pagan, Adrian (2000), “A Structural VAR Model of the Australian Economy”, The Economic Record, 76, 321-342
Fernández, Francisco de Castro and Hernández de Cos, Pablo (2006), „The Economic Effects of Exogenous Fiscal Shocks in Spain: a SVAR Approach”,
European Central Bank, Working Paper No. 647
Gottschalk, Jan (2001), “An Introduction into the SVAR Methodology: Identification, Interpretation and Limitations of SVAR models”, Kiel Institute of World Economics, Working Paper No. 1072
Guay, Alan and Pelgrin, Florian ”SVAR models and the short-run resilience effect”
Hamilton JD (1994), “Time series analysis”, Princeton University Press, Princeton.
Hsiao, Cheng and Wang, Siyan (2005), “Modified two-stage least-squares estimators for the estimation of a structural vector autoregressive integrated process”, Journal of Econometrics, 135, 427–463
Kehoe, Patrick J. (2006), „How to Advance Theory with Structural VARs: Use the Sims-Cogley-Nason Approach”, Federal Reserve Bank of Minneapolis, Research Department Staff Report 379
Leeper, Eric M., Sims, Christopher A. and Zha Tao (1996), “What Does Monetary Policy Do?”, Brookings Papers on Economic Activity, 2, pp. 1–78
Pagan, Adrian and Pesaran, Hashem (2007), “On Econometric Analysis of Structural Systems with Permanent and Transitory Shocks and Exogenous Variables”, NCER Working Paper 7
Sims, Chris (2002), “Structural VAR’s”, Time Series Econometrics, Econ. 513
Sousa, Joao Miguel and Zaghini, Andrea (2006), „Global Monetary Policy Shocks in the G5: A SVAR Approach”, CFS Working Paper No. 30
Waggoner, Daniel F. and Zha, Tao (2000), „A Gibbs Simulator for Restricted VAR Models”, Federal Reserve Bank of Atlanta, Working Paper 2000-3