Valentyn Panchenko

A Note on the Hiemstra-Jones Test for Granger Non-causality

We address a consistency problem in the commonly used nonparametric test for Granger causality developed by Hiemstra and Jones (1994). We show that the relationship tested is not implied by the null hypothesis of Granger non-causality. Monte Carlo simulations using processes satisfying the null hypothesis show that, for a given nominal size, the actual rejection rate may tend to one as the sample size increases. Our results imply that evidence for nonlinear Granger causality reported in the applied empirical literature should be re-interpreted.

Nonparametric Tests for Serial Independence Based on Quadratic Forms

Tests for serial independence and goodness-of-fit based on divergence notions between probability distributions, such as the Kullback-Leibler divergence or Hellinger distance, have recently received much interest in time series analysis. The aim of this paper is to introduce tests for serial independence using kernel-based quadratic forms. This separates the problem of consistently estimating the divergence measure from that of consistently estimating the underlying joint densities, the existence of which is no longer required. Exact level tests are obtained by implementing a Monte Carlo procedure using permutations of the original observations. The bandwidth selection problem is addressed by introducing a multiple bandwidth procedure based on a range of different bandwidth values. After numerically establishing that the tests perform well compared to existing nonparametric tests, applications to estimated time series residuals are considered. The approach is illustrated with an application to financial returns data.

Asset price dynamics with heterogeneous beliefs and local network interactions

In this paper we investigate the effects of network topologies on asset price dynamics. We introduce network communications into a simple asset pricing model with heterogeneous beliefs. The agents may switch between several belief types according to their performance. The performance information is available to the agents only locally through their own experience and the experience of other agents directly connected to them. We model the communications with four commonly considered network topologies: a fully connected network, a regular lattice, a small world, and a random graph. The results show that the network topologies influence asset price dynamics in terms of the regions of stability, amplitudes of fluctuations and statistical properties.

Connecting the Dots: Econometric Methods for Uncovering Networks with an Application to the Australian Financial Institutions

This paper connects variance-covariance estimation methods, Gaussian graph- ical models, and the growing literature on economic and nancial networks. We construct the network using the concept of partial correlations which captures direct linear depen- dence between any two entities, conditional on dependence between all other entities. We relate the centrality measures of this network to shock propagation. The methodology is applied to construct the perceived network of the publicly traded Australian banks and their connections to the domestic nancial sector, real economy, and international mar- kets. We nd strong links between the big four Australian banks, the nancial services sector and the other sectors of the economy and determine which entities play a central role in transmitting and absorbing the shocks.

Comparing the Accuracy of Copula- Based Multivariate Density Forecasts in Selected Regions of Support

This paper develops a testing framework for comparing the predictive accuracy of copula-based multivariate density forecasts, focusing on a specific part of the joint distribution. The test is framed in the context of the Kullback-Leibler Information Criterion, but using (out-of-sample) conditional likelihood and censored likelihood in order to focus the evaluation on the region of interest. Monte Carlo simulations document that the resulting test statistics have satisfactory size and power properties in small samples. In an empirical application to daily exchange rate returns we find evidence that the dependence structure varies with the sign and magnitude of returns, such that different parametric copula models achieve superior forecasting performance in different regions of the support. Our analysis highlights the importance of allowing for lower and upper tail dependence for accurate forecasting of common extreme appreciation and depreciation of different currencies.

Rank-based entropy tests for serial independence

In nonparametric tests for serial independence the marginal distribution of the data acts as an infinite dimensional nuisance parameter. The decomposition of joint distributions in terms of a copula density and marginal densities shows that in general empirical marginals carry no information on dependence. It follows that the order of ranks is sufficient for inference, which motivates transforming the data to a pre-specified marginal distribution prior to testing. As a test statistic we use an estimator of the marginal redundancy. We numerically study the finite sample properties of the tests obtained when the data are transformed to uniform as well as normal marginals. For comparison purposes we also derive a rank-based test against local ARCH alternatives. The performance of the new tests is compared with a modified version of the BDS test and with the Ljung-Box test.

Heterogeneous beliefs under different market architectures

The paper analyzes the dynamics in a model with heterogeneous agents trading in simple markets under different trading protocols. Starting with the analytically tractable model of [4], we build a simulation platform with the aim to investigate the impact of the trading rules on the agents’ ecology and aggregate time series properties. The key behavioral feature of the model is the presence of a finite set of simple beliefs which agents choose each time step according to a fitness measure. The price is determined endogenously and our focus is on the role of the structural assumption about the market architecture. Analyzing dynamics under such different trading protocols as the Walrasian auction, the batch auction and the ‘order-book’ mechanism, we find that the resulting time series are similar to those originating from the noisy version of the model [4]. We distinguish the randomness caused by a finite number of agents and the randomness induced by an order-based mechanisms and analyze their impact on the model dynamics.

A model of network formation for the overnight interbank market

We introduce an endogenous network model of the interbank overnight lending market. Banks are motivated to meet the minimum reserve requirements set by the Central Bank, but their reserves are subject to random shocks. To adjust their expected end-of-the-day reserves, banks enter the interbank market, where borrowers decrease their expected cost of borrowing with the Central Bank, and lenders decrease their deposits with the Central bank in an attempt to gain a higher interest rate from the interbank market, but face a counter-party default risk. In this setting, we show that a financial network arises endogenously, exhibiting a unique giant component which is at the same time connected but bipartite in lenders and borrowers. The model reproduces features of trading decisions observed empirically in the Italian e-MID market for overnight interbank deposits.

Now You See It, Now You Don’t: How to Make the Allais Paradox Appear, Disappear, or Reverse

The Allais Paradox, or Common Consequence Effect to be precise, is one of the most wellknown behavioral regularities in individual decision making under risk. A common perception in the literature, which motivated the development of numerous generalized non‐expected utility theories, is that the Allais Paradox is a robust empirical finding. We argue that such a perception does not accurately reflect the experimental evidence on the Allais Paradox and show how specific choices of parameters can make it appear, disappear, or reverse. For example, our results suggest that the Allais Paradox is likely to disappear when lotteries involve relatively small outcomes under real financial incentives and probability distributions are described as compound lotteries or in a frequency format (rather than as reduced‐form simple lotteries). We also find that the Allais Paradox is likely to get reversed when lotteries are designed with an even division of the probability mass between the lowest and the highest outcomes.