Forecasting under model uncertainty: Non-homogeneous hidden Markov models with Pòlya-Gamma data augmentation

We consider finite state-space non-homogeneous hidden Markov models for forecasting univariate time series. Given a set of predictors, the time series are modeled via predictive regressions with state-dependent coefficients and time-varying transition probabilities that depend on the predictors via a logistic/multinomial function. In a hidden Markov setting, inference for logistic regression coefficients becomes complicated and in some cases impossible due to convergence issues. In this paper, we aim to address this problem utilizing the recently proposed Pólya-Gamma latent variable scheme. Also, we allow for model uncertainty regarding the predictors that affect the series both linearly — in the mean — and non-linearly — in the transition matrix. Predictor selection and inference on the model parameters are based on an automatic Markov chain Monte Carlo scheme with reversible jump steps. Hence the proposed methodology can be used as a black box for predicting time series. Using simulation experiments, we illustrate the performance of our algorithm in various setups, in terms of mixing properties, model selection and predictive ability. An empirical study on realized volatility data shows that our methodology gives improved forecasts compared to benchmark models.     

Does a lot help a lot? Forecasting stock returns with pooling strategies in a data‐rich environment

A variety of recent studies provide a skeptical view on the predictability of stock returns. Empirical evidence shows that most prediction models suffer from a loss of information, model uncertainty, and structural instability by relying on low‐dimensional information sets. In this study, we evaluate the predictive ability of various lately refined forecasting strategies, which handle these issues by incorporating information from many potential predictor variables simultaneously. We investigate whether forecasting strategies that (i) combine information and (ii) combine individual forecasts are useful to predict US stock returns, that is, the market excess return, size, value, and the momentum premium. Our results show that methods combining information have remarkable in‐sample predictive ability. However, the out‐of‐sample performance suffers from highly volatile forecast errors. Forecast combinations face a better bias–efficiency trade‐off, yielding a consistently superior forecast performance for the market excess return and the size premium even after the 1970s.     

Making the abstract concrete: The role of norms and values in experimental modeling

Experimental modeling is the construction of theoretical models hand in hand with experimental activity. As explained in Section 1, experimental modeling starts with claims about phenomena that use abstract concepts, concepts whose conditions of realization are not yet specified; and it ends with a concrete model of the phenomenon, a model that can be tested against data. This paper argues that this process from abstract concepts to concrete models involves judgments of relevance, which are irreducibly normative. In Section 2, we show, on the basis of several case studies, how these judgments contribute to the determination of the conditions of realization of the abstract concepts and, at the same time, of the quantities that characterize the phenomenon under study. Then, in Section 3, we compare this view on modeling with other approaches that also have acknowledged the role of relevance judgments in science. To conclude, in Section 4, we discuss the possibility of a plurality of relevance judgments and introduce a distinction between locally and generally relevant factors.     

Exploring Survey‐Based Inflation Forecasts

This paper first shows that survey‐based expectations (SBE) outperform standard time series models in US quarterly inflation out‐of‐sample prediction and that the term structure of survey‐based inflation forecasts has predictive power over the path of future inflation changes. It then proposes some empirical explanations for the forecasting success of survey‐based inflation expectations. We show that SBE pool a large amount of heterogeneous information on inflation expectations and react more flexibly and accurately to macro conditions both contemporaneously and dynamically. We illustrate the flexibility of SBE forecasts in the context of the 2008 financial crisis. Copyright © 2011 John Wiley & Sons, Ltd.     

What do numerical (climate) models really represent?

The translation of a mathematical model into a numerical one employs various modifications in order to make the model accessible for computation. Such modifications include discretizations, approximations, heuristic assumptions, and other methods. The paper investigates the divergent styles of mathematical and numerical models in the case of a specific piece of code in a current atmospheric model. Cognizance of these modifications means that the question of the role and function of scientific models has to be reworked. Neither are numerical models pure intermediaries between theory and data, nor are they autonomous tools of inquiry. Instead, theory and data are transformed into a new symbolic form of research due to the fact that computation has become an essential requirement for every scientific practice. Therefore the question is posed: What do numerical (climate) models really represent?     

