Results 1  10
of
614
The Colonial Origins of Comparative Development: An Empirical Analysis
 AMERICAN ECONOMIC REVIEW
, 2002
"... We exploit differences in early colonial experience to estimate the effect of institutions on economic performance. Our argument is that Europeans adopted very different colonization policies in different colonies, with different associated institutions. The choice of colonization strategy was, at l ..."
Abstract

Cited by 1585 (38 self)
 Add to MetaCart
(Show Context)
We exploit differences in early colonial experience to estimate the effect of institutions on economic performance. Our argument is that Europeans adopted very different colonization policies in different colonies, with different associated institutions. The choice of colonization strategy was, at least in part, determined by the feasibility of whether Europeans could settle in the colony. In places where Europeans faced high mortality rates, they could not settle and they were more likely to set up worse (extractive) institutions. These early institutions persisted to the present. We document these hypotheses in the data. Exploiting differences in mortality rates faced by soldiers, bishops and sailors in the colonies during the 18th and 19th centuries as an instrument for current institutions, we estimate large effects of institutions on income per capita. Our estimates imply that a change from the worst (Zaire) to the best (US or New Zealand) institutions in our sample would be associated with a five fold increase in income per capita.
Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
, 2010
"... ..."
(Show Context)
Greedy Function Approximation: A Gradient Boosting Machine
 Annals of Statistics
, 2000
"... Function approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest{descent minimization. A general gradient{descent \boosting" paradigm is developed for additi ..."
Abstract

Cited by 951 (12 self)
 Add to MetaCart
Function approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest{descent minimization. A general gradient{descent \boosting" paradigm is developed for additive expansions based on any tting criterion. Specic algorithms are presented for least{squares, least{absolute{deviation, and Huber{M loss functions for regression, and multi{class logistic likelihood for classication. Special enhancements are derived for the particular case where the individual additive components are regression trees, and tools for interpreting such \TreeBoost" models are presented. Gradient boosting of regression trees produces competitive, highly robust, interpretable procedures for both regression and classication, especially appropriate for mining less than clean data. Connections between this approach and the boosting methods of Freund and Shapire 1996, and Frie...
Strictly Proper Scoring Rules, Prediction, and Estimation
, 2007
"... Scoring rules assess the quality of probabilistic forecasts, by assigning a numerical score based on the predictive distribution and on the event or value that materializes. A scoring rule is proper if the forecaster maximizes the expected score for an observation drawn from the distribution F if he ..."
Abstract

Cited by 357 (27 self)
 Add to MetaCart
(Show Context)
Scoring rules assess the quality of probabilistic forecasts, by assigning a numerical score based on the predictive distribution and on the event or value that materializes. A scoring rule is proper if the forecaster maximizes the expected score for an observation drawn from the distribution F if he or she issues the probabilistic forecast F, rather than G ̸ = F. It is strictly proper if the maximum is unique. In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest. In estimation problems, strictly proper scoring rules provide attractive loss and utility functions that can be tailored to the problem at hand. This article reviews and develops the theory of proper scoring rules on general probability spaces, and proposes and discusses examples thereof. Proper scoring rules derive from convex functions and relate to information measures, entropy functions, and Bregman divergences. In the case of categorical variables, we prove a rigorous version of the Savage representation. Examples of scoring rules for probabilistic forecasts in the form of predictive densities include the logarithmic, spherical, pseudospherical, and quadratic scores. The continuous ranked probability score applies to probabilistic forecasts that take the form of predictive cumulative distribution functions. It generalizes the absolute error and forms a special case of a new and very general type of score, the energy score. Like many other scoring rules, the energy score admits a kernel representation in terms of negative definite functions, with links to inequalities of Hoeffding type, in both univariate and multivariate settings. Proper scoring rules for quantile and interval forecasts are also discussed. We relate proper scoring rules to Bayes factors and to crossvalidation, and propose a novel form of crossvalidation known as randomfold crossvalidation. A case study on probabilistic weather forecasts in the North American Pacific Northwest illustrates the importance of propriety. We note optimum score approaches to point and quantile
Estimating Portfolio and Consumption Choice: A Conditional Euler Equations Approach
 JOURNAL OF FINANCE
, 1999
"... This paper develops a nonparametric approach to examine how portfolio and consumption choice depends on variables that forecast timevarying investment opportunities. I estimate singleperiod and multiperiod portfolio and consumption rules of an investor with constant relative risk aversion and a on ..."
Abstract

