Empirical Modeling Process 1 - Identify Problem / Question 2 - Conceptualize model 3 - Collect data 4 - Examine and Summarize data 5 - Estimate model.

Slides:



Advertisements
Similar presentations
Lecture 10 F-tests in MLR (continued) Coefficients of Determination BMTRY 701 Biostatistical Methods II.
Advertisements

Chap 12-1 Statistics for Business and Economics, 6e © 2007 Pearson Education, Inc. Chapter 12 Simple Regression Statistics for Business and Economics 6.
Regression Analysis Simple Regression. y = mx + b y = a + bx.
Regression Analysis Once a linear relationship is defined, the independent variable can be used to forecast the dependent variable. Y ^ = bo + bX bo is.
Heteroskedasticity The Problem:
Multiple Regression [ Cross-Sectional Data ]
Valuation 4: Econometrics Why econometrics? What are the tasks? Specification and estimation Hypotheses testing Example study.
Classical Regression III
Chapter 13 Multiple Regression
LINEAR REGRESSION: Evaluating Regression Models. Overview Standard Error of the Estimate Goodness of Fit Coefficient of Determination Regression Coefficients.
Linear Regression.
Chapter 14 Introduction to Multiple Regression
Lecture 23: Tues., Dec. 2 Today: Thursday:
Chapter 12 Simple Regression
Chapter 12 Multiple Regression
Statistics for Business and Economics
Lecture 24: Thurs