Forecasting regional house price inflation: a comparison between dynamic factor models and vector autoregressive models

This paper uses the dynamic factor model framework, which accommodates a large cross‐section of macroeconomic time series, for forecasting regional house price inflation. In this study, we forecast house price inflation for five metropolitan areas of South Africa using principal components obtained from 282 quarterly macroeconomic time series in the period 1980:1 to 2006:4. The results, based on the root mean square errors of one to four quarters ahead out‐of‐sample forecasts over the period 2001:1 to 2006:4 indicate that, in the majority of the cases, the Dynamic Factor Model statistically outperforms the vector autoregressive models, using both the classical and the Bayesian treatments. We also consider spatial and non‐spatial specifications. Our results indicate that macroeconomic fundamentals in forecasting house price inflation are important. Copyright © 2010 John Wiley & Sons, Ltd.     

An ensemble of LSTM neural networks for high‐frequency stock market classification

We propose an ensemble of long–short‐term memory (LSTM) neural networks for intraday stock predictions, using a large variety of technical analysis indicators as network inputs. The proposed ensemble operates in an online way, weighting the individual models proportionally to their recent performance, which allows us to deal with possible nonstationarities in an innovative way. The performance of the models is measured by area under the curve of the receiver operating characteristic. We evaluate the predictive power of our model on several US large‐cap stocks and benchmark it against lasso and ridge logistic classifiers. The proposed model is found to perform better than the benchmark models or equally weighted ensembles.     

Long Memory of Financial Time Series and Hidden Markov Models with Time‐Varying Parameters

Hidden Markov models are often used to model daily returns and to infer the hidden state of financial markets. Previous studies have found that the estimated models change over time, but the implications of the time‐varying behavior have not been thoroughly examined. This paper presents an adaptive estimation approach that allows for the parameters of the estimated models to be time varying. It is shown that a two‐state Gaussian hidden Markov model with time‐varying parameters is able to reproduce the long memory of squared daily returns that was previously believed to be the most difficult fact to reproduce with a hidden Markov model. Capturing the time‐varying behavior of the parameters also leads to improved one‐step density forecasts. Finally, it is shown that the forecasting performance of the estimated models can be further improved using local smoothing to forecast the parameter variations. Copyright © 2016 John Wiley & Sons, Ltd.     

The impact of parameter and model uncertainty on market risk predictions from GARCH‐type models

We study the effect of parameter and model uncertainty on the left‐tail of predictive densities and in particular on VaR forecasts. To this end, we evaluate the predictive performance of several GARCH‐type models estimated via Bayesian and maximum likelihood techniques. In addition to individual models, several combination methods are considered, such as Bayesian model averaging and (censored) optimal pooling for linear, log or beta linear pools. Daily returns for a set of stock market indexes are predicted over about 13 years from the early 2000s. We find that Bayesian predictive densities improve the VaR backtest at the 1% risk level for single models and for linear and log pools. We also find that the robust VaR backtest exhibited by linear and log pools is better than the backtest of single models at the 5% risk level. Finally, the equally weighted linear pool of Bayesian predictives tends to be the best VaR forecaster in a set of 42 forecasting techniques.     

Forecasting VaR models under Different Volatility Processes and Distributions of Return Innovations

This paper provides clear‐cut evidence that the out‐of‐sample VaR (value‐at‐risk) forecasting performance of alternative parametric volatility models, like EGARCH (exponential general autoregressive conditional heteroskedasticity) or GARCH, and Markov regime‐switching models, can be considerably improved if they are combined with skewed distributions of asset return innovations. The performance of these models is found to be similar to that of the EVT (extreme value theory) approach. The performance of the latter approach can also be improved if asset return innovations are assumed to be skewed distributed. The performance of the Markov regime‐switching model is considerably improved if this model allows for EGARCH effects, for all different volatility regimes considered. Copyright © 2014 John Wiley & Sons, Ltd.