Kasahara, Hiroyuki, and Katsumi Shimotsu. “Asymptotic properties of the maximum likelihood estimator in regime switching econometric models." Journal of econometrics 208.2 (2019): 442-467. [PDF]
Dufays, Arnaud, and Jeroen VK Rombouts. “Relevant parameter changes in structural break models." Journal of Econometrics (2019). [PDF]
Structural break time series models, which are commonly used in macroeconomics and finance, capture unknown structural changes by allowing for abrupt changes to model parameters. However, most specifications suffer from an over-parametrization issue, since all parameters have to change when a break occurs. We introduce a sparse change-point model to detect which parameters change over time. We propose a shrinkage prior distribution, which controls model parsimony by limiting the number of parameters that change from one structural break to another. We develop a Bayesian sampler for inference on the sparse change-point model. An extensive simulation study based on AR, ARMA and GARCH processes highlights the excellent performance of the sampler. We then propose three empirical applications. First, we revisit the US three-month Treasury bill modelling proposed in Pesaran, Pettenuzzo, and Timmermann (2006) to emphasize that many of the detected breaks are due to a change in only a subset of the model parameters. A second application consists of studying the 22 most-used macroeconomic time series for breaks in parameters. As a final exercise, we summarize GARCH parameter breaks detected in 384 financial returns for companies in the S&P 500 index.
==noted by yinung=
使用路透社新聞資料庫 Reuters online news archive
In the wake of the still ongoing global financial crisis, bank interdependencies have come into focus in trying to assess linkages among banks and systemic risk. To date, such analysis has largely been based on numerical data. By contrast, this study attempts to gain further insight into bank interconnections by tapping into financial discourse. We present a text-to-network process, which has its basis in co-occurrences of bank names and can be analyzed quantitatively and visualized. To quantify bank importance, we propose an information centrality measure to rank and assess trends of bank centrality in discussion. For qualitative assessment of bank networks, we put forward a visual, interactive interface for better illustrating network structures. We illustrate the text-based approach on European Large and Complex Banking Groups (LCBGs) during the ongoing financial crisis by quantifying bank interrelations and centrality from discussion in 3M news articles, spanning 2007Q1 to 2014Q3. JEL Classification: E
|Keywords:||bank networks, information centrality, systemic risk, text analysis|
|By:||Áureo de Paula (Institute for Fiscal Studies and University College London)|
In this article I provide a (selective) review of the recent econometric literature on networks. I start with a discussion of developments in the econometrics of group interactions. I subsequently provide a description of statistical and econometric models for network formation and approaches for the joint determination of networks and interactions mediated through those networks. Finally, I give a very brief discussion of measurement issues in both outcomes and networks. My focus is on identification and computational issues, but estimation aspects are also discussed.
Direct purchases are a widespread and important typology of the so-called Alternative Food Networks. Within this channel, farmers’ markets represent a popular and deeply investigated farmer-to-consumer market segment. While farmers’ markets are a quite recent initiatives, it is traditional to find in many towns in Italy both conventional stands and farmers’ stands selling fruit and vegetables in the same district market. We therefore analyse the behavioural characteristics of local market consumers choosing to purchase from farmers in order to point out the determinants of their choice. The consumers’ preferences were assessed through an in-person survey. Data were collected interviewing consumers in open-air markets in Torino, Cuneo, Alessandria and Asti, four cities in Piedmont Region (Italy) where farmers sell their products. The determinants of the choice to buy from farm stands were analysed with a probit model using a final sample of 1,138 respondents. Explanatory variables comprise the consumers’ general attitudes towards the purchase of food (importance given to convenience, price, quality and trust) and their personal characteristics. Also, other variables were added in order to highlight the possible role of markets and areas with distinctive characteristics. The most important factor affecting consumers’ choice for farm stand is the quest for quality. Consumers with a strong interest in quality are significantly more likely to buy from farmers. Among the personal characteristics, being the household member in charge of buying fruits and vegetables, and education, are the main determinants of the choice of farmers’ stands. On the contrary, the effects of variables such as income and job skill level are not clear enough,and seem to be open to different interpretations.
|Keywords:||Alternative Food Networks, direct purchase, consumers’ choices, Agricultural and Food Policy, D4, Q13,|
|By:||Jolivet, Grégory (University of Bristol)
Turon, Hélène (University of Bristol)
We analyse consumers’ search and purchase decisions on an Internet platform. Using a rich dataset on all adverts posted and transactions made on a major French Internet platform (PriceMinister), we show evidence of substantial price dispersion among adverts for the same product. We also show that consumers do not necessarily choose the cheapest advert available and sometimes even choose an advert that is dominated in price and non-price characteristics (such as seller’s reputation) by another available advert. To explain the transactions observed on the platform, we derive and estimate a structural model of sequential directed search where consumers observe all advert prices but have to pay a search cost to see the other advert characteristics. We allow for flexible heterogeneity in consumers’ preferences and search costs. After deriving tractable identification conditions for our model, we estimate sets of parameters that can rationalize each transaction. Our model can predict a wide range of consumer search strategies and fits almost all transactions observed in our sample. We find empirical evidence of heterogenous, sometimes positive and substantially large search costs and marginal willingness to pay for advert hedonic characteristics.
