Abstract This paper explores the effect of real estate news sentiment on the stock returns of Swedbank and SEB Bank, which are leading banks in Sweden and the Baltic region. For this purpose, we have selected sentiments from news about real estate in the markets of these banks in Sweden, Estonia, Latvia, and Lithuania between 4 January 2016 and 19 February 2019. Estimation results showed that sentiments about the housing market affect stock returns for both banks, and the effect is different for positive and negative news. We also found that there is a difference in the stock returns of these banks in terms of when and to what extent they react to news coming from the Baltic States and Sweden. Moreover, we found that the number of negative news affects the stock returns of the banks more than the strength of the news. We also apply several GARCH specifications to explore if negative and positive news affect the volatility processes to some extent. We found out that the volatilities are explained better by the GJR-GARCH and NAGARCH models. Overall, the volatility of SEB stock returns depends more on the news sentiments compared to the volatility of Swedbank stock returns.
{"title":"Effect of Real Estate News Sentiments on the Stock Returns of Swedbank and SEB Bank","authors":"Yuliia Puzanova, M. Eratalay","doi":"10.2478/erfin-2021-0005","DOIUrl":"https://doi.org/10.2478/erfin-2021-0005","url":null,"abstract":"Abstract This paper explores the effect of real estate news sentiment on the stock returns of Swedbank and SEB Bank, which are leading banks in Sweden and the Baltic region. For this purpose, we have selected sentiments from news about real estate in the markets of these banks in Sweden, Estonia, Latvia, and Lithuania between 4 January 2016 and 19 February 2019. Estimation results showed that sentiments about the housing market affect stock returns for both banks, and the effect is different for positive and negative news. We also found that there is a difference in the stock returns of these banks in terms of when and to what extent they react to news coming from the Baltic States and Sweden. Moreover, we found that the number of negative news affects the stock returns of the banks more than the strength of the news. We also apply several GARCH specifications to explore if negative and positive news affect the volatility processes to some extent. We found out that the volatilities are explained better by the GJR-GARCH and NAGARCH models. Overall, the volatility of SEB stock returns depends more on the news sentiments compared to the volatility of Swedbank stock returns.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"77 - 117"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45406495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ifeanyi Francis Osegbue, John Ogbonnia Obasi, Chitom Rachael John-Akamelu, Chizoba Mary Nwoye
Abstract This paper analyzes the effect of cash flow from corporate tax aggressiveness on corporate investment expenditure in Nigeria and Ghana from 2010 to 2017. The sampled outcome is measured by estimating pooled ordinary least squares, as well as random and fixed effects models. The study uses dynamic models to draw significance because it corrects for endogeneity, cross-sectional dependence, serial correlation, and heteroscedasticity by including instruments that are uncorrelated with the regressors in the underlying routine during estimation. The corporate tax aggressiveness indicators are tax saving, effective tax rate, book-tax difference, and temporary tax difference - with firm size as the control variable. Findings, among others, reveal that tax aggressiveness has a statistically significant influence on corporate investment expenditure in both countries. This provides evidence that tax aggressiveness is positive and that its coefficients are statistically significant to the tax aggressiveness variables; in particular, tax saving and effective tax rate maintained consistent positive and statistically significant relationships to corporate investment expenditure across all model specifications. In other words, an increase in tax saving and effective tax rate boost the total and new investment expenditure in both countries. Other findings show that a large difference between income reported on financial statements and income reported on tax return reduces corporate total and new investment expenditure in both countries. Furthermore, a proportionate increase in investment maintenance expenditure occurs when a book-tax gap changes in Nigeria. This is because managers reduce taxable income in order to increase investment maintenance expenditure. For the control variables, firm size boosts corporate investment expenditure in both countries.
