This paper proposes a new combined semiparametric estimator of the conditional variance that takes the product of a parametric estimator and a nonparametric estimator based on machine learning. A popular kernel-based machine learning algorithm, known as the kernel-regularized least squares...

In this paper, we compare the performance of two non-parametric methods of classification, Regression Trees (CART) and the newly Multivariate Adaptive Regression Splines (MARS) models, in forecasting bankruptcy. Models are implemented on a large universe of US banks over a complete market cycle...

The paper examines episodes of current account adjustment in individual economies. A central finding is that these episodes are very divergent and can be usefully classified, on the basis of cluster analysis, in three groups. A majority of cases is characterised by internal adjustment,...

The paper examines over seventy episodes of current account adjustment in industrial and major emerging market economies. It argues that these episodes were characterised by strongly divergent economic developments. To reduce this divergence, the paper classifies episodes with similar...

We develop a flexible nonparametric similarity-based approach to predict the state of the business cycle in different interest rate environments. Our approach provides methodological advantages over parametric logit and probit models and new empirical perspectives on the usefulness of the term...

We augment the existing literature using the Log-Periodic Power Law Singular (LPPLS) structures in the log-price dynamics to diagnose financial bubbles by providing three main innovations. First, we introduce the quantile regression to the LPPLS detection problem. This allows us to disentangle...

We study the relationship between conditional quantiles of returns and the long-, medium- and short-term volatility in a portfolio of financial assets. We argue that the combination of quantile panel regression and wavelet decomposition of the volatility time series provides us with new insights...

This paper considers estimation and inference for heterogeneous counterfactual effects with high‐dimensional data. We propose a novel robust score for debiased estimation of the unconditional quantile regression (Firpo, Fortin, and Lemieux (2009)) as a measure of heterogeneous counterfactual...

SEMIFAR models introduced in Beran (1999) provide a semiparametric modelling framework that enables the data analyst to separate deterministic and stochastic trends as well as short- and long-memory components in an observed time series. A correct distinction between these components, and in...