Agriregionieuropa A CCOUNTING FOR MULTIPLE IMPACTS OF THE C OMMON A GRICULTURAL P OLICIES IN RURAL AREAS : AN ANALYSIS USING A B AYESIAN NETWORKS APPROACH.

Slides:



Advertisements
Similar presentations
Agriregionieuropa A regional analysis of CAP expenditure in Austria Wibke Strahl, Thomas Dax, Gerhard Hovorka Bundesanstalt fuer Bergbauernfragen, Vienna.
Advertisements

The Simple Linear Regression Model Specification and Estimation Hill et al Chs 3 and 4.
Autonomic Scaling of Cloud Computing Resources
Multiple Indicator Cluster Surveys Data Interpretation, Further Analysis and Dissemination Workshop Basic Concepts of Further Analysis.
A Tutorial on Learning with Bayesian Networks
1 Some Comments on Sebastiani et al Nature Genetics 37(4)2005.
How to measure the CMEF R2 Indicator about Gross Value Added in agricultural holdings without reliable accounting data ? A methodological proposal applied.
Managerial Economics Estimation of Demand
1 Knowledge Engineering for Bayesian Networks. 2 Probability theory for representing uncertainty l Assigns a numerical degree of belief between 0 and.
The IMAP Hybrid Method for Learning Gaussian Bayes Nets Oliver Schulte School of Computing Science Simon Fraser University Vancouver, Canada
Introduction of Probabilistic Reasoning and Bayesian Networks
Landbouweconomie, Coupure Links 653, 9000 Gent Sub-vector Efficiency Analysis in Chance Constrained Stochastic.
Agriregionieuropa A metafrontier approach to measuring technical efficiency The case of UK dairy farms Andrew Barnes*, Cesar Reverado-Giha*, Johannes Sauer+
Bayesian Networks Chapter 2 (Duda et al.) – Section 2.11
Parameterising Bayesian Networks: A Case Study in Ecological Risk Assessment Carmel A. Pollino Water Studies Centre Monash University Owen Woodberry, Ann.
Agriregionieuropa Farm level impact of rural development policy: a conditional difference in difference matching approach Salvioni C. 1 and Sciulli D.
Agriregionieuropa The “Rural-Sensitive Evaluation Model” for evaluation of local governments’ sensitivity to rural issues in Serbia Milic B. B.1, Bogdanov.
Agriregionieuropa The CAP and the EU budget Do ex-ante data tell the true? Franco Sotte Università Politecnica delle Marche – Ancona (Italy) 122 nd European.
Data Mining Techniques Outline
Regulatory Network (Part II) 11/05/07. Methods Linear –PCA (Raychaudhuri et al. 2000) –NIR (Gardner et al. 2003) Nonlinear –Bayesian network (Friedman.
Agriregionieuropa Methodological and practical solutions for the evaluation of the economic impact of RDP in Latvia M.oec. Armands Veveris Latvian University,
Learning with Bayesian Networks David Heckerman Presented by Colin Rickert.
Agriregionieuropa Mapping changes on agricultural and rural areas: an ex-post evaluation of the EU membership for Hungary Monasterolo, I., Pagliacci, F.
UNIVERSITY OF SOUTH CAROLINA Department of Computer Science and Engineering CSCE 580 Artificial Intelligence Ch.6 [P]: Reasoning Under Uncertainty Sections.
Agriregionieuropa An empirical analysis of the determinants of the Rural Development policy spending for Human Capital Beatrice Camaioni 1, Valentina Cristiana.
Modeling the efficiency of the agri-environmental payments to Czech agriculture in a CGE framework incorporating public goods approach Zuzana Křístková.
Data Mining CS 341, Spring 2007 Lecture 4: Data Mining Techniques (I)
Agriregionieuropa Dynamic adjustments in Dutch greenhouse sector due to environmental regulations Daphne Verreth 1, Grigorios Emvalomatis 1, Frank Bunte.
Agriregionieuropa Assessing the effect of the CAP on farm innovation adoption. An analysis in two French regions Bartolini Fabio 1 ; Latruffe Laure 2,3.
Agriregionieuropa The impact of pillar I support on farm choices: conceptual and methodological challenges Daniele Moro and Paolo Sckokai Università Cattolica,
Agriregionieuropa Evaluating the CAP Reform as a multiple treatment effect Evidence from Italian farms Roberto Esposti Department of Economics, Università.
Empirical validity of the evaluation of public policies: models of evaluation and quality of evidence. Marielle BERRIET-SOLLIEC 1, Pierre LABARTHE 2*,
