Chapter 17 - Quantile Prediction

https://doi.org/10.1016/B978-0-444-62731-5.00017-8Get rights and content

Abstract

This chapter is concerned with the problem of quantile prediction (or forecasting). There are numerous applications in economics and finance where quantiles are of interest. We primarily focus on methods that are relevant for dynamic time series data. The chapter is organized around two key questions: first, how to measure and forecast the conditional quantiles of some series of interest given the information currently available and second, how to assess the accuracy of alternative conditional quantile predictors.

Introduction

In a general prediction or forecasting problem, the objective of the exercise is to “find an approximation of an unobserved variable that is a function of the observations” (Gourieroux and Monfort, 1995). In this chapter, the object of interest is the conditional α-quantile q of a scalar variable Y, PrYqI=α, where the probability 0<α<1 is given and I denotes an information set generated by some covariates X and/or lags of Y.1

The motivation for studying quantiles is twofold. In some situations, predicting a particular quantile is required by, say, an outside regulator. Which particular quantile is to be predicted depends on the context. In the banking sector, for example, the 1% or 5% quantile describing the left tail of the profit and loss account’s distribution (the so-called Value-at-Risk) is of interest to risk managers (as per the recommendations of the Basel Committee on Banking Supervision, 1996, Basel Committee on Banking Supervision, 2011). Systemic real risk (defined as the 5% quantile of quarterly growth in real GDP) and systemic financial risk (defined as the 5% quantile of a system-wide financial risk indicator) are of concern to policymakers (see, e.g., De Nicolò and Lucchetta, 2010). Lower and upper quantiles may be of interest in the studies of unemployment duration (see, e.g., Koenker and Xiao, 2002) or wage inequalities (see, e.g., Machado and Mata, 2005). More often, however, one wishes to obtain a collection of conditional quantiles that can characterize the entire conditional distribution.2 For instance, predicting several conditional quantiles of future inflation gives some idea on the entire distribution of the latter, which can be vital in assessing the risk to inflation stability due to macroeconomic shocks (see, e.g., Manzana and Zeromb, 2010).

In many other cases, however, quantiles are not given as primitive. Here, the objective is to provide an optimal point forecast of Y and optimality can be closely tied to the decision maker’s loss function. To elaborate more, consider a forecaster (e.g., policy maker, firm, government, Central Bank, or international organization) whose loss function L(y,f) depends on the realization y of the target variable Y (e.g., inflation rate, GDP growth, budget deficit) and on its forecast f. For example, the reputation (or reward) of professional forecasters is likely to depend on the accuracy with which they forecast the variable of interest. The optimal point forecast of Y is the value of f that given the forecaster’s information I minimizes the expected loss E[L(Y,f)I] (see, e.g., Elliott and Timmermann, 2008).

In realistic applications, it is natural to assume that the loss L is a smooth function that is everywhere positive except when f=y in which case L(y,y)=0. This guarantees that the loss is minimum when the forecaster has perfect foresight. For imperfect forecasts, fy, and the resulting loss is positive L(y,f)>0. The embarrassment costs to the forecaster resulting from underpredicting the target (i.e., f<y) as compared to overpredicting the target (i.e., f>y) by the same magnitude are likely to differ. This can be captured by letting the forecaster’s loss be an asymmetric function for which it is possible that L(y,f)L(f,y). So let L(y,f) be parameterized as:L(y,f)=ραG(y)-G(f),where ρα denotes the so-called “tick” or “check” function defined for any scalar e asρα(e)α-1I(e0)e,and where 0<α<1,1I denotes the usual indicator function, and G is any strictly increasing real function.3 The parameter α describes the degree of asymmetry in the forecaster’s loss function: values less than one half indicate that overpredicting Y induces greater loss to the forecaster than underpredicting Y by the same magnitude. In the symmetric case, α equals one half and the forecaster’s embarrassment costs due to over- and underpredictions are the same.

If the forecaster’s loss is of the form given in Eq. (1), then the optimal forecast of Y is its conditional α quantile qKomunjer, 2005, Komunjer and Vuong, 2010b, Gneiting, 2011. Interestingly, the real function G, which enters the forecaster’s loss need not be known. This means that quantiles are optimal forecasts for a large class of decision makers obtained by letting G vary in the set of monotone increasing functions. In the simple case where G is identity, one obtains L(y,f)=ρα(y-f), which is a well-known loss function in the literature on quantile estimation (see, e.g., the seminal paper by Koenker and Bassett (1978)).

