Research Topics

Publications on Asymmetric vector autoregression (AVAR)

There are 2 publications for Asymmetric vector autoregression (AVAR).
  • Interest Rate Determination in India

    Working Paper No. 744 | December 2012
    Empirical Evidence on Fiscal Deficit – Interest Rate Linkages and Financial Crowding Out

    Controlling for capital flows using the high-frequency macro data of a financially deregulated regime, this paper examines whether there is any evidence of the fiscal deficit determining the interest rate in the context of India. The period of analysis is FY 2006–07 (April) to FY 2011 (April). Contrary to the debates in policy circles, the paper finds that an increase in the fiscal deficit does not cause a rise in interest rates. Using the asymmetric vector autoregressive model, the paper establishes that the interest rate is affected by changes in the reserve currency, expected inflation, and volatility in capital flows, but not by the fiscal deficit. This result has significant policy implications for interest rate determination in India, especially since the central bank has cited the high fiscal deficit as the prime reason for leaving the rates unchanged in all of its recent policy announcements. The paper analyzes both long- and short-term interest rates to determine the occurrence of financial crowding out, and finds that the fiscal deficit does not appear to be causing either shorts and longs. However, a reverse causality is detected, from interest rates to deficits.

  • Infinite-variance, Alpha-stable Shocks in Monetary SVAR

    Working Paper No. 682 | August 2011
    Final Working Paper Version

    This paper adumbrates a theory of what might be going wrong in the monetary SVAR literature and provides supporting empirical evidence. The theory is that macroeconomists may be attempting to identify structural forms that do not exist, given the true distribution of the innovations in the reduced-form VAR. The paper shows that this problem occurs whenever (1) some innovation in the VAR has an infinite-variance distribution and (2) the matrix of coefficients on the contemporaneous terms in the VAR’s structural form is nonsingular. Since (2) is almost always required for SVAR analysis, it is germane to test hypothesis (1). Hence, in this paper, we fit α-stable distributions to VAR residuals and, using a parametric-bootstrap method, test the hypotheses that each of the error terms has finite variance.

Quick Search

Search in: