1 Risk in the MOLINO André de Palma UCP & Ecole Nationale des Ponts et Chaussée Lætitia Andrieu CERMICS-ENPC Nathalie Picard University of Cergy-Pontoise.

Slides:



Advertisements
Similar presentations
Copula Representation of Joint Risk Driver Distribution
Advertisements

VALUE AT RISK.
Value-at-Risk: A Risk Estimating Tool for Management
Chapter 25 Risk Assessment. Introduction Risk assessment is the evaluation of distributions of outcomes, with a focus on the worse that might happen.
Design of Experiments Lecture I
FIN 685: Risk Management Topic 6: VaR Larry Schrenk, Instructor.
Capital Budgeting. Cash Investment opportunity (real asset) FirmShareholder Investment opportunities (financial assets) InvestPay dividend to shareholders.
TK 6413 / TK 5413 : ISLAMIC RISK MANAGEMENT TOPIC 6: VALUE AT RISK (VaR) 1.
Applications of Stochastic Processes in Asset Price Modeling Preetam D’Souza.
Msci.com ©2011. All rights reserved. msci.com Reverse Stress Testing Ron Papanek.
VAR.
Introduction to Algorithmic Trading Strategies Lecture 8 Risk Management Haksun Li
Sensitivity and Scenario Analysis
©GoldSim Technology Group LLC., 2004 Probabilistic Simulation “Uncertainty is a sign of humility, and humility is just the ability or the willingness to.
RISK VALUATION. Risk can be valued using : Derivatives Valuation –Using valuation method –Value the gain Risk Management Valuation –Using statistical.
Value-at-Risk on a portfolio of Options, Futures and Equities Radhesh Agarwal (Ral13001) Shashank Agarwal (Sal13003) Sumit Jalan (Sjn13024)
Descriptive statistics Experiment  Data  Sample Statistics Experiment  Data  Sample Statistics Sample mean Sample mean Sample variance Sample variance.
Value at Risk (VAR) VAR is the maximum loss over a target
Market Risk VaR: Historical Simulation Approach
UNCLASSIFIED Schopenhauer's Proof For Software: Pessimistic Bias In the NOSTROMO Tool (U) Dan Strickland Dynetics Program Software Support
Demand Estimation & Forecasting
Chapter 14 Risk and Uncertainty Managerial Economics: Economic Tools for Today’s Decision Makers, 4/e By Paul Keat and Philip Young.
By: Brian Scott. Topics Defining a Stochastic Process Geometric Brownian Motion G.B.M. With Jump Diffusion G.B.M with jump diffusion when volatility is.
Lecture 11 Implementation Issues – Part 2. Monte Carlo Simulation An alternative approach to valuing embedded options is simulation Underlying model “simulates”
Computer Simulation A Laboratory to Evaluate “What-if” Questions.
© Harry Campbell & Richard Brown School of Economics The University of Queensland BENEFIT-COST ANALYSIS Financial and Economic Appraisal using Spreadsheets.
Value at Risk.
Ewa Lukasik - Jakub Lawik - Juan Mojica - Xiaodong Xu.
Advanced Risk Management I Lecture 6 Non-linear portfolios.
Practical analysis and valuation of heterogeneous telecom services Case-based analysis.
Alternative Measures of Risk. The Optimal Risk Measure Desirable Properties for Risk Measure A risk measure maps the whole distribution of one dollar.
Irwin/McGraw-Hill 1 Market Risk Chapter 10 Financial Institutions Management, 3/e By Anthony Saunders.
©2003 McGraw-Hill Companies Inc. All rights reserved Slides by Kenneth StantonMcGraw Hill / Irwin Chapter Market Risk.
The Oxford Guide to Financial Modeling by Ho & Lee Chapter 15. Risk Management The Oxford Guide to Financial Modeling Thomas S. Y. Ho and Sang Bin Lee.
LECTURE 22 VAR 1. Methods of calculating VAR (Cont.) Correlation method is conceptually simple and easy to apply; it only requires the mean returns and.
ENERGY AND SUSTAINABLE DEVELOPMENT Impact of the Oil Shocks: Transmission Channels and Models for Impact Evaluation Cristina Mocci Italian Ministry of.
Managerial Economics Demand Estimation & Forecasting.
Simulation is the process of studying the behavior of a real system by using a model that replicates the behavior of the system under different scenarios.
Actuarial Science Meets Financial Economics Buhlmann’s classifications of actuaries Actuaries of the first kind - Life Deterministic calculations Actuaries.
Market Risk VaR: Historical Simulation Approach N. Gershun.
Estimating Credit Exposure and Economic Capital Using Monte Carlo Simulation Ronald Lagnado Vice President, MKIRisk IPAM Conference on Financial Mathematics.
1 A non-Parametric Measure of Expected Shortfall (ES) By Kostas Giannopoulos UAE University.
Monté Carlo Simulation  Understand the concept of Monté Carlo Simulation  Learn how to use Monté Carlo Simulation to make good decisions  Learn how.
A Stochastic Model of CPP Liabilities – Preliminary Results Rick Egelton Chief Economist CPPIB October 27, 2007 The views in this presentation reflect.
FIN 614: Financial Management Larry Schrenk, Instructor.
Measurement of Market Risk. Market Risk Directional risk Relative value risk Price risk Liquidity risk Type of measurements –scenario analysis –statistical.
Copyright © 2005 by the McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Managerial Economics Thomas Maurice eighth edition Chapter 7.
© English Matthews Brockman Business Planning in Personal Lines using DFA A Talk by Mike Brockman and Karl Murphy 2001 Joint GIRO/CAS Conference.
 Measures the potential loss in value of a risky asset or portfolio over a defined period for a given confidence interval  For example: ◦ If the VaR.
Lotter Actuarial Partners 1 Pricing and Managing Derivative Risk Risk Measurement and Modeling Howard Zail, Partner AVW
An Reexamination of Jump Effect on Credit Spreads with Noisy Information Lung-fu Chang, Department of Finance, National Taipei College of Business.
Louisiana Department of Transportation and Development Forecasting Construction Cost Index Values Using Auto Regression Modeling Charles Nickel, P.E. Cost.
Lecture 3 Types of Probability Distributions Dr Peter Wheale.
Lecture 9 Cost of Capital Analysis Investment Analysis.
Chapter 12 – Single Investment Risk Analysis u Reasons for looking at risk from a single project prospective u lack comprehensive knowledge u of the rest.
COST BENEFIT ANALYSIS, DEVELOPMENT PLANNING AND THE EU COHESION FUND: LEARNING FROM EXPERIENCE Massimo Florio and Silvia Vignetti University of Milan and.
Applications of Stochastic Processes in Asset Price Modeling Preetam D’Souza.
Probabilistic Slope Stability Analysis with the
Supplementary Chapter B Optimization Models with Uncertainty
Value at Risk (VaR).
Types of risk Market risk
Market-Risk Measurement
Risk Mgt and the use of derivatives
Portfolio Risk Management : A Primer
Types of risk Market risk
Lecture Notes: Value at Risk (VAR)
Andrei Iulian Andreescu
VaR Introduction I: Parametric VaR Tom Mills FinPricing
Lecture Notes: Value at Risk (VAR)
Poverty and Social Impact Analysis: a User’s Guide – Economic tools
Presentation transcript:

1 Risk in the MOLINO André de Palma UCP & Ecole Nationale des Ponts et Chaussée Lætitia Andrieu CERMICS-ENPC Nathalie Picard University of Cergy-Pontoise (UCP) December 9, 2005

2

3 Two types of evaluations Socio-economic analysis Financial analysis

4 Motivation

5 Large-scale projects Large amount of failure of large projects: Suez canal, Eurotunnel Sources of uncertainty –Demand uncertainty –Supply uncertainty –Micro and macro shocks Risk (actual/perceived) is not well taken into account in current CBA: High risk should be associated with a high return: computation of financial /economical compensation (monetarization)?

6 Check-list # 1: sources of randomness Demand Production costs Industry structure and regulation Execution time Economic variables (macro-economic, regional) Financial variables Human resources for the management of the project

7 Check-list # 2: sources of randomness 1.Evaluation of secondary infrastructure 2.Accompanying measures 3.VOT, schedule delay costs 4.Value of external costs : accidents, human life, environment costs, etc. 5.Market: regulation, potential entry, etc.

8 Tools to take risk into account 1.Sensitivity analysis 2.Scenarios 3.Capital asset pricing model (CAPM) 4.Our suggestions – based on Monte-Carlo simulations (discussed later) - Confidence interval and - “Value at Risk” & “Conditional Value at Risk”

9 Empirical analysis Behavior towards risk and towards equity are interrelated A NR Online evaluation of risk with  Laboratory experiments about risk sharing Proposed: risk taking for decision maker: (in)formal interview

10 Practical issues Implementation A simple manner to incorporate risk in the MOLINO model

11 Cost variability Use (historical) data base on predicted costs and actual costs. Based on this information, determine the (pdf) probability density function of the cost functions.

12 Short run: travel time variability Deterministic case: demand depends on travel time, endogeneous but deterministic! If travel time varies from day to day (stationary process): assume a mean-variance model (CARA and normal distributions)  VOR (Small, 2005, Econometrica)

13 Medium long run: Demand variability Estimation of demand: where Y represents macroeconomics variables (growth of GNP, price of oil, etc.)  represents random shocks (opening of new markets, technological shock, etc.)

14 Variability of estimated demand Demand depends on parameters and macro variables estimated and predicted with more or less accuracy Autoregressive process, cumulated errors  Variance increases with time (e.g. linearly for Brownian motion)

15 Demand estimates over time t Demand

16 Micro-simulation (Monte Carlo) Generate sets of random parameters and demand values from a joint distribution allowing for correlations and fat tails (e.g. double exponential  extreme risks) Compute the distribution of relevant output variables (such as revenues, benefit, welfare, …) for each set of random parameters and demand values

17 Reminder: Value at risk: VaR Definition: maximum amount of lost acceptable for a project under “normal conditions” For example, if the VaR is 5 % for a critical value of q  = 100, this means that with a probability of 5 %, the cost will be larger than 100 for the time horizon considered

18 Micro-simulation (Results) 1.Eliminate the 2.5% larger values and 2.5% lower values to get a 95% bilateral confidence interval for each output variable 2.Select the  % worst cases to compute the Value at Risk  Implementation envisaged in the MOLINO model

19 Micro-simulation (Speed) Convergence requires about 7 iterations with an accuracy of Without Nash equilibrium, and with 10 origin- destination, this means about 14 hours, for iterations.

20 Questions