World Commodity Prices and Domestic Retail Food Price Inflation: Some Insights from the UK

We focus on two aspects of the links between world commodity prices and retail food price inflation: first, the effects of exchange rates and other input costs, and second; the effects of the duration of shocks on world commodity markets, not just the magnitude of price spikes (the latter often commanding most attention). The UK offers a natural and rather unexplored setting for the analysis. Applying time series methods to a sample of 259 monthly observations over the 1990(9)–2012(3) period we find substantial and significant long‐term partial elasticities for domestic food price inflation with respect to world food commodity prices, the exchange rate and oil prices (the latter indirectly via a relationship with world food commodity prices). Domestic demand pressures and food chain costs are found to be less substantial and significant over our data period. Interactions between the main driving variables in the system tend to moderate rather than exacerbate these partial effects. Furthermore, the persistence of shocks to these variables markedly affects their effects on domestic food prices.     

基于机器学习方法的城市社区尺度商铺租金空间布局分析

研究目的：通过引入机器学习方法,利用地理时空大数据研究精细尺度的商铺租金分布,以弥补传统基于计量模型的租金分析中样本量不足、要素量化方式主观、模型形式僵化等问题。研究方法：研究利用网络爬虫技术获取相关时空大数据,随后采用密度制图、空间句法分析等量化相关指标,并通过LASSO模型筛选影响因子,最后采用机器学习方法对社区尺度商铺租金进行空间布局分析。研究结果：基于机器学习方法的广州市中心城区社区尺度商铺租金布局分析能较好拟合估计值和观测值,其分析结果显示广州市中心城区中荔湾区、越秀区、天河区和海珠区各自形成了成熟的高租金核心,商铺租金从高值区域向外逐渐下降。研究结论：该研究方法可以应用于房租、房价空间分布估计等领域,研究成果可作为基准地价更新、城市异值空间发现等的参考。     

A copula‐based approach to the simultaneous estimation of group and meta‐frontiers by constrained maximum likelihood

Existing approaches to the meta‐frontier estimation consist of two stages where the estimates of the local frontier parameters obtained in the first step are used to estimate meta‐frontier parameters by means of a linear or quadratic minimisation procedure in the second. Since it was shown by Schmidt (Review of Economics and Statistics 58: 238) that the second step is equivalent to constrained maximisation of a likelihood function, we extend this idea and offer a copula‐based approach to the estimation of the parameters of both meta‐ and group frontiers in a one‐step setting. In this way, we ensure a single data‐generating mechanism for the estimated parameters, expand the set of potential meta‐frontiers and account for the fact that shocks to the individual production units may be correlated with shocks to the local technological environment as a whole. We apply our estimation methodology to a data set on the world agriculture and find that the deviations from the group frontiers are positively correlated with deviations from the meta‐frontier, which is a conclusion that is impossible to reach without accounting for stochastic dependence between the two deviation types represented by a copula.     

Social learning and technology adoption: the case of coffee pruning in Peru

A unique natural experiment involving a coffee pruning technology is used to study social learning. The yield effects of pruning take two years to appear, a characteristic that aids in identifying social learning apart from correlated unobservable variables that are a concern in the social learning and technology adoption literature. Panel data are employed that start with a private initiative which introduced systematic pruning in central Peru and that contain the population of participating growers. Results show a jump of at least 0.15 in the probability of adoption two years after the first pruning in a grower's group.     

Ranking efficiency units in DEA using bootstrapping an applied analysis for Slovenian farm data

This article explores how data envelopment analysis (DEA), along with a smoothed bootstrap method, can be used in applied analysis to obtain more reliable efficiency rankings for farms. The main focus is the smoothed homogeneous bootstrap procedure introduced by Simar and Wilson (1998) to implement statistical inference for the original efficiency point estimates. Two main model specifications, constant and variable returns to scale, are investigated along with various choices regarding data aggregation. The coefficient of separation (CoS), a statistic that indicates the degree of statistical differentiation within the sample, is used to demonstrate the findings. The CoS suggests a substantive dependency of the results on the methodology and assumptions employed. Accordingly, some observations are made on how to conduct DEA in order to get more reliable efficiency rankings, depending on the purpose for which they are to be used. In addition, attention is drawn to the ability of the SLICE MODEL, implemented in GAMS, to enable researchers to overcome the computational burdens of conducting DEA (with bootstrapping).     