Agriregionieuropa Closing session Few final considerations Giovanni Anania University of Calabria (Italy) & Spera 122 nd European Association of Agricultural.
Agriregionieuropa A minimum cross entropy model to generate disaggregated agricultural data at the local level António Xavier 1, Maria de Belém Martins.
1 Learning with Bayesian Networks Author: David Heckerman Presented by Yan Zhang April
Employment Decisions of European Women After Childbirth Chiara Pronzato (ISER) EPUNet Conference, May 9th 2006.
Agriregionieuropa Exploring the perspectives of a mixed case study approach for the evaluation of the EU Rural Development Policy Ida Terluin.
Agriregionieuropa Evaluating the Improvement of Quality of Life in Rural Areas Cagliero R., Cristiano S., Pierangeli F., Tarangioli S. Istituto Nazionale.
Statistics on enterprise groups – the EGR potential European Commission – Eurostat Directorate G: Global business statistics.
TENURE INSECURITY AND PROPERTY INVESTMENTS OF SMALLHOLDERS IN RURAL AND URBAN MOZAMBIQUE: EVIDENCE FROM TWO BASELINE SURVEYS Raul Pitoro, Songqing Jin,
Judgment and Decision Making in Information Systems Computing with Influence Diagrams and the PathFinder Project Yuval Shahar, M.D., Ph.D.
1 Prediction of Software Reliability Using Neural Network and Fuzzy Logic Professor David Rine Seminar Notes.
Serving society Stimulating innovation Supporting legislation Ex-ante assessment of the potential economic and environmental impacts.
Graphical Causal Models: Determining Causes from Observations William Marsh Risk Assessment and Decision Analysis (RADAR) Computer Science.
Income convergence prospects in Europe: Assessing the role of human capital dynamics Jesus Crespo Cuaresma Miroslava Luchava Havettová Martin Lábaj BRATISLAVA.
A Brief Introduction to Graphical Models
19 th ICABR Conference “IMPACTS OF THE BIOECONOMY ON AGRICULTURAL SUSTAINABILITY, THE ENVIRONMENT AND HUMAN HEALTH” Ravello : June , 2015 Bartolini.
“... providing timely, accurate, and useful statistics in service to U.S. agriculture.” Wendy Barboza, Darcy Miller, Nathan Cruze United States Department.
Off-farm labour participation of farmers and spouses Alessandro Corsi University of Turin.
73 rd EAAE Seminar Ancona, June rd EAAE Seminar Ancona, June rd EAAE Ancona, Franco Sotte Dipartimento di Economia Università.
Peter HinrichsEconomic Questions and Data Needs1 ELPEN. European Livestock Policy Evaluation Network.
第十讲 概率图模型导论 Chapter 10 Introduction to Probabilistic Graphical Models
THE IMPACTS OF THE EU SUBSIDIES ON THE PRODUCTION OF ORGANIC FARMS Marie Pechrová Czech University of Life Sciences Prague, Faculty of Ecoomics and Management.
Bayesian Networks for Data Mining David Heckerman Microsoft Research (Data Mining and Knowledge Discovery 1, (1997))
U.S. Department of the Interior U.S. Geological Survey.
CAPRI EC4MACS Kick Off meeting, Laxenburg, Peter Witzke, EuroCARE The role of EuroCARE and Bonn University in EC4MACS The role of EuroCARE.
Ch 8. Graphical Models Pattern Recognition and Machine Learning, C. M. Bishop, Revised by M.-O. Heo Summarized by J.W. Nam Biointelligence Laboratory,
METU Informatics Institute Min720 Pattern Classification with Bio-Medical Applications Lecture notes 9 Bayesian Belief Networks.
Spatial impacts and sustainability of farm biogas diffusion in Italy Oriana Gava, Fabio Bartolini and Gianluca Brunori 150th EAAE Seminar ‘The spatial.
Lecture 2: Statistical learning primer for biologists
Bayesian networks and their application in circuit reliability estimation Erin Taylor.
Learning and Acting with Bayes Nets Chapter 20.. Page 2 === A Network and a Training Data.
Bayesian Brain Probabilistic Approaches to Neural Coding 1.1 A Probability Primer Bayesian Brain Probabilistic Approaches to Neural Coding 1.1 A Probability.
Bayesian Networks Chapter 2 (Duda et al.) – Section 2.11 CS479/679 Pattern Recognition Dr. George Bebis.
Impact of agricultural innovation adoption: a meta-analysis
THE MACRO-MICRO APPROACH FOR THE EVALUATION OF PUBLIC POLICIES
Meredith L. Wilcox FIU, Department of Epidemiology/Biostatistics
Determining How Costs Behave
Propagation Algorithm in Bayesian Networks
THE MACRO-MICRO APPROACH FOR THE EVALUATION OF PUBLIC POLICIES
Presentation transcript:

agriregionieuropa A CCOUNTING FOR MULTIPLE IMPACTS OF THE C OMMON A GRICULTURAL P OLICIES IN RURAL AREAS : AN ANALYSIS USING A B AYESIAN NETWORKS APPROACH Sardonini L. 1, Viaggi D. 1 and Raggi M. 2 1 Department of Agricultural Economics and Engineering, University of Bologna, Italy 2 Department of Statistics, University of Bologna, Italy 122 nd European Association of Agricultural Economists Seminar Evidence-Based Agricultural and Rural Policy Making Methodological and Empirical Challenges of Policy Evaluation February 17 th – 18 th, 2011, Ancona (Italy) associazioneAlessandroBartola studi e ricerche di economia e di politica agraria Centro Studi Sulle Politiche Economiche, Rurali e Ambientali Università Politecnica delle Marche

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy)  Objective  Background  Methodology: Bayesian Networks (BNs)  Results from a farm/household survey in 9 EU countries  Discussion Outline

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Objective  Discuss the potential use of Bayesian Networks to represent the multiple determinants and impacts of CAP in rural areas across Europe: – Analysis of stated intention to farming in 9 EU countries (micro level data)

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Background 1/2 Tools for evaluating effects of CAP are wide and heterogeneous: − high number of drivers − high number of potential dimensions (economic, social and environmental issues) − complex behaviour

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Background 2/2 Problems due to the complexity of relationships: − non-linear − too many variables − correlations among explanatory variables − multiple variables outcome − missing data

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Bayesian Networks (BNs) Some application fields: – Artificial Intelligence (first field): NASA, NOKIA – Sociology: Rhodes 2007 – Medical diagnoses: Kahn et al – Environment: species conservation (Marcot et al. 2006), water (Zorrilla et al. 2010) – Land Use (Bacon et al. 2002)

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Bayesian Networks (BNs)  Simple and useful tools for modelling predictions and aiding resource managment decision making  Direct Acyclic Graph (DAG) where the nodes are random variables and the arcs represent direct connections between them (under conditional dependence assumptions)

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Bayesian Networks (BNs)  Example from Charniak 1996 Family-out Bowel problem Dog out Hear bark Light on outcome child node causal link Input parent nodes

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) BNs: advantages  Graphical construction interface  Incomplete database  Learn from data  Prior information  No linear relation  Could combine empirical data and expert judgement  Multiple outcomes

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) BNs: methodology  Assuming a set explanatory variables pa(x)  Computation of P(x i |pa(x))  Estimation using EM alghorithm: – Maximization of the log-likelihood – Iterative process – Update the posterior probability Bayes theorem

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Case study  Around 2000 farm-households interviews in 9 EU countries (telephone, face-to-face, postal)  European project CAP-IRE “Assessing the multiple Impacts of the Common Agricultural Policies (CAP) on Rural Economies”, 7th FP (SSH )  Questions about farm and household (social characteristics, structural aspects and future intentions )  Policy scenarios: – CAP after 2013, No-CAP after 2013

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) BNs: Application 1/2  Variables used in the network: – Current farm/household characteristics  Multiple outcomes in terms of: VariableLabel INTENTIONReaction to the hypothetical policy scenarios CHANGE_LEGAL_STATUSChanging in legal status PESTICIDESChanging in use of pesticides CHANGE_SELLOUTPUTSChanging who sells output LAND_OWNEDChanging in farm size (land owned) MACHINERYChanging in machinery endowment INNOVATION_01Adoption of at least one innovation CREDITChanging in use of credit HH_LAB_INChanging in household labour on farm

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) BNs: Application 2/2

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Net description  The causal relationships derive by WPs results and economic theory  INTENTION is a key node  Current characteristics influence the INTENTION and all the outcome nodes Outcome child nodesParent nodes INTENTION Cap, farm size, rent, income from farm, age, fulltime hh, country CHANGE_LEGAL_STATUSSFP per ha and advisory assistant PESTICIDESFarm size, specialization, SFP per ha, advisory assistant CHANGE_SELLOUTPUTSFarm size and innovation LAND_OWNEDFarm size, rent, altitude, SFP per ha, fulltime hh MACHINERYFarm size, rent, SFP per ha, fulltime hh, innovation INNOVATION_01SFP per ha, educational level, advisory assistant, age CREDITFarm size, SFP per ha, fulltime hh, rent, innovation HH_LAB_IN Educational level, fulltime hh, SFP per ha, specialization, income from farm, rent, innovation

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) BNs: Result (CPTs) Future stated plan to:  Adopt at least one INNOVATION_01: – young with a degree or old with high level of SFP and education  Increase the LAND_OWNED: – medium and medium-large farm size, rented-in already land and with at least two fulltime household members  Increase in MACHINERY: – increase in land and adopt at least one innovation  Increase in PESTICEDES: – livestock and mixed specialisation, SFP in the class 150-|500€ and increase the land  CHANGE_SELLOUTPUT – increase in land and adopt at least one innovation

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) BNs: Results Effect of scenario (Cap/No-Cap) – Exit frequency increases in No-Cap (from 21% to 30.6%) – The adoption of at least one innovation decreases in No-Cap (from 28.9% to 25.5%) – The increasing in land size decreases in No-Cap (from 19.2% to 17.2%) – The increasing in the fulltime household decreases in No-Cap (from to 18.1%)

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) BNs: Accurancy  Error rates: percentage of missclassified between observed and predicted VariableError rate Intention1.037% Land owned8.019% Innovation5.226% Pesticides18.05% Machinery14.85% Change_sell_output22.37% Change_legal status11.07% Credit24.19% Hh_lab_in10.33%

agriregionieuropa 122 nd EAAE Seminar, February 17 th – 18 th, 2011, Ancona (Italy) Discussion  Results – Coherence between the outcomes and the expectations – The older show a larger likelihood to quit farming activity – Good fit of the net in terms of low error rates  Further developments – Policy simulation: simulate the multiple outcomes from farming under different exogenous conditions

agriregionieuropa Thank for the attention