{"title":"Corporate Tax Aggressiveness and Corporate Investment Expenditure in Nigeria and Ghana","authors":"Ifeanyi Francis Osegbue, John Ogbonnia Obasi, Chitom Rachael John-Akamelu, Chizoba Mary Nwoye","doi":"10.2478/erfin-2021-0007","DOIUrl":"https://doi.org/10.2478/erfin-2021-0007","url":null,"abstract":"Abstract This paper analyzes the effect of cash flow from corporate tax aggressiveness on corporate investment expenditure in Nigeria and Ghana from 2010 to 2017. The sampled outcome is measured by estimating pooled ordinary least squares, as well as random and fixed effects models. The study uses dynamic models to draw significance because it corrects for endogeneity, cross-sectional dependence, serial correlation, and heteroscedasticity by including instruments that are uncorrelated with the regressors in the underlying routine during estimation. The corporate tax aggressiveness indicators are tax saving, effective tax rate, book-tax difference, and temporary tax difference - with firm size as the control variable. Findings, among others, reveal that tax aggressiveness has a statistically significant influence on corporate investment expenditure in both countries. This provides evidence that tax aggressiveness is positive and that its coefficients are statistically significant to the tax aggressiveness variables; in particular, tax saving and effective tax rate maintained consistent positive and statistically significant relationships to corporate investment expenditure across all model specifications. In other words, an increase in tax saving and effective tax rate boost the total and new investment expenditure in both countries. Other findings show that a large difference between income reported on financial statements and income reported on tax return reduces corporate total and new investment expenditure in both countries. Furthermore, a proportionate increase in investment maintenance expenditure occurs when a book-tax gap changes in Nigeria. This is because managers reduce taxable income in order to increase investment maintenance expenditure. For the control variables, firm size boosts corporate investment expenditure in both countries.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"139 - 161"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46726372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chizoba Mary Nwoye, P. Egbunike, Ifeanyi Francis Osegbue
Abstract This paper evaluates the effect of integrated reporting on the firm value of oil and gas companies comparing the two biggest economies in Africa from 2015 to 2018. The study used Tobin’s Q ratio as a proxy to firm value, while integrated reporting was broken down into five capitals of integrated reporting: intellectual capital, human capital, natural capital, social/responsibility capital, and financial capital. Preliminary analyses were conducted, such as descriptive statistics and correlation matrix. In analyzing the data, the study adopted the panel multiple regression method to identify the possible effect of integrated reporting on the firm value of oil and gas companies in Nigeria and South Africa using the Hausman test to choose between fixed and random effects. The result shows that integrated reporting has a significant positive effect on firm values in South Africa and Nigeria. We, therefore, recommend that integrated reporting in Nigeria should be used as a mandatory reporting system because this will encourage stakeholder understanding, instead of trying to source sustainability reports after examining financial statements.
{"title":"Integrated Reporting and Firm Value in the Nigerian and South African Oil and Gas Sector","authors":"Chizoba Mary Nwoye, P. Egbunike, Ifeanyi Francis Osegbue","doi":"10.2478/erfin-2021-0008","DOIUrl":"https://doi.org/10.2478/erfin-2021-0008","url":null,"abstract":"Abstract This paper evaluates the effect of integrated reporting on the firm value of oil and gas companies comparing the two biggest economies in Africa from 2015 to 2018. The study used Tobin’s Q ratio as a proxy to firm value, while integrated reporting was broken down into five capitals of integrated reporting: intellectual capital, human capital, natural capital, social/responsibility capital, and financial capital. Preliminary analyses were conducted, such as descriptive statistics and correlation matrix. In analyzing the data, the study adopted the panel multiple regression method to identify the possible effect of integrated reporting on the firm value of oil and gas companies in Nigeria and South Africa using the Hausman test to choose between fixed and random effects. The result shows that integrated reporting has a significant positive effect on firm values in South Africa and Nigeria. We, therefore, recommend that integrated reporting in Nigeria should be used as a mandatory reporting system because this will encourage stakeholder understanding, instead of trying to source sustainability reports after examining financial statements.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"163 - 181"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47235002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Artificial intelligence has transformed the forecasting of stock prices and the evaluation of companies. Novel techniques, allowing the real-time processing of large amounts of data, have enabled the use of data on various external factors to improve the forecasting of the company’s value and stock price. Although conventional approaches solely focus on the use of quantitative data, history has shown that news announcements and statements may significantly affect the performance of the stock value of companies. We present an innovative framework for integrating a nonlinear autoregressive network with a natural language processing approach to analyze stock price movements and forecast stock prices. The framework analyzes and processes the company’s financial statements, determining indicative factors and transforming them into categorical parameters which are then integrated into a nonlinear autoregressive network to estimate and forecast the company’s stock price. The analysis of several Saudi companies listed in the Tadawul index affirms the improved estimation of the stock price and the possibility of a more precise prediction of long-term stock price evolution.
