|
on Econometric Time Series |
| By: | Reinhard Ellwanger, Stephen Snudden (Wilfrid Laurier University) |
| Abstract: | Macroeconomic series are often aggregated from higher-frequency data. We show that this seemingly innocent feature has far-reaching consequences for the predictability of such series. First, the series are predictable by construction. Second, conventional tests of predictability are less informative about the data-generating process than frequently assumed. Third, a simple improvement to the conventional test leads to a sizeable correction, making it necessary to re-evaluate existing forecasting approaches. Fourth, forecasting models should be estimated with end-of-period observations even when the goal is to forecast the aggregated series. We highlight the relevance of these insights for forecasts of several macroeconomic variables. |
| Keywords: | Forecasting and Prediction Methods, Interest Rates, Exchange Rates, Asset Prices, Oil Prices, Commodity Prices |
| JEL: | C1 C53 E47 F37 G17 Q47 |
| Date: | 2021 |
| URL: | http://d.repec.org/n?u=RePEc:wlu:lcerpa:bm0127&r= |
| By: | Meenagh, David (Cardiff Business School); Minford, Patrick (Cardiff Business School); Wickens, Michael (Cardiff Business School) |
| Abstract: | We ask whether Bayesian estimation creates a potential estimation bias as compared with standard estimation techniques based on the data, such as maximum likelihood or indirect estimation. We investigate this with a Monte Carlo experiment in which the true version of a New Keynesian model may either have high wage/price rigidity or be close to pure flexibility; we treat each in turn as the true model and create Bayesian estimates of it under priors from the true model and its false alternative. The Bayesian estimation of macro models may thus give very misleading results by placing too much weight on prior information compared to observed data; a better method may be Indirect estimation where the bias is found to be low. |
| Keywords: | Bayesian; Maximum Likelihood; Indirect Inference; Estimation Bias |
| JEL: | C11 E12 |
| Date: | 2021–09 |
| URL: | http://d.repec.org/n?u=RePEc:cdf:wpaper:2021/22&r= |
| By: | Yifei Cai; Jamel Saadaoui |
| Abstract: | According to the Schumpeterian endogenous growth theory, the efficacy of R&D is lowered by the proliferation of products. To be consistent with empirical data, the ratio between innovative activity and product variety (also called R&D intensity) must be stationary. In this perspective, our contribution investigates whether the R&D intensity series are stationary when structural breaks are considered. Our sample of G7 countries is examined over the period spanning from 1870 to 2016. Our results indicate that traditional unit root tests (ADF, DF-GLS and KPSS) conclude that the R&D intensity series are non-stationary in contradiction with the Schumpeterian endogenous growth theory. The conclusions of these traditional unit root tests may be misleading, as they ignore the presence of structural breaks. Indeed, we use several types of Fourier Dickey-Fuller tests to consider the presence of structural breaks. In the Fourier Dickey-Fuller unit root tests using double frequency and fractional frequency, the R&D intensity is significantly stationary at least at the 5% level for Canada, France, Germany, Italy, Japan when a deterministic trend is included in the tests. Nevertheless, the R&D intensity is non-stationary for the US, even when we consider structural breaks. Indeed, the integration analyses aimed at discriminating between competing theories of endogenous growth should be careful of the presence of structural breaks. Especially when historical data are used, traditional unit root tests may lead to erroneous economic interpretations. These findings may help to understand the true nature of long-run economic growth and may help to formulate sound policy recommendations. |
| Keywords: | R&D intensity; Schumpeterian growth model; Double frequency; Fourier DickeyFuller unit root test. |
| JEL: | C12 C22 O30 O40 |
| Date: | 2021 |
| URL: | http://d.repec.org/n?u=RePEc:ulp:sbbeta:2021-34&r= |
| By: | Florens Odendahl; Barbara Rossi; Tatevik Sekhposyan |
| Abstract: | We propose a novel forecast evaluation methodology to assess models' absolute and relative forecasting performance when it is a state-dependent function of economic variables. In our framework, the forecasting performance, measured by a forecast error loss function, is modeled via a hard or smooth threshold model with unknown threshold values. Existing tests either assume a constant out-of-sample forecast performance or use non-parametric techniques robust to time-variation; consequently, they may lack power against state-dependent predictability. Our tests can be applied to relative forecast comparisons, forecast encompassing, forecast efficiency, and, more generally, moment-based tests of forecast evaluation. Monte Carlo results suggest that our proposed tests perform well in finite samples and have better power than existing tests in selecting the best forecast or assessing its efficiency in the presence of state dependence. Our tests uncover "pockets of predictability" in U.S. equity premia; although the term spread is not a useful predictor on average over the sample, it forecasts significantly better than the benchmark forecast when real GDP growth is low. In addition, we find that leading indicators, such as measures of vacancy postings and new orders for durable goods, improve the forecasts of U.S. industrial production when financial conditions are tight. |
| Keywords: | State dependence, forecast evaluation, predictive ability testing, moment-based tests; pockets of predictability |
| JEL: | C52 C53 E17 G17 |
| Date: | 2021–07 |
| URL: | http://d.repec.org/n?u=RePEc:upf:upfgen:1800&r= |
| By: | Kaan Gokcesu; Hakan Gokcesu |
| Abstract: | In this paper, we propose a nonparametric approach that can be used in envelope extraction, peak-burst detection and clustering in time series. Our problem formalization results in a naturally defined splitting/forking of the time series. With a possibly hierarchical implementation, it can be used for various applications in machine learning, signal processing and mathematical finance. From an incoming input signal, our iterative procedure sequentially creates two signals (one upper bounding and one lower bounding signal) by minimizing the cumulative $L_1$ drift. We show that a solution can be efficiently calculated by use of a Viterbi-like path tracking algorithm together with an optimal elimination rule. We consider many interesting settings, where our algorithm has near-linear time complexities. |
| Date: | 2021–09 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2109.02082&r= |
| By: | Hainaut, Donatien (Université catholique de Louvain, LIDAM/ISBA, Belgium) |
| Abstract: | This article establishes the moment generating function (mgf) of self-excited claim processes with memory functions that admit a Fourier's transform representation. In this case, the claim and intensity processes may be reformulated as an infinite dimensional Markov processes in the complex plane. Approaching these processes by discretization and next considering the limit allows us to find their moment generating function. We illustrate the article by fitting non-Markov self-excited processes to the time-series of cyber-attacks targeting medical and other services, in the US from 2014 to 2018. |
| Keywords: | self-excited process, shot noise process, Hawkes process |
| JEL: | C5 G22 |
| Date: | 2021–07–02 |
| URL: | http://d.repec.org/n?u=RePEc:aiz:louvad:2021028&r= |