Socio-economic and biophysical determinants of land degradation in Vietnam: An integrated causal analysis at the national level

Recognizing the socio-economic and biophysical causes of land degradation at the national level is important for cause-targeted strategies when designing policies for combating land degradation. This study aims to identify the biophysical and socio-economic factors that significantly affect land degradation across Vietnam and to interpret the causalities underlying the effects. The dependent variables considered in the study are spatial, the extent and intensity of degradation in three land-use zones (agriculture, forest and severely degraded abandonment). The hypothesized explanatory variables are common economic and demographic drivers and bio-physical factors such as soil, terrain constraints, and neighborhood land-use structures that are often neglected in many large-scale land degradation assessments. Instead of using a single inferential statistic technique, we used multi-linear regression and binary logistic regression in a complementary manner to increase the detectability and credibility of the degradation cause analyses. The results showed agricultural production growth had strong and consistent effects on land degradation extent and intensity. Population growth, especially in rural areas, had a strong effect on the extent of overall land degradation. The importance of a neighboring forest was revealed for its ability to reduce land degradation intensity in abandoned, unproductive lands. The concrete faceting of the causal analysis for each land-use zone as social–ecological stratum allowed us to combine the defined social–ecological contexts, contemporary theories, and hypotheses in the field to clarify the causal factors of a complex phenomenon like land degradation. The study demonstrates these contemporary inferential statistics can be complementarily used to sufficiently detect and understand land degradation causes at the national level. The results suggest implications for national land management policy: internalizing land degradation costs in the farming system evaluation for payment for ecosystem services policy, restricting forest conversion, and improving extension services and education in agrarian communities.     

Relationships between Technical Efficiency and Financial Management for Czech Republic Farms

This paper provides the first analysis of the relationship between farm financial structure and technical efficiency in Central and Eastern European farming during the transition to a market economy. First, technical efficiency scores for a sample of Czech farms are computed with data envelopment analysis, accounting for sampling variability by using the Simar and Wilson bootstrapping procedure. The confidence intervals show that corporate livestock farms are the most homogenous in terms of technical efficiency. Second, a Tobit model is applied for the investigation of factors, including financial considerations, which influence the variation in technical efficiency. The potential endogeneity of the financial variables in the explanation of efficiency is examined, following Smith and Blundell. The Amemiya estimator is used for those cases which are revealed as endogenous. The analysis indicates substantial differences in the way in which the different management structures are treated by lenders. De novo, individual farms are subject to stringent evaluation of their loan applications, which is not the case for the successors of the former collective and state farms.     

Capturing household-level spatial influence in agricultural management using random effects regression

Data on agricultural and natural resource management typically have spatial patterns related to the landscapes from which they came. Consequently, econometric models designed to explain the determinants of humans' natural resource management practices or their outcomes often have spatial structure that can bring bias or inefficiency to parameter estimates. Although econometric tools are available to correct for spatial structure, such tools are largely lacking for use with discrete dependent variable models. While one obvious solution would be to develop the necessary tools, an alternative is to identify conditions under which spatial dependency can be managed effectively without formal spatial autoregressive models. This study examines conditions under which spatial structure corresponds closely to defined agro‐ecological zones, making it possible to model spatial effects by random effects regression. Using household survey data sampled along agro‐ecological zone strata, this article develops two models of links between farmer assets and agricultural natural resource degradation in southern Peru. The first stage model looks at determinants of crop yield loss over time (an index of soil productivity), while the second stage model looks at determinants of the extent of fallow cycles in crop rotation, a key agricultural practice reducing crop yield loss. Diagnostic statistics for spatial dependency reveal spatial structure, particularly in the fallow model. This spatial dependency is eliminated in the ordinary least squares (OLS) models by inclusion of the agro‐ecological zone random effects. In the spatially dependent fallow model, comparison of coefficient estimates between OLS and the spatial autoregressive maximum likelihood models showed OLS with random effects to give virtually identical results to the spatial autoregressive models, making the latter unnecessary. These results show that spatial structure in natural resource management models can sometimes be captured by zonal variables. When this occurs, random effects regression can largely eliminate spatial dependency. A necessary precondition for this approach with household survey data is prior sample stratification according to landscape characteristics. Where random effects models can effectively capture spatial structure, they may also offer analysts greater flexibility in analyzing models with limited dependent variables.     