Not only do the loss functions in (1) yield quantiles as optimal predictors of Y, but they are the only ones to do so. In other words, whenever the forecast f corresponds to the conditional α quantile of Y, the forecaster’s loss L(y,f) is necessarily of the form in Eq. (1). This result establishes a strong link between the quantiles as optimal predictors of Y and the underlying forecast loss functions for a given probability level α. In certain situations, however, α may be unknown and the question is whether it is possible to uncover it from the properties of the optimal forecast of Y. Elliott et al. (2005) show that the answer is yes provided one focuses on the so-called “lin-lin” losses in (1) obtained when G is identity.

There is a variety of applications in economics and finance where quantile prediction has been of interest. In finance, for example, the question of Value-at-Risk (VaR) measurement and prediction has been the leading motivation for quantile prediction in the last 20 years.4 An excellent survey of such applications can be found in Manganelli and Engle, 2004, Kuester et al., 2007. Two books by Christoffersen, 2003, McNeil et al., 2005 give overviews of quantile prediction for risk management in general.

Quantile prediction has also been used in the construction of interval forecasts and the closely related density forecasts. An early example is Granger et al. (1989), who construct interval forecasts based on estimated time-series models for ARCH processes using quantile regression. Numerous applications have been proposed since; a survey can be found in Chatfield (1993). Among more recent work, Hansen (2006) proposes a two-step quantile estimation method that focuses on incorporating parameter estimation uncertainty in interval forecasts. Examples of quantile use in density forecasting can be found in the survey by Tay and Wallis (2000). Applications are in a variety of fields, ranging from the construction of the so-called “fan charts”5 in macroeconomics (see, e.g., Manzana and Zeromb, 2010), predicting densities of financial return series (see, e.g., Cenesizoglu and Timmermann, 2008, Kim et al., 2010), to the paired comparison model of sports ratings (see, e.g., Koenker and Bassett, 2010).

Interestingly, conditional quantile forecasts have also been used to generate conditional volatility predictions that are of great importance in many area of finance. The quantile approach to volatility forecasting exploits an interesting result: that, for a variety of probability distributions, there is a surprising constancy of the ratio of the standard deviation to the interval between symmetric tail quantiles. This means that the conditional volatility can be approximated by a simple time-invariant function of the interval between symmetric conditional quantiles, even though the conditional volatility and distribution of financial returns may vary over time. Taylor (2005) uses this approach to construct volatility forecasts from quantile forecasts produced by a variety of VaR methods.

Finally, in the context of forecast evaluation, Patton and Timmermann (2007) proposed using quantiles as a way to test for forecast efficiency under more general loss functions than quadratic loss.

Depending on the type of data that they use, the above applications can be classified into two broad categories: cross-sectional and dynamic. An example of a cross-sectional application would be the one in which quantiles of the distribution of wages across a population of individuals are predicted given a variety of individuals’ socioeconomic characteristics, such as their age, education, or experience. An example of a dynamic application would be the one in which one tries to predict the quantiles of various financial asset or portfolio returns given the information set generated by lagged returns. To focus the scope of this chapter, we shall primarily turn our attention to the quantile prediction methods that use dynamic (time-series) data. In particular, this means that we shall mostly omit from this review the existing work on conditional quantiles that only applies to independent and identically distributed (iid) data. That work is more geared towards cross-sectional applications, which for the most part shall remain outside of the scope of the chapter. To emphasize the dynamic nature of the problem, we shall hereafter denote the conditional quantile of interest as qt where PrYtqtIt-1=α where It-1 is the information set generated by lagged observations of Yt as well as those of the covariates Xt available up to time t-1.

In this chapter, we shall try to address two key issues. Our first question of interest is that of prediction (forecasting): how to predict qt+1 given the information available up to time t? This question is closely related to the question of measuring qt even when the time t observations have become available. As in many forecasting situations, the object of interest qt itself is not observable. Thus, we cannot directly compute the prediction (or forecasting) errors et+1=qt+1-qˆt+1t, which complicates the prediction problem.

Our second question of interest is that of forecast evaluation: how to assess the accuracy of the predictor qˆt+1t of qt+1? As with the prediction problem, this question is closely related to the question of evaluating the accuracy of the measurement qˆt of qt. Understanding the underpinnings of forecast evaluation is particularly important if one is interested in comparing alternative quantile predictors.

The chapter is organized as follows: in Section 2 we review the three families of prediction approaches based on fully parametric, semi-parametric, and non-parametric methods. Section 3 discusses the conditional quantile forecast evaluation techniques. In Section 4, some of the issues specific to quantiles, such as near-extreme quantiles and multivariate quantiles, are considered. Section 5 concludes and discusses possible venues for future research. Throughout, we shall use the terms “predictor” (resp. “prediction”) and “forecast” (resp. “forecasting”) interchangeably.

