This website uses cookies.

By clicking the "Accept" button or continuing to browse our site, you agree to first-party and session-only cookies being stored on your device to enhance site navigation and analyze site performance and traffic. For more information on our use of cookies, please see our Privacy Policy.

  1. Home
  2. ASSA Annual Meeting
  3. 2024
  4. Program
  5. Time Series and Financial Econometrics
« Back to Results

Time Series and Financial Econometrics

Paper Session

Sunday, Jan. 7, 2024 1:00 PM - 3:00 PM (CST)

Grand Hyatt, Travis B
Hosted By: Econometric Society
  • Chair: Jean-Marie Dufour, McGill University

Local Projection Based Inference under General Conditions

Ke-Li Xu
,
Indiana University

Abstract

This paper provides the uniform asymptotic theory for local projection (LP) regression when the true lag order of the model is unknown, possibly infinity. The theory allows for various persistence levels of the data, growing response horizons, and general conditionally heteroskedastic shocks. Based on the theory, we make two contributions. First, we show that LPs are semiparametrically efficient under classical assumptions on data and horizons if the controlled lag order diverges. Thus the commonly perceived efficiency loss of running LPs is asymptotically negligible with many controls. Second, we propose LP-based inferences for (individual and cumulated) impulse responses with robustness properties not shared by other existing methods. Inference methods using two different standard errors are considered, and neither involves HAR-type correction. The uniform validity for the first method depends on a zero fourth moment condition on shocks, while the validity for the second holds more generally for martingale-difference heteroskedastic shocks.

Sieve Managed Portfolios 

Xiaohong Chen
,
Yale University
Francisco Penaranda
,
CUNY-Queens College
Demian Pouzo
,
University of California-Berkeley
Enrique Sentana
,
CEMFI

Abstract

Empirical finance researchers and professional portfolio managers have long considered strategies that exploit individual stock characteristics such as value and momentum, but recently they have shifted their attention to others. Our empirical goal is to assess if portfolios that exploit the profitability and investment characteristics really provide new opportunities for investors by testing whether they can be spanned by dynamic portfolios of traditional strategies. Given that the optimal weights of these dynamic portfolios depend in an unrestricted manner on predictors such as yield spreads, we develop a new econometric methodology called sieve managed portfolios that can handle non-parametric weights. We find that the two new strategies do not increase the conditional Sharpe ratio that can achieved from
traditional strategies, but they are relevant for investors that want to exploit the changing
investment opportunities that our predictors generate.

Linear Regression with Weak Exogeneity

Anna Mikusheva
,
Massachusetts Institute of Technology
Mikkel Sølvsten
,
Aarhus University

Abstract

This paper studies linear time series regressions with many regressors. Weak exogeneity is the most commonly used identifying assumption in time series. Weak exogeneity requires that the structural error has zero expectation conditional on the current and past value of the regressors, but it allows the errors to be correlated with future realizations of regressors. We show that weak exogeneity in a time series regression with many controls may produce very large biases and can even lead to inconsistency of the least squares (OLS) estimator. The bias arises in settings with many autocorrelated regressors because the normalized OLS design matrix remains asymptotically random and is correlated with the regression error, when only weak but not strict exogeneity holds. We propose an innovative approach to bias correction that yields a large class of estimators with improved properties relative to OLS. We analyze asymptotic bias and variance for this class of estimators, and suggest bias-aware confidence sets that account for any potential remaining bias in the improved estimators.

Intervention Analysis, Causality and Generalized Impulse Responses in VAR Models: Theory and Inference

Jean-Marie Dufour
,
McGill University
Endong Wang
,
McGill University

Abstract

In macroeconomics, a central focus is placed on unraveling the roles of specific variables in
the transmission of exogenous shocks to a target variable across varying time periods. One
influential study in this topic is Bernanke’s (1995) exploration of the credit channel’s role in
transmission of momentary policy shocks to real output. This paper introduces an innovative
index designed to provide a quantitative measure of a mediator’s impact as either an amplifier
or an attenuator within a dynamic system during the transmission of a specific shock over time.
The index offers researchers a clearer perspective on the underlying transmission mechanisms.
Our research is rooted in the Structural VAR model. Firstly, we present the concept of ‘impulse
response decomposition’, which illustrates that, for a given impulse response horizon and time
of decomposition, the impulse response is contributed to the movements of variables triggered
by the initial intervention. Secondly, we engage in a hypothetical scenario at the time of
evaluation where the mediator of interest exerts no causal influence on the target variable,
holding all other factors constant. The index is computed based on the ramifications of this
counterfactual analysis on the target variable. The causal relationship between the mediator
and the target variable, while keeping all other factors constant, is assessed through Granger
causality over multiple time horizons, as formalized by Dufour and Renault (1998). This pivotal
counterfactual analysis is akin to assuming that the target variable responds to all variables
except for the mediator of interest. Lastly, we apply our channel index to quantify the role
of the credit channel in transmitting monetary policy shocks, shedding light on the intricate
dynamics of macroeconomic responses to such shocks.
JEL Classifications
  • C0 - General
  • G1 - General Financial Markets