A contribution to the assessment of scenic quality of landscapes based on preferences expressed by the public

The purpose of this paper is to validate a model for predicting the public's preference for a landscape using simple statistical techniques. The model assigns numerical values to 42 landscape variables grouped into physical, aesthetic and psychological attributes. The landscape value is obtained using an additive value function. The results of the model on certain landscapes are compared with the preference expressed by the public in a survey of 183 people.The homogeneity of the survey responses was checked in each photograph. It was determined that means and standard deviations of the scores represent the true preference.A strong positive association was observed between preference and certain landscape attributes such as expression, soil use or colour. A marked negative association was detected with respect to landscape alterations.A linear regression was carried out to analyse the predictive capacity of the model. The independent variable was the global score assigned by the model to each photograph and the dependant variable was the mean of the scores assigned by the survey respondents. The high level of correlation obtained indicates that the model is a good predictor of the public's preferences in relation to the set of photographs shown in the survey.To complete the analysis of the model as a preference predictor, a multiple linear regression was carried out between the mean score obtained in the survey and the model elements. Attributes and variables that have the greatest influence on pubic preference were detected.     

Analyzing driving factors of land values in urban scale based on big data and non-linear machine learning techniques

Land value plays a vital role in the real estate market. It is a critical reference for urban planners to reallocate land resources and introduce valid policies. Studying the influential factors on land value can help better understand the spatial-temporal variation of land values and design effective control policies. This attracted a number of scholars to study the spatial and temporal relationships between land value and its possible influential factors from the perspective of macro and micro. However, the majority of the existing studies have the problems of linear assumption and multicollinearity in research models. Limited features and the lack of feature selection procedure are another two commonly seen limitations. To overcome the gaps, this paper adopts non-linear machine learning (ML) methods to investigate the influential factors on land values per square foot based on “big data” in New York City. More than one thousand potential factors are considered, covering from the land attribute, point of interest, demographics, housing, to economic, education, and social. They are further selected using a feature extraction model named Recursive Feature Elimination (RFE). Six ML algorithms, including Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Multi Linear Regression (MLR), Linear Support Vector Regression (SVR), Multilayer Perceptron (MLP) Regression, and K-Nearest Neighbor (KNN) Regression are evaluated and compared. The optimal one with an R-square value of 0.933 is used to calculate the feature importance further. Several important impact features are disclosed, including the number of newsstands, and the vacant housing percentage.     

基于支持向量机的小型水库风险等级模型研究

根据小型水库现状,研究得到小型水库安全风险的主要影响因子。在此基础上,利用机器学习方法,建立小型水库安全风险等级评价模型。通过实例分析,验证了模型的正确性和适用性。研究表明,基于支持向量机的小型水库安全风险等级评估在小水库安全风险识别上具有一定的适用性,能够有效解决小型水库安全风险等级评价中存在的数据样本较少的问题,该研究成果可以为小型水库下游区域山洪预警提供新的思路。     

多元回归分析法下森林资源资产批量评估模型研究——陕西省宁陕县实证案例

以宁陕县134个森林资源资产交易案例为基础,运用多元线性回归分析方法,建立森林资源资产批量评估模型。首先深入分析影响森林资源资产单位评估值的特征因素,确定模型的自变量和因变量;然后利用SPSS软件对样本数据进行分析,检验各变量的正态性和线性关系,把通过检验的变量引入模型;在求出模型中各变量系数后,进行残差分析,确保模型通过正态性、共方差性和独立性的假设检验;最后,利用测试样本对模型的有效性和预测精度进行验证。     

A revised Tobit procedure for mitigating bias in the presence of non-zero censoring with an application to milk-market participation in the Ethiopian highlands

Fixed transactions costs that prohibit exchange engender bias in supply analysis due to censoring of the sample observations. The associated bias in conventional regression procedures applied to censored data and the construction of robust methods for mitigating bias have been preoccupations of applied economists since Tobin [Econometrica 26 (1958) 24]. This literature assumes that the true point of censoring in the data is zero and, when this is not the case, imparts a bias to parameter estimates of the censored regression model. We conjecture that this bias can be significant; affirm this from experiments; and suggest techniques for mitigating this bias using Bayesian procedures. The bias-mitigating procedures are based on modifications of the key step that facilitates Bayesian estimation of the censored regression model; are easy to implement; work well in both small and large samples; and lead to significantly improved inference in the censored regression model. These findings are important in light of the widespread use of the zero-censored Tobit regression and we investigate their consequences using data on milk-market participation in the Ethiopian highlands.     