Section snippets

Prediction

Depending on the strength of the model assumptions that they employ, existing quantile prediction methods can be categorized into three broad categories: fully parametric, semi-parametric, and non-parametric approaches. Manganelli and Engle, 2004, Kuester et al., 2007 offer similar classifications in their respective surveys on VaR prediction. In this section, we first set up the quantile forecasting problem, then offer a review of the existing prediction approaches.

Evaluation

Given the range of approaches available for producing conditional quantile predictions, it is necessary to have adequate tools for their evaluation. There are several dimensions according to which it is possible to classify the existing evaluation techniques. For example, one could separately consider evaluation criteria based on in-sample performance of conditional quantile predictions versus out-of-sample. Another classification is into absolute versus relative evaluation approaches. Absolute

Specific Issues

We now address some of the issues specific to the quantiles, such as quantiles whose probabilities are far in the tails (α close to zero or one), the problem of quantile crossings, which can occur if several quantiles of the same variable are measured or forecast at the same time, as well as the issue of multivariate quantiles.

Conclusion and Directions for Future Research

The goal of this chapter was to review the existing methods for quantile prediction and predictive ability testing. Existing prediction approaches were classified according to the strength of the model assumptions they rely on. Thus, we separately considered fully parametric, semi-parametric, and non-parametric methods. Existing forecast evaluation tests were grouped into two categories: absolute and relative. Relative merits of various forecasting models and evaluation methods were reviewed in

Acknowledgments

The author would like to thank the Editors, Allan Timmermann and Graham Elliott, as well as two anonymous referees for providing excellent suggestions and comments. She would also like to thank the participants of the 2011 St. Louis Fed Handbook of Forecasting Conference for their valuable feedback. Financial support from the National Science Foundation SES-0962473 is gratefully acknowledged.

References (127)

  • J. Geweke et al.

    Smoothly mixing regressions

    Journal of Econometrics

    (2007)
  • P. Giot et al.

    Modelling daily value-at-risk using realized volatility and arch type models

    Journal of Empirical Finance

    (2004)
  • T. Gneiting

    Quantiles as optimal point forecasts

    International Journal of Forecasting

    (2011)
  • C. Gourieroux et al.

    Dynamic quantile models

    Journal of Econometrics

    (2008)
  • C. Granger et al.

    Interval forecasting: an analysis based upon ARCH-quantile estimators

    Journal of Econometrics

    (1989)
  • B.E. Hansen

    Interval forecasts and parameter uncertainty

    Journal of Econometrics

    (2006)
  • R. Koenker et al.

    An interior point algorithm for nonlinear quantile regression

    Journal of Econometrics

    (1996)
  • I. Komunjer

    Quasi-maximum likelihood estimation for conditional quantiles

    Journal of Econometrics

    (2005)
  • I. Komunjer et al.

    Efficient estimation in dynamic conditional quantile models

    Journal of Econometrics

    (2010)
  • M.W. McCracken

    Robust Out-of-Sample Inference

    Journal of Econometrics

    (2000)
  • K. Abberger

    Quantile smoothing in financial time series

    Statistical Papers

    (1997)
  • T.G. Andersen et al.

    Modeling and forecasting realized volatility

    Econometrica

    (2003)
  • D.W.K. Andrews

    Asymptotics for semiparametric econometric models via stochastic equicontinuity

    Econometrica

    (1994)
  • J. Angrist et al.

    Quantile regression under misspecification, with an application to the US Wage structure

    Econometrica

    (2006)
  • Y. Bao et al.

    Evaluating predictive performance of value-at-risk models in emerging markets: a reality check

    Journal of Forecasting

    (2006)
  • Y. Bao et al.

    Comparing density forecast models

    Journal of Forecasting

    (2007)
  • Basel Committee on Banking Supervision 1996. Amendment to the Capital Accord to incorporate market risks, Bank for...
  • Basel Committee on Banking Supervision 2011. Revisions to the Basel II market risk framework, Bank for International...
  • J. Berkowitz et al.

    Evaluating value-at-risk models with desk-level data

    Management Science

    (2011)
  • H.J. Bierens

    A consistent conditional moment test of functional form

    Econometrica

    (1990)
  • H.J. Bierens et al.

    Integrated conditional moment testing of quantile regression models

    Empirical Economics

    (2001)
  • H.J. Bierens et al.