Cited by 163 (16 self)
 Add to MetaCart
This paper develops a nonparametric approach to examine how portfolio and consumption choice depends on variables that forecast timevarying investment opportunities. I estimate singleperiod and multiperiod portfolio and consumption rules of an investor with constant relative risk aversion and a onemonth to 20year horizon. The investor allocates wealth to the NYSE index and a 30day Treasury bill. I find that the portfolio choice varies significantly with the dividend yield, default premium, term premium, and lagged excess return. Furthermore, the optimal decisions depend on the investor’s horizon and rebalancing frequency.
Piecewise linear regularized solution paths
 Ann. Statist
, 2007
"... We consider the generic regularized optimization problem ˆ β(λ) = arg minβ L(y, Xβ) + λJ(β). Recently, Efron et al. (2004) have shown that for the Lasso – that is, if L is squared error loss and J(β) = ‖β‖1 is the l1 norm of β – the optimal coefficient path is piecewise linear, i.e., ∂ ˆ β(λ)/∂λ i ..."
Abstract

Cited by 138 (9 self)
 Add to MetaCart
(Show Context)
We consider the generic regularized optimization problem ˆ β(λ) = arg minβ L(y, Xβ) + λJ(β). Recently, Efron et al. (2004) have shown that for the Lasso – that is, if L is squared error loss and J(β) = ‖β‖1 is the l1 norm of β – the optimal coefficient path is piecewise linear, i.e., ∂ ˆ β(λ)/∂λ is piecewise constant. We derive a general characterization of the properties of (loss L, penalty J) pairs which give piecewise linear coefficient paths. Such pairs allow for efficient generation of the full regularized coefficient paths. We investigate the nature of efficient path following algorithms which arise. We use our results to suggest robust versions of the Lasso for regression and classification, and to develop new, efficient algorithms for existing problems in the literature, including Mammen & van de Geer’s Locally Adaptive Regression Splines. 1
The Economic Impacts of Climate Change: Evidence from Agricultural Output and Random Fluctuations in
 Weather. The American Economic Review
, 2007
"... no. 0426 ..."
(Show Context)
Practical selection of svm parameters and noise estimation for svm regression
 Neural Networks
, 2004
"... We investigate practical selection of metaparameters for SVM regression (that is, εinsensitive zone and regularization parameter C). The proposed methodology advocates analytic parameter selection directly from the training data, rather than resampling approaches commonly used in SVM applications. ..."
Abstract

Cited by 111 (1 self)
 Add to MetaCart
We investigate practical selection of metaparameters for SVM regression (that is, εinsensitive zone and regularization parameter C). The proposed methodology advocates analytic parameter selection directly from the training data, rather than resampling approaches commonly used in SVM applications. Good generalization performance of the proposed parameter selection is demonstrated empirically using several lowdimensional and highdimensional regression problems. Further, we point out the importance of Vapnik’s εinsensitive loss for regression problems with finite samples. To this end, we compare generalization performance of SVM regression (with optimally chosen ε) with regression using ‘leastmodulus ’ loss (ε =0). These comparisons indicate superior generalization performance of SVM regression, for finite sample settings.
The determinants of corporate board size and composition: An empirical analysis
 Journal of Financial Economics
, 2007
"... Several nonmutually exclusive theories have been proposed to explain how corporate boards are structured. In this paper we group these theories into three hypotheses and test them empirically. The first hypothesis is that boards are shaped by the scope and complexity of the organization they are de ..."
Abstract

Cited by 110 (0 self)
 Add to MetaCart
Several nonmutually exclusive theories have been proposed to explain how corporate boards are structured. In this paper we group these theories into three hypotheses and test them empirically. The first hypothesis is that boards are shaped by the scope and complexity of the organization they are designed to oversee. Consistent with this hypothesis, we find that board size and the fraction of independent outsiders are positively related to firm size, age, and diversification. The second hypothesis is that board composition is determined through negotiations between the CEO and outside board members. Consistent with this view, we find that the fraction of independent outsiders is negatively related to contemporaneous and lagged measures of the CEO's power. We also find support for the third hypothesis, which is that boards are shaped by the opportunities for private benefits and monitoring costs afforded by the firm's unique business environment. These results indicate that corporate boards adjust to the firm's specific advising and monitoring requirements, and undermine notions that onesizefitsall remedies can improve board and firm performance. *This paper is preliminary and incomplete. Please do not quote without the authors'