The principal component analysis (PCA) is a staple statistical and unsupervised machine learning technique in finance. The application of PCA in a financial setting is associated with several difficulties, such as numerical instability and nonstationarity. We attempt to resolve them by proposing two new variants of PCA: an iterated principal component analysis (IPCA) and an exponentially weighted moving principal component analysis (EWMPCA). Both variants rely on the Ogita-Aishima iteration as a crucial step.
{"title":"Iterated and Exponentially Weighted Moving Principal Component Analysis","authors":"Paul Bilokon, David Finkelstein","doi":"10.2139/ssrn.3913940","DOIUrl":"https://doi.org/10.2139/ssrn.3913940","url":null,"abstract":"The principal component analysis (PCA) is a staple statistical and unsupervised machine learning technique in finance. The application of PCA in a financial setting is associated with several difficulties, such as numerical instability and nonstationarity. We attempt to resolve them by proposing two new variants of PCA: an iterated principal component analysis (IPCA) and an exponentially weighted moving principal component analysis (EWMPCA). Both variants rely on the Ogita-Aishima iteration as a crucial step.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131452862","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}
This article introduces the xtivdfreg command in Stata, which implements a general Instrumental Variables (IV) approach for estimating large panel data models with unobserved common factors or interactive effects, as developed by Norkute et al. (2020) and Cui et al. (2020a). The underlying idea of this approach is to project out the common factors from exogenous co-variates using principal components analysis, and run IV regression using de-factored co-variates as instruments. The resulting "IVDF" method is valid for models with homogeneous or heterogeneous slope coefficients, and has several advantages relative to existing popular approaches. In addition, the xtivdfreg command extends the IVDF approach in two major ways. Firstly, the algorithm accommodates estimation of unbalanced panels. Secondly, the algorithm permits highly flexible instrumentation strategies. It is shown that when one imposes zero factors, the xtivdfreg command can replicate the results of the popular ivregress Stata command. Notably, xtivdfreg also permits estimation of the two-way error components panel data model with heterogeneous slope coefficients.
{"title":"Instrumental Variable Estimation of Large Panel Data Models with Common Factors","authors":"Sebastian Kripfganz, Vasilis Sarafidis","doi":"10.2139/ssrn.3668588","DOIUrl":"https://doi.org/10.2139/ssrn.3668588","url":null,"abstract":"This article introduces the xtivdfreg command in Stata, which implements a general Instrumental Variables (IV) approach for estimating large panel data models with unobserved common factors or interactive effects, as developed by Norkute et al. (2020) and Cui et al. (2020a). The underlying idea of this approach is to project out the common factors from exogenous co-variates using principal components analysis, and run IV regression using de-factored co-variates as instruments. The resulting \"IVDF\" method is valid for models with homogeneous or heterogeneous slope coefficients, and has several advantages relative to existing popular approaches. \u0000 \u0000In addition, the xtivdfreg command extends the IVDF approach in two major ways. Firstly, the algorithm accommodates estimation of unbalanced panels. Secondly, the algorithm permits highly \u0000flexible instrumentation strategies. \u0000 \u0000It is shown that when one imposes zero factors, the xtivdfreg command can replicate the results of the popular ivregress Stata command. Notably, xtivdfreg also permits estimation of the two-way error components panel data model with heterogeneous slope coefficients.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122404647","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}
Impulse response analysis is a cornerstone in applied (macro-)econometrics. Estimating impulse response functions using local projections (LPs) has become an appealing alternative to the traditional structural vector autoregressive (SVAR) approach. Despite its growing popularity and applications, however, no R package yet exists that makes this method available. In this paper, I introduce lpirfs, a fast and flexible R package that provides a broad framework to compute and visualize impulse response functions using LPs for a variety of data sets.
