@techreport{66449, abstract = {{This paper evaluates the forecasting performance of an expanded class of (semi-)parametric GARCH models belonging to the EGARCH family (EGF), including recently introduced long and short memory specifications and their semiparametric extensions. The semiparametric variants employ a multiplicative volatility decomposition into conditional and slowly varying unconditional components, where the latter is estimated via a data-driven local polynomial smoother to accommodate non-stationarities commonly observed in financial time series. Based on the revised Basel Committee framework for market-risk assessment, all models are capable of producing rolling one-day-ahead forecasts for Value at Risk (VaR) and Expected Shortfall (ES) under a wide range of symmetric and skewed innovation distributions. Their forecasting accuracy is examined using the regulatory traffic light tests for VaR and the recently developed ES-specific traffic light procedure, complemented by the regulatory loss function. In addition, model selection incorporates both a recently proposed corrected firm-oriented loss function that accounts for opportunity costs and the Weighted Absolute Deviation (WAD) criterion. The empirical comparison demonstrates that (semiparametric) long memory GARCH models - particularly those combining fractional dynamics with nonparametric scale adjustments - can serve as valuable alternatives to traditional parametric short memory models, offering more stable volatility estimates and improved tail-risk forecasts for practical risk management applications.}}, author = {{Hanke, Dominik Christian and Uhde, André and Feng, Yuanhua}}, keywords = {{semiparametric GARCH extension, data-driven local polynomial smoother, long memory, GARCH models, Value at Risk, Expected Shortfall, traffic light test, backtesting, Basel III, market risk}}, title = {{{Application of Novel Exponential (Semi-)Parametric Short and Long Memory GARCH Models under Regulatory Requirements of Basel III}}}, year = {{2026}}, } @techreport{66447, abstract = {{Volatility modeling is utilized across numerous fields including finance, environmental studies, and social sciences. It is particularly relevant in scenarios where understanding and predicting conditional variability is crucial, such as when dealing with incremental or time-dependent data. In this paper, novel short and long memory volatility models of the EGARCH family are introduced and analyzed, which are closely related to the well-established EGARCH model proposed by Nelson (1991) but share desirable theoretical properties in several dimensions. Recently developed members of the so-called EGARCH family, which introduces a modulus-log transformation proposed by John and Draper (1980) and a power transformation for the size and magnitude effect to tackle the problem with near-zero innovations and the asymmetric impact of positive and negative shocks on the volatility, are discussed. After a theoretical discussion of the proposed and related volatility models, the practical performance of the elaborated volatility models is compared to well-established and traditional GARCH approaches. A general QMLE algorithm is proposed to estimate the model parameters. The practical relevance of the advanced models is illustrated through a comparative study. By applying these volatility models to a variety of international stock index returns, this paper identifies market-specific characteristics as well as unique strengths and weaknesses of discussed volatility models. Although the practical performance of the recently introduced models is comparable to those obtained by the traditional EGARCH model, they generally outperform traditional non-exponential volatility models used as benchmarks and thus provide a useful alternative to existing short and long memory volatility models. }}, author = {{Hanke, Dominik Christian and Feng, Yuanhua and Uhde, André}}, keywords = {{Modulus Log-GARCH, Modified (FI)EGARCH, Modulus asymmetric (FI)Log-GARCH, (FI)EGARCH, long memory, modulus-log transformation, QMLE, model