Ownership,autonomy, incentives and efficiency: Evidence from the forest product processing industry in China

Using enterprise-level data from China's Northeast-Inner Mongolia state-owned forest area for the year 2004, this paper investigates the technical efficiency of forest product processing mills and the relationship between institutional and managerial practices and efficiency. A two-stage procedure proposed by Simar and Wilson (2007) is adopted. In the first stage, a bootstrapped data envelopment analysis (DEA) model is used to compute the efficiency scores. In the second stage, the bootstrapped DEA scores are estimated over a set of mills’ institutional and managerial systems and other characteristics with a bootstrapped truncated regression. The results show that there is a wide dispersion in the technical efficiency among mills. Private ownership, autonomy and mill size have statistically significant positive impacts on efficiency. These results provide support for the ongoing reform and implications for future development of this area.     

节水潜力预测研究综述

系统整理并分析了不同领域节水潜力预测方法的分类、原理、适用范围及研究现状,帮助从业人员针对实际问题快速选择模型。分析认为,基于公式模型的节水潜力预测方法收集数据较少,操作简捷,使用范围较广,但精确性不高;基于机器学习的节水潜力预测方法虽然收集的数据种类和数量较多,但构造出的预测模型使用范围广,精度高。针对节水潜力预测的现存问题,总结分析了其发展趋势。未来节水潜力预测的研究应根据不同产业和地域特点,引入深度学习、大数据等新技术,实现精细化节水潜力预测;同时加快完善基于互联网的节水潜力预测应用,实现集成数据收集、处理、预测、发布等功能于一体的节水社会化服务。     

Under the hood Issues in the specification and interpretation of spatial regression models

This paper reviews a number of conceptual issues pertaining to the implementation of an explicit “spatial” perspective in applied econometrics. It provides an overview of the motivation for including spatial effects in regression models, both from a theory‐driven as well as from a data‐driven perspective. Considerable attention is paid to the inferential framework necessary to carry out estimation and testing and the different assumptions, constraints and implications embedded in the various specifications available in the literature. The review combines insights from the traditional spatial econometrics literature as well as from geostatistics, biostatistics and medical image analysis.     

Bringing automated,remote‐sensed,machine learning methods to monitoring crop landscapes at scale

This article provides an overview of how recent advances in machine learning and the availability of data from earth observing satellites can dramatically improve our ability to automatically map croplands over long periods and over large regions. It discusses three applications in the domain of crop monitoring where machine learning (ML) approaches are beginning to show great promise. For each application, it highlights machine learning challenges, proposed approaches, and recent results. The article concludes with discussion of major challenges that need to be addressed before ML approaches will reach their full potential for this problem of great societal relevance.     

Assessing the Contribution of Attitudinal Variables in International Models of Food Consumption

Abstract

This study compares the predictive ability of attitudinal variables with that of demographic variables in an international context. Using hierarchical regression analysis, the contribution of attitudinal variables to five models of food purchase behavior in urban China is evaluated. The results of the study indicate that, in some circumstances, multinational firms might opt to omit attitudinal measures in international consumer studies. Analysis of variance techniques are then used to examine the relationship between key demographic variables and food purchase behaviors.     

Assessing multiple approaches for modelling land-use conflict potential from participatory mapping data

Spatial social data collected through participatory mapping are increasingly used to assess social dimensions for land use planning and management. However, there has been limited research to evaluate alternative approaches to identify potential land-use conflict. Using data from Queensland, Australia, we applied multiple approaches (land-use preferences, weighted preferences, combined place values and land-use preferences, and value compatibility scoring to identify land-use conflict potential and to assess these methods for four different land uses (residential development, tourism development, mining, and conservation). The performance of these approaches were evaluated using selected reference sites in the study area to determine which spatial attributes and methods were most predictive of conflict potential. Weighted preferences, and combined place values and land-use preferences were most effective for all land use types. The conflict mapping results for mining and conservation were sensitive to the number of place value and land-use preference points available for analysis and the number of individuals participating in the mapping process. To determine the inferential quality of conflict mapping results, we operationalised confidence levels based on the number of unique participants that mapped preferences in a given location. Overall, the highest confidence in mapped results was observed for tourism development, followed by mining, conservation, and residential development. Confidence levels varied across the study area and by reference sites. The findings of this study increase the external validity of preference-based conflict mapping methods while demonstrating a means to assess the inferential quality of conflict mapping results. The generation of confidence levels can assist in the prioritization and allocation of planning resources to places with both high conflict potential and high confidence.