{"title":"lpirfs: An R Package to Estimate Impulse Response Functions by Local Projections","authors":"P. Adämmer","doi":"10.32614/RJ-2019-052","DOIUrl":"https://doi.org/10.32614/RJ-2019-052","url":null,"abstract":"Impulse response analysis is a cornerstone in applied (macro-)econometrics. Estimating impulse response functions using local projections (LPs) has become an appealing alternative to the traditional structural vector autoregressive (SVAR) approach. Despite its growing popularity and applications, however, no R package yet exists that makes this method available. In this paper, I introduce lpirfs, a fast and flexible R package that provides a broad framework to compute and visualize impulse response functions using LPs for a variety of data sets.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121505099","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}
We develop a simple method to reduce privacy loss when disclosing statistics such as OLS regression estimates based on samples with small numbers of observations. We focus on the case where the dataset can be broken into many groups (“cells”) and one is interested in releasing statistics for one or more of these cells. Building on ideas from the differential privacy literature, we add noise to the statistic of interest in proportion to the statistic's maximum observed sensitivity, defined as the maximum change in the statistic from adding or removing a single observation across all the cells in the data. Intuitively, our approach permits the release of statistics in arbitrarily small samples by adding sufficient noise to the estimates to protect privacy. Although our method does not offer a formal privacy guarantee, it generally outperforms widely used methods of disclosure limitation such as count-based cell suppression both in terms of privacy loss and statistical bias. We illustrate how the method can be implemented by discussing how it was used to release estimates of social mobility by Census tract in the Opportunity Atlas. We also provide a step-by-step guide and illustrative Stata code to implement our approach.
{"title":"A Practical Method to Reduce Privacy Loss When Disclosing Statistics Based on Small Samples","authors":"Raj Chetty, John N Friedman","doi":"10.1257/PANDP.20191109","DOIUrl":"https://doi.org/10.1257/PANDP.20191109","url":null,"abstract":"We develop a simple method to reduce privacy loss when disclosing statistics such as OLS regression estimates based on samples with small numbers of observations. We focus on the case where the dataset can be broken into many groups (“cells”) and one is interested in releasing statistics for one or more of these cells. Building on ideas from the differential privacy literature, we add noise to the statistic of interest in proportion to the statistic's maximum observed sensitivity, defined as the maximum change in the statistic from adding or removing a single observation across all the cells in the data. Intuitively, our approach permits the release of statistics in arbitrarily small samples by adding sufficient noise to the estimates to protect privacy. Although our method does not offer a formal privacy guarantee, it generally outperforms widely used methods of disclosure limitation such as count-based cell suppression both in terms of privacy loss and statistical bias. We illustrate how the method can be implemented by discussing how it was used to release estimates of social mobility by Census tract in the Opportunity Atlas. We also provide a step-by-step guide and illustrative Stata code to implement our approach.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117036699","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}
Matthias Weber, Jonas Striaukas, M. Schumacher, H. Binder
Often, variables are linked to each other via a network. When such a network structure is known, this knowledge can be incorporated into regularized regression settings via a network penalty term. However, when the type of interaction via the network is unknown (that is, whether connections are of an activating or a repressing type), the connection signs have to be estimated simultaneously with the covariate coefficients. This can be done with an algorithm iterating a connection sign estimation step and a covariate coefficient estimation step. We develop such an algorithm and show detailed simulation results and an application forecasting event times. The algorithm performs well in a variety of settings. We also briefly describe the R-package that we developed for this purpose, which is publicly available.
{"title":"Network-Constrained Covariate Coefficient and Connection Sign Estimation","authors":"Matthias Weber, Jonas Striaukas, M. Schumacher, H. Binder","doi":"10.2139/ssrn.3211163","DOIUrl":"https://doi.org/10.2139/ssrn.3211163","url":null,"abstract":"Often, variables are linked to each other via a network. When such a network structure is known, this knowledge can be incorporated into regularized regression settings via a network penalty term. However, when the type of interaction via the network is unknown (that is, whether connections are of an activating or a repressing type), the connection signs have to be estimated simultaneously with the covariate coefficients. This can be done with an algorithm iterating a connection sign estimation step and a covariate coefficient estimation step. We develop such an algorithm and show detailed simulation results and an application forecasting event times. The algorithm performs well in a variety of settings. We also briefly describe the R-package that we developed for this purpose, which is publicly available.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116160244","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}
This paper presents and discusses the contributions and usage of GetDFPData, which is an open and free software for accessing corporate data from the Brazilian financial exchange, B3. The distribution and popularization of an open-source algorithm for gathering and managing financial data can improve finance research and practice in two ways. First, it increases the number and quality of research in accounting and corporate finance. Secondly, it provides retail investors with reliable data that may help their allocation decisions. Initially, we analyze the use of this kind of data in a list of recent publications to show the relevance of financial reports and corporate events data for research in the fields of accounting and finance. Finally, we illustrate the use of GetDFPData in large-scale research, an empirical and reproducible example of a corporate finance study.