    Asymptotic theory of integrated conditional moment tests

    Econometrica

    (1997)
  • F. Black et al.

    The valuation of options and corporate liabilities

    Journal of Political Economy

    (1972)
  • T. Bollerslev et al.

    ARCH models

    (1994)
  • E. Bouyé et al.

    Copula quantile regressions and tail area dynamic dependence in forex markets

    The European Journal of Finance

    (2009)
  • Britton, E., Fisher, P., Whitley, J., 1998. Bank of England Quarterly Bulletin: February...
  • C. Brooks et al.

    Model choice and value-at-risk performance

    Financial Analysts Journal

    (2002)
  • Buchinsky, M., 1992. Methodological Issues in Quantile Regression. Working...
  • M. Buchinsky

    Changes in the US Wage structure 1963–1987: application of quantile regression

    Econometrica

    (1994)
  • M. Buchinsky et al.

    An alternative estimator for the censored quantile regression model

    Econometrica

    (1998)
  • Z. Cai

    Regression quantiles for time series

    Econometric Theory

    (2002)
  • Cenesizoglu, T., Timmermann, A., 2008. Is the Distribution of Stock Returns Predictable?. Working paper, HEC...
  • C. Chatfield

    Calculating interval forecasts

    Journal of Business and Economic Statistics

    (1993)
  • P. Chaudhuri

    On a geometric notion of quantiles for multivariate data

    Journal of the American Statistical Association

    (1996)
  • X. Chen et al.

    Copula-based nonlinear quantile autoregression

    Econometrics Journal

    (2009)
  • Chernozhukov, V., 2001. Conditional extremes and near-extremes. Working...
  • V. Chernozhukov

    Extremal quantile regression

    The Annals of Statistics

    (2005)
  • Chernozhukov, V., Du, S., 2006. Extremal Quantiles and Value-at-Risk, MIT Department of Economics Working Paper No....
  • V. Chernozhukov et al.

    Three-step censored quantile regression and extramarital affairs

    Journal of the American Statistical Association

    (2002)
  • V. Chernozhukov et al.

    Conditional value-at-risk: aspects of modeling and estimation

    Empirical Economics

    (2001)
  • Cited by (38)

    • Sequential forecasting of downside extreme risk during overnight and daytime: Evidence from the Chinese Stock Market<sup>☆</sup>

      2020, Pacific Basin Finance Journal
      Citation Excerpt :

      The extreme downside risk forecasting has been widely discussed in the literature. The main focus is on daily based close-to-close returns (see Andersen et al., 2006; Komunjer, 2013; McNeil et al., 2015), which views the trading and non-trading periods as a whole and ignore their differences in daily-frequency risk monitor. However, it sometimes needs to measure and forecast the downside extreme risk during the trading and non-trading periods separately, especially for investors who have to take an overnight position, or only want to pursue daytime trading.

    • Dynamic semiparametric models for expected shortfall (and Value-at-Risk)

      2019, Journal of Econometrics
      Citation Excerpt :

      There is, however, a paucity of empirical models for expected shortfall. The large literature on volatility models (see Andersen et al. (2006) for a review) and VaR models (see Komunjer (2013) and [33]), have provided many useful models for these measures of risk. However, while ES has long been known to be a “coherent” measure of risk (Artzner et al., 1999), in contrast with VaR, the literature contains relatively few models for ES; some exceptions are discussed below.

    • Quantile smoothing in supply chain and logistics forecasting

      2019, International Journal of Production Economics
      Citation Excerpt :

      This approach is considered within the so-called decision-theoretic framework, i.e., as a method of delivering optimal forecasts for a given forecast cost (loss) function, assumed here to be the asymmetric doubly linear (LINLIN) function of the forecast error (for similar considerations in the SCM or logistics contexts, see, for example, Pearson, 2006; Chopra and Meindl, 2007, Chapter XII, Ferbar et al., 2009; Tratar, 2010, 2015; Alwan et al., 2016; and Wang and Petropoulos, 2016). As is well known, the LINLIN loss leads to the solution of the forecasting task in the form of a quantile forecast (see Granger, 1969; Christoffersen and Diebold, 1997; Gneiting, 2011a, 2011b; Komunjer, 2013). In our paper, following the idea of a joint optimization of demand forecasting and stock control parameters as introduced by Tratar (2010), (2015), we suggest and examine various ways of computing quantile predictions with a generalized theta model or, to be more precise, with various modifications of the simple exponential smoothing (SES) with drift model (abbreviated as SES-d).

    View all citing articles on Scopus
    View full text