|Keywords:||consumer search, revealed preferences, individual heterogeneity, price dispersion, internet|
|JEL:||C13 D12 D81 D83 L13|
|By:||Federico Etro (Department of Economics, University Of Venice Cà Foscari)
Elena Stepanova (Sant’Anna School of Advanced Studies, Pisa)
We analyze organization of auctions and bidding strategies with a unique dataset on Paris auctions between 700s and 800s. Prices reflect the objective features of the paintings and of the sale, and they reveal a substantial death effect, with upward jumps in the years after the death of the artists. Both the hedonic and repeated sale price indexes show a declining pattern for the relative price of paintings starting with the French Revolution. On this basis we analyze the emerging role and market power of art dealers and employ network theory to study whether they created rings to manipulate the outcome of the auctions for their profits. Dealers appear to have been divided into four main communities heavily trading between themselves and we find evidence of collusive behavior with lower hammer prices for buyers belonging to the same community of the dealers organizing the auction.
|Keywords:||Art market, Hedonic prices, Repeated sales price index, Network theory.|
|JEL:||Z11 N0 D4|
YNY: 這是一篇分析法國2009年實施的 Hadopi law (有在 P2P 網路的軟體盜版行為之法律: 前2次不罰, 第3次偵測到才罰) 的實證影響, 透過網路問卷。
|By:||MICHAEL ARNOLD (Department of Economics,University of Delaware)
ERIC DARMON (CREM, University of Rennes)
SYLVAIN DEJEAN (CREM, LR-MOS, University of La Rochelle)
THIERRY PENARD (CREM, University of Rennes 1 & University of Delaware)
Most developed countries have tried to restrain digital piracy by strength- ening laws against copyright infringement. In 2009, France implemented the Hadopi law. Under this law individuals receive a warning the first two times they are detected illegally sharing content through peer to peer (P2P) networks. Legal action is only taken when a third violation is detected. We analyze the impact of this law on individual behavior. Our theoretical model of illegal be- havior under a graduated response law predicts that the perceived probability of detection has no impact on the decision to initially engage in digital piracy, but may reduce the intensity of illegal file sharing by those who do pirate. We test the theory using survey data from French Internet users. Our econometric results indicate that the law has no substantial deterrent effect. In addition, we find evidence that individuals who are better informed about the law and piracy alternatives substitute away from monitored P2P networks and illegally access content through unmonitored channels.
|Keywords:||Digital Piracy, digital media, Hadopi, three-strikes law, property rights|
|JEL:||L82 O34 K42 D11|
YNY: 這是一篇難得一見的研究主題, 以吸毒的幫派紀錄估計組織犯罪網路之網路外部性和其價值。
|By:||Mastrobuoni, Giovanni (University of Essex)|
Using declassified Federal Bureau of Narcotics (毒品) records on 800 US Mafia members active in the 1950s and 1960s, and on their connections within the organized crime network, I estimate network effects on gangsters’ economic status. Lacking information on criminal proceeds, I measure economic status exploiting detailed information about their place of residence. Housing values are reconstructed using current deflated transactions recorded on Zillow.com. I deal with the potential reverse causality between the economic status and the gangster’s position in the network exploiting exogenous exposure to potential pre-immigration connections. In the absence of pre-immigration data I use the informational content of surnames, called isonomy, to measure the place of origin. The instrument is valid as long as conditional on the characteristics of the gangsters (including the region of birth and a rich set of controls about the gangsters’ legal and illegal activities) such exposure influences the gangsters’ importance in- side the network (called centrality) but not the preference for specific housing needs. A standard deviation increase in closeness centrality increases economic status by between one forth (OLS) and one standard deviation (2SLS).
|Keywords:||mafia, networks, centrality, housing prices, value of connections, crime, surnames, isonomy|
|JEL:||A14 C21 D23 D85 K42 Z13|
Kerr, Norbert L.; MacCoun, Robert J.; Kramer, Geoffrey P. (1996) “Bias in judgment: Comparing individuals and groups." Psychological Review, Vol 103(4), Oct 1996, 687-719. http://psycnet.apa.org/?fa=main.doiLanding&doi=10.1037/0033-295X.103.4.687. uci.edu 提供的 [PDF]
The relative susceptibility of individuals and groups to systematic judgmental biases is considered. An overview of the relevant empirical literature reveals no clear or general pattern. However, a theoretical analysis employing J. H. Davis’s (1973) social decision scheme (SDS) model reveals that the relative magnitude of individual and group bias depends upon several factors, including group size, initial individual judgment, the magnitude of bias among individuals, the type of bias, and most of all, the group-judgment process. It is concluded that there can be no simple answer to the question, “Which are more biased, individuals or groups?," but the SDS model offers a framework for specifying some of the conditions under which individuals are both more and less biased than groups.