{"title":"Accessing Financial Reports and Corporate Events with GetDFPdata","authors":"M. Perlin, Guilherme Kirch, D. Vancin","doi":"10.2139/ssrn.3128252","DOIUrl":"https://doi.org/10.2139/ssrn.3128252","url":null,"abstract":"This paper presents and discusses the contributions and usage of GetDFPData, which is an open and free software for accessing corporate data from the Brazilian financial exchange, B3. The distribution and popularization of an open-source algorithm for gathering and managing financial data can improve finance research and practice in two ways. First, it increases the number and quality of research in accounting and corporate finance. Secondly, it provides retail investors with reliable data that may help their allocation decisions. Initially, we analyze the use of this kind of data in a list of recent publications to show the relevance of financial reports and corporate events data for research in the fields of accounting and finance. Finally, we illustrate the use of GetDFPData in large-scale research, an empirical and reproducible example of a corporate finance study.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123018792","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}
This paper is the first to investigate the effect of industrial penetration (geographic concentration of industries) and internet intensity (the proportion of enterprises that uses the internet) for Taiwan manufacturing firms, and analyses whether the relationships are substitutes or complements. The sample observations are based on a unique set of data, namely 153,081 manufacturing plants, and covers 26 two-digit industry categories and 358 geographical townships in Taiwan. The Heckman sample selection model is used to accommodate sample selectivity for unobservable data for firms that use the internet. The empirical results from Heckman’s two-stage estimation show that: (1) a higher degree of industrial penetration will not affect the probability that firms will use the internet, but it will affect the total expenditure on internet intensity; (2) for two-digit SIC (Standard Industrial Classification) industries, industrial penetration generally decreases the total expenditure on internet intensity; and, (3) industrial penetration and internet intensity are substitutes.
{"title":"A Statistical Analysis of Industrial Penetration and Internet Intensity in Taiwan","authors":"Chia‐Lin Chang, M. McAleer, Yu-Chieh Wu","doi":"10.2139/ssrn.3100203","DOIUrl":"https://doi.org/10.2139/ssrn.3100203","url":null,"abstract":"This paper is the first to investigate the effect of industrial penetration (geographic concentration of industries) and internet intensity (the proportion of enterprises that uses the internet) for Taiwan manufacturing firms, and analyses whether the relationships are substitutes or complements. The sample observations are based on a unique set of data, namely 153,081 manufacturing plants, and covers 26 two-digit industry categories and 358 geographical townships in Taiwan. The Heckman sample selection model is used to accommodate sample selectivity for unobservable data for firms that use the internet. The empirical results from Heckman’s two-stage estimation show that: (1) a higher degree of industrial penetration will not affect the probability that firms will use the internet, but it will affect the total expenditure on internet intensity; (2) for two-digit SIC (Standard Industrial Classification) industries, industrial penetration generally decreases the total expenditure on internet intensity; and, (3) industrial penetration and internet intensity are substitutes.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123962126","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}
Since household consumption depends among others on income, it will be of interest to examine the change of household consumption structure due to income changes. This will be useful to supply chain management as well as policy makers. Our sample refers to Western Europe, USA and Japan during the period 1996-2015. The panel data regression is made feasible through the Eviews software package.