selection, implementation in R}}, title = {{{Comparing the behaviors of some original short and long memory exponential volatility models}}}, year = {{2026}}, } @article{60118, author = {{Fritz, Marlon and Forstinger, Sarah and Feng, Yuanhua and Gries, Thomas}}, issn = {{0266-4763}}, journal = {{Journal of Applied Statistics}}, number = {{7}}, pages = {{1342--1360}}, publisher = {{Informa UK Limited}}, title = {{{Forecasting economic growth by combining local linear and standard approaches}}}, doi = {{10.1080/02664763.2024.2424920}}, volume = {{52}}, year = {{2024}}, } @article{35992, abstract = {{In this paper new semiparametric generalized autoregressive conditional heteroscedasticity (GARCH) models with long memory are introduced. A multiplicative decomposition of the volatility into a conditional component and an unconditional component is assumed. The estimation of the latter is carried out by means of a data-driven local polynomial smoother. According to the revised recommendations by the Basel Committee on Banking Supervision to measure market risk in the banks’ trading books, these new semiparametric GARCH models are applied to obtain rolling one-step ahead forecasts for the value-at-risk and expected shortfall (ES) for market risk assets. Standard regulatory traffic-light tests and a newly introduced traffic-light test for the ES are carried out for all models. In addition, model performance is assessed via a recently introduced model selection criterion. The practical relevance of our proposal is demonstrated by a comparative study. Our results indicate that semiparametric long-memory GARCH models are a meaningful substitute for their conventional, parametric counterparts. }}, author = {{Letmathe, Sebastian and Feng, Yuanhua and Uhde, André}}, journal = {{Journal of Risk}}, keywords = {{long memory, generalized autoregressive conditional heteroscedasticity (GARCH) models, value-at-risk (VaR), expected shortfall (ES), traffic-light test, backtesting}}, number = {{2}}, title = {{{Semiparametric GARCH models with long memory applied to Value at Risk and Expected Shortfall}}}, volume = {{25}}, year = {{2022}}, } @article{29317, abstract = {{In this paper new semiparametric GARCH models with long memory are in- troduced. The estimation of the nonparametric scale function is carried out by an adapted version of the SEMIFAR algorithm (Beran et al., 2002). Recurring on the revised recommendations by the Basel Committee to measure market risk in the banks' trading books (Basel Committee on Banking Supervision, 2013), the semi- parametric GARCH models are applied to obtain rolling one-step ahead forecasts for the Value at Risk (VaR) and Expected Shortfall (ES) for market risk assets. In addition, standard regulatory traffic light tests (Basel Committee on Banking Supervision, 1996) and a newly introduced traffic light test for the ES are carried out for all models. The practical relevance of our proposal is demonstrated by a comparative study. Our results indicate that semiparametric long memory GARCH models are an attractive alternative to their conventional, parametric counterparts.}}, author = {{Letmathe, Sebastian and Feng, Yuanhua and Uhde, André}}, journal = {{Journal of Risk}}, keywords = {{Semiparametric, long memory, GARCH models, forecasting, Value at Risk, Expected Shortfall, traffic light test, Basel Committee on Banking Supervision}}, title = {{{Semiparametric GARCH models with long memory applied to Value at Risk and Expected Shortfall}}}, doi = {{10.21314/JOR.2022.044}}, year = {{2022}}, } @article{50025, author = {{Feng, Yuanhua and Gries, Thomas and Letmathe, Sebastian and Schulz, Dominik}}, issn = {{2073-4859}}, journal = {{The R Journal}}, keywords = {{Statistics, Probability and Uncertainty, Numerical Analysis, Statistics and Probability}}, number = {{1}}, pages = {{182--195}}, publisher = {{The R Foundation}}, title = {{{The smoots Package in R for Semiparametric Modeling of Trend Stationary Time Series}}}, doi = {{10.32614/rj-2022-017}}, volume = {{14}}, year = {{2022}}, } @article{16873, author = {{Peitz, Christian and Feng, Yuanhua and Gilroy, Bernard Michael and Stöckmann, Nico}}, journal = {{Asian Economic and Financial Review}}, number = {{4}}, pages = {{427--438}}, publisher = {{Asian Economic and Social Society}}, title = {{{The Shanghai-Hong Kong Stock Connect: An Application of the Semi-CGARCH and Semi-EGARCH}}}, volume = {{10}}, year = {{2020}}, } @inproceedings{4665, author = {{Schäfer, Bastian and Feng, Yuanhua}}, booktitle = {{Book of Abstracts}}, location = {{Paderborn, Germany}}, pages = {{7}}, title = {{{Further Development of the Double Conditional Smoothing for Nonparametric Surfaces Under a Lattice Spatial Model}}}, year = {{2018}}, } @inproceedings{4667, author = {{Feng, Yuanhua and Letmathe, Sebastian}}, location = {{Paderborn, Germany}}, pages = {{7}}, title = {{{The Non-Gaussian ESEMIFAR Model}}}, year = {{2018}}, } @inproceedings{4668, author = {{Forstinger, Sarah and Feng, Yuanhua and Peitz, Christian}}, booktitle = {{Book of Abstracts}}, location = {{Paderborn, Germany}}, pages = {{17}}, title = {{{Forecasting Non-Negative Financial Processes Using Different Parametric and Semi-Parametric ACD-Type Models}}}, year = {{2018}}, } @inproceedings{4669, author = {{Zhang, Xuehai and Feng, Yuanhua}}, booktitle = {{Book of Abstracts}}, location = {{Paderborn, Germany}}, pages = {{19}}, title = {{{A Box-Cox Semiparametric Multiplicative Error Model}}}, year = {{2018}}, } @techreport{4633, author = {{Zhang, Xuehai and Feng, Yuanhua and Peitz, Christian}}, title = {{{A general class of SemiGARCH models based on the Box-Cox transformation}}}, year = {{2017}}, } @techreport{4671, author = {{Feng, Yuanhua and Gries, Thomas}}, title = {{{Data-driven local polynomial for the trend and its derivatives in economic time series}}}, year = {{2017}}, } @article{4592, author = {{Feng, Yuanhua and Forstinger, Sarah and Peitz, Christian}}, issn = {{0094-9655}}, journal = {{Journal of Statistical Computation and Simulation}}, number = {{12}}, pages = {{2291--2307}}, publisher = {{Informa UK Limited}}, title = {{{On the iterative plug-in algorithm for estimating diurnal patterns of financial trade durations}}}, doi = {{10.1080/00949655.2015.1107908}}, volume = {{86}}, year = {{2015}}, } @article{4593, author = {{Feng, Yuanhua and Zhou, Chen}}, issn = {{0169-2070}}, journal = {{International Journal of Forecasting}}, number = {{2}}, pages = {{349--363}}, publisher = {{Elsevier BV}}, title = {{{Forecasting financial market activity using a semiparametric fractionally integrated Log-ACD}}}, doi = {{10.1016/j.ijforecast.2014.09.001}}, volume = {{31}}, year = {{2015}}, } @book{4649, editor = {{Beran, Jan and Feng, Yuanhua and Hebbel, Hartmut}}, publisher = {{Springer}}, title = {{{Empirical Economic and Financial Research - Theory, Methods and Practice}}}, year = {{2015}}, } @inbook{4650, author = {{Beran, Jan and Feng, Yuanhua and Hebbel, Hartmut}}, booktitle = {{Empirical Economic and Financial Research}}, isbn = {{9783319031217}}, issn = {{1570-5811}}, pages = {{1--6}}, publisher = {{Springer International Publishing}}, title = {{{Introduction}}}, doi = {{10.1007/978-3-319-03122-4_1}}, year = {{2015}}, } @techreport{4656, author = {{Feng, Yuanhua and Zhou, Chen}}, title = {{{An iterative plug-in algorithm for realized kernels}}}, year = {{2015}}, } @article{4599, author = {{Beran, Jan and Feng, Yuanhua and Ghosh, Sucharita}}, issn = {{0932-5026}}, journal = {{Statistical Papers}}, number = {{2}}, pages = {{431--451}}, publisher = {{Springer Nature}}, title = {{{Modelling long-range dependence and trends in duration series: an approach based on EFARIMA and ESEMIFAR models}}}, doi = {{10.1007/s00362-014-0590-x}}, volume = {{56}}, year = {{2014}}, } @inbook{4602, author = {{Beran, Jan and Feng, Yuanhua and Ghosh, Sucharita}}, booktitle = {{Empirical Economic and Financial Research}}, isbn = {{9783319031217}}, issn = {{1570-5811}}, pages = {{239--253}}, publisher = {{Springer International Publishing}}, title = {{{On EFARIMA and ESEMIFAR Models}}}, doi = {{10.1007/978-3-319-03122-4_15}}, year = {{2014}}, }