{"title":"An Innovative Artificial Intelligence and Natural Language Processing Framework for Asset Price Forecasting Based on Islamic Finance: A Case Study of the Saudi Stock Market","authors":"Klemens Katterbauer, Philippe Moschetta","doi":"10.2478/erfin-2021-0009","DOIUrl":"https://doi.org/10.2478/erfin-2021-0009","url":null,"abstract":"Abstract Artificial intelligence has transformed the forecasting of stock prices and the evaluation of companies. Novel techniques, allowing the real-time processing of large amounts of data, have enabled the use of data on various external factors to improve the forecasting of the company’s value and stock price. Although conventional approaches solely focus on the use of quantitative data, history has shown that news announcements and statements may significantly affect the performance of the stock value of companies. We present an innovative framework for integrating a nonlinear autoregressive network with a natural language processing approach to analyze stock price movements and forecast stock prices. The framework analyzes and processes the company’s financial statements, determining indicative factors and transforming them into categorical parameters which are then integrated into a nonlinear autoregressive network to estimate and forecast the company’s stock price. The analysis of several Saudi companies listed in the Tadawul index affirms the improved estimation of the stock price and the possibility of a more precise prediction of long-term stock price evolution.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"183 - 196"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44439921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract There has been a renewed interest in accurately forecasting the price of crude oil and its fluctuations. That said, this paper aims to study whether the price of crude oil in the United States (US) could be predicted using the stock prices of the top information technology companies. To this end, time-series data was collected and pre-processed as needed, and three architectures of computational neural networks were tested: deep neural networks, long-short term memory (LSTM) neural networks, and a combination of convolutional and LSTM neural networks. The findings suggest that LSTM networks are the best architectures to predict the crude oil price. The outcomes of this paper could potentially help in making the oil price prediction mechanism a more tractable task and in assisting decision-makers to improve macroeconomic policies, generate enhanced macroeconomic projections, and better assess macroeconomic risks.
{"title":"Predicting the Price of Crude Oil and its Fluctuations Using Computational Econometrics: Deep Learning, LSTM, and Convolutional Neural Networks","authors":"Rayan H. Assaad, S. Fayek","doi":"10.2478/ERFIN-2021-0006","DOIUrl":"https://doi.org/10.2478/ERFIN-2021-0006","url":null,"abstract":"Abstract There has been a renewed interest in accurately forecasting the price of crude oil and its fluctuations. That said, this paper aims to study whether the price of crude oil in the United States (US) could be predicted using the stock prices of the top information technology companies. To this end, time-series data was collected and pre-processed as needed, and three architectures of computational neural networks were tested: deep neural networks, long-short term memory (LSTM) neural networks, and a combination of convolutional and LSTM neural networks. The findings suggest that LSTM networks are the best architectures to predict the crude oil price. The outcomes of this paper could potentially help in making the oil price prediction mechanism a more tractable task and in assisting decision-makers to improve macroeconomic policies, generate enhanced macroeconomic projections, and better assess macroeconomic risks.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"119 - 137"},"PeriodicalIF":0.0,"publicationDate":"2021-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47797956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Orji, Jonathan E. Ogbuabor, G. Aza, Onyinye I. Anthony‐Orji
Abstract This study investigates the impact of foreign direct investment on the level of firm technical efficiency in West Africa. Firms from Nigeria, Ghana, Sierra Leone and the Gambia were sampled due to the fact that they used to belong to the British Empire. The data, sourced from the World Bank enterprise survey, covers the period from 2006 to 2018, with the sampled countries having data for different years. A time varying stochastic frontier production function for panel was developed for this enquiry. The findings of the study show that foreign direct investment has a significant and positive impact on both technical efficiency and productivity of firms in West Africa. Controlling for other effects, international trade and firm size both have positive and significant effects on firm level technical efficiency. Therefore, policies should be aimed at encouraging more inflows and maintenance of the stock of foreign direct investment to avert divestments. This includes, but is not limited to, ensuring sociopolitical stability and introducing policies that would remove bureaucratic bottlenecks from the path of direct investment inflow and simplify the process of doing business in these countries.