{"title":"Consumption Structure Repercussions","authors":"M. Georgiou","doi":"10.2139/ssrn.3081675","DOIUrl":"https://doi.org/10.2139/ssrn.3081675","url":null,"abstract":"Since household consumption depends among others on income, it will be of interest to examine the change of household consumption structure due to income changes. This will be useful to supply chain management as well as policy makers. Our sample refers to Western Europe, USA and Japan during the period 1996-2015. The panel data regression is made feasible through the Eviews software package.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133880525","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}
Spanish Abstract: Se desarrolla la modelación del esquema básico de la teoría macroeconómica (IS-LM), en un contexto de economía cerrada y posteriormente en una economía abierta, así también se desarrollan algunas estimaciones de los efectos de política económica en el modelo planteado.
English Abstract: We develop the modelling of the basic scheme of the macroeconomic theory (IS-LM model) in a close economy and after that in a open economy setting, we develop some estimations about the effects of economic policy on the proposed model.
{"title":"Modelos Macroeconómicos Básicos En Matlab (Basic Macroeconomic Models in Matlab)","authors":"Alfonso Ayala","doi":"10.2139/ssrn.3621904","DOIUrl":"https://doi.org/10.2139/ssrn.3621904","url":null,"abstract":"<b>Spanish Abstract:</b> Se desarrolla la modelación del esquema básico de la teoría macroeconómica (IS-LM), en un contexto de economía cerrada y posteriormente en una economía abierta, así también se desarrollan algunas estimaciones de los efectos de política económica en el modelo planteado.<br><br><b>English Abstract:</b> We develop the modelling of the basic scheme of the macroeconomic theory (IS-LM model) in a close economy and after that in a open economy setting, we develop some estimations about the effects of economic policy on the proposed model.<br>","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134569587","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}
This paper considers the optimal switching problem and the optimal multiple stopping problem for one-dimensional Markov processes in a finite horizon discrete time framework. We develop a dynamic programming procedure to solve these problems and provide easy-to-verify conditions to characterize connectedness of switching and exercise regions. When the transition or Feynman-Kac semigroup of the Markov process has discrete spectrum, we develop an efficient algorithm based on eigenfunction expansions that explicitly solves the dynamic programming problem. We also prove that the algorithm converges exponentially in the series truncation level. Our method is applicable to a rich family of Markov processes which are widely used in financial applications, including many diffusions as well as jump-diffusions and pure jump processes that are constructed from diffusion through time change. In particular, many of these processes are often used to model mean-reversion. We illustrate the versatility of our method by considering three applications: valuation of combination shipping carriers, interest-rate chooser flexible caps and commodity swing options. Numerical examples show that our method is highly efficient and has significant computational advantages over standard numerical PDE methods that are typically used to solve such problems.
{"title":"An Efficient Algorithm Based on Eigenfunction Expansions for Some Optimal Timing Problems in Finance","authors":"Lingfei Li, X. Qu, Gongqiu Zhang","doi":"10.2139/ssrn.2605742","DOIUrl":"https://doi.org/10.2139/ssrn.2605742","url":null,"abstract":"This paper considers the optimal switching problem and the optimal multiple stopping problem for one-dimensional Markov processes in a finite horizon discrete time framework. We develop a dynamic programming procedure to solve these problems and provide easy-to-verify conditions to characterize connectedness of switching and exercise regions. When the transition or Feynman-Kac semigroup of the Markov process has discrete spectrum, we develop an efficient algorithm based on eigenfunction expansions that explicitly solves the dynamic programming problem. We also prove that the algorithm converges exponentially in the series truncation level. Our method is applicable to a rich family of Markov processes which are widely used in financial applications, including many diffusions as well as jump-diffusions and pure jump processes that are constructed from diffusion through time change. In particular, many of these processes are often used to model mean-reversion. We illustrate the versatility of our method by considering three applications: valuation of combination shipping carriers, interest-rate chooser flexible caps and commodity swing options. Numerical examples show that our method is highly efficient and has significant computational advantages over standard numerical PDE methods that are typically used to solve such problems.","PeriodicalId":438593,"journal":{"name":"ERN: Econometric Software (Topic)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133217034","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：