{"title":"Does Foreign Presence Influence the Level of Firm Technical Efficiency? Evidence from Africa","authors":"A. Orji, Jonathan E. Ogbuabor, G. Aza, Onyinye I. Anthony‐Orji","doi":"10.2478/erfin-2021-0001","DOIUrl":"https://doi.org/10.2478/erfin-2021-0001","url":null,"abstract":"Abstract This study investigates the impact of foreign direct investment on the level of firm technical efficiency in West Africa. Firms from Nigeria, Ghana, Sierra Leone and the Gambia were sampled due to the fact that they used to belong to the British Empire. The data, sourced from the World Bank enterprise survey, covers the period from 2006 to 2018, with the sampled countries having data for different years. A time varying stochastic frontier production function for panel was developed for this enquiry. The findings of the study show that foreign direct investment has a significant and positive impact on both technical efficiency and productivity of firms in West Africa. Controlling for other effects, international trade and firm size both have positive and significant effects on firm level technical efficiency. Therefore, policies should be aimed at encouraging more inflows and maintenance of the stock of foreign direct investment to avert divestments. This includes, but is not limited to, ensuring sociopolitical stability and introducing policies that would remove bureaucratic bottlenecks from the path of direct investment inflow and simplify the process of doing business in these countries.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"1 - 20"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47187498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract An abundant amount of literature has documented the limitations of traditional unconstrained mean-variance optimization and Efficient Frontier (EF) considered as an estimation-error maximization that magnifies errors in parameter estimates. Originally introduced by Michaud (1998), empirical superiority of portfolio resampling supposedly lies in the addressing of parameter uncertainty by averaging forecasts that are based on a large number of bootstrap replications. Nevertheless, averaging over resampled portfolio weights in order to obtain the unique Resampled Efficient Frontier (REF, U.S. patent number 6,003,018) has been documented as a debated statistical procedure. Alternatively, we propose a probabilistic extension of the Michaud resampling that we introduce as the Probabilistic Resampled Efficient Frontier (PREF). The originality of this work lies in addressing the information loss in the REF by proposing a geometrical three-dimensional representation of the PREF in the mean-variance-probability space. Interestingly, this geometrical representation illustrates a confidence region around the naive EF associated to higher probabilities; in particular for simulated Global-Mean-Variance portfolios. Furthermore, the confidence region becomes wider with portfolio return, as is illustrated by the dispersion of simulated Maximum-Mean portfolios.
{"title":"A Probabilistic-Based Portfolio Resampling Under the Mean-Variance Criterion","authors":"Anmar Al Wakil","doi":"10.2478/erfin-2021-0003","DOIUrl":"https://doi.org/10.2478/erfin-2021-0003","url":null,"abstract":"Abstract An abundant amount of literature has documented the limitations of traditional unconstrained mean-variance optimization and Efficient Frontier (EF) considered as an estimation-error maximization that magnifies errors in parameter estimates. Originally introduced by Michaud (1998), empirical superiority of portfolio resampling supposedly lies in the addressing of parameter uncertainty by averaging forecasts that are based on a large number of bootstrap replications. Nevertheless, averaging over resampled portfolio weights in order to obtain the unique Resampled Efficient Frontier (REF, U.S. patent number 6,003,018) has been documented as a debated statistical procedure. Alternatively, we propose a probabilistic extension of the Michaud resampling that we introduce as the Probabilistic Resampled Efficient Frontier (PREF). The originality of this work lies in addressing the information loss in the REF by proposing a geometrical three-dimensional representation of the PREF in the mean-variance-probability space. Interestingly, this geometrical representation illustrates a confidence region around the naive EF associated to higher probabilities; in particular for simulated Global-Mean-Variance portfolios. Furthermore, the confidence region becomes wider with portfolio return, as is illustrated by the dispersion of simulated Maximum-Mean portfolios.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"45 - 56"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41715652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Ferreira, Oussama Tilfani, E. Pereira, Cleónidas Tavares, H. Pereira, My Youssef El Boukfaoui
Abstract This paper aims to analyse the connectivity of 13 stock markets, between 1998 and 2019, with a time-varying proposal, to evaluate evolution of the linkage between these markets over time. To do so, we propose to use a network built based on the correlation coefficients from the Detrended Cross-Correlation Analysis, using a sliding windows approach. Besides allowing for analysis over time, our approach also enables us to verify how the network behaves for different time scales, which enriches the analysis. We use two different properties of networks: global efficiency and average grade, to measure the network’s connectivity over time. We find that the markets under analysis became more connected before the subprime crisis, with this behavior extending even after the Eurozone crisis, showing that during extreme events there is an increase in financial risk, as found in the international literature.
{"title":"Dynamic Connectivity in a Financial Network Using Time-Varying DCCA Correlation Coefficients","authors":"P. Ferreira, Oussama Tilfani, E. Pereira, Cleónidas Tavares, H. Pereira, My Youssef El Boukfaoui","doi":"10.2478/erfin-2021-0004","DOIUrl":"https://doi.org/10.2478/erfin-2021-0004","url":null,"abstract":"Abstract This paper aims to analyse the connectivity of 13 stock markets, between 1998 and 2019, with a time-varying proposal, to evaluate evolution of the linkage between these markets over time. To do so, we propose to use a network built based on the correlation coefficients from the Detrended Cross-Correlation Analysis, using a sliding windows approach. Besides allowing for analysis over time, our approach also enables us to verify how the network behaves for different time scales, which enriches the analysis. We use two different properties of networks: global efficiency and average grade, to measure the network’s connectivity over time. We find that the markets under analysis became more connected before the subprime crisis, with this behavior extending even after the Eurozone crisis, showing that during extreme events there is an increase in financial risk, as found in the international literature.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"57 - 75"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46388575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Stock market indices are the benchmark of valuation uncertainty. Funding conditions can have an impact on the discounting process. Therefore time-premium, country-specific premia as well as (un)conventional monetary policy should be considered when studying market volatility. The aim of our research is to identify the effects of the unconventional monetary policy of European central banks on stock markets and to explore specific aspects of the relationship between domestic quantitative easing and the influence of the ECB, through the pattern of small, open economies in Europe. This study employs quantile panel regression to compare the 25% (calming) and 75% (stressed) scenarios of quarterly averaged conditional variance and compares them with an ordinary linear panel regression.
{"title":"Can Market Making of Last Resort Calm the European Stock Markets? The Result of Quantile Regressions on a Sample of Six European Countries","authors":"Mercédesz Mészáros, Dóra Sallai, G. Kiss","doi":"10.2478/ERFIN-2021-0002","DOIUrl":"https://doi.org/10.2478/ERFIN-2021-0002","url":null,"abstract":"Abstract Stock market indices are the benchmark of valuation uncertainty. Funding conditions can have an impact on the discounting process. Therefore time-premium, country-specific premia as well as (un)conventional monetary policy should be considered when studying market volatility. The aim of our research is to identify the effects of the unconventional monetary policy of European central banks on stock markets and to explore specific aspects of the relationship between domestic quantitative easing and the influence of the ECB, through the pattern of small, open economies in Europe. This study employs quantile panel regression to compare the 25% (calming) and 75% (stressed) scenarios of quarterly averaged conditional variance and compares them with an ordinary linear panel regression.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"6 1","pages":"21 - 44"},"PeriodicalIF":0.0,"publicationDate":"2021-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45361668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This paper evaluates the accuracy of forecasts for Polish interest rates of various maturities. We apply the traditional autoregressive Diebold-Li framework as well as its extension, in which the dynamics of latent factors are explained with machine learning techniques. Our findings are fourfold. Firstly, they show that all methods have failed to predict the declining trend of interest rates. Secondly, they suggest that the dynamic affine models have not been able to systematically outperform standard univariate time series models. Thirdly, they indicate that the relative performance of the analyzed models has depended on yield maturity and forecast horizon. Finally, they demonstrate that, in comparison to the traditional time series models, machine learning techniques have not systematically improved the accuracy of forecasts.
{"title":"Forecasting the Yield Curve for Poland","authors":"T. Kostyra, Micha l Rubaszek","doi":"10.2478/erfin-2020-0006","DOIUrl":"https://doi.org/10.2478/erfin-2020-0006","url":null,"abstract":"Abstract This paper evaluates the accuracy of forecasts for Polish interest rates of various maturities. We apply the traditional autoregressive Diebold-Li framework as well as its extension, in which the dynamics of latent factors are explained with machine learning techniques. Our findings are fourfold. Firstly, they show that all methods have failed to predict the declining trend of interest rates. Secondly, they suggest that the dynamic affine models have not been able to systematically outperform standard univariate time series models. Thirdly, they indicate that the relative performance of the analyzed models has depended on yield maturity and forecast horizon. Finally, they demonstrate that, in comparison to the traditional time series models, machine learning techniques have not systematically improved the accuracy of forecasts.","PeriodicalId":33177,"journal":{"name":"Econometric Research in Finance","volume":"5 1","pages":"103 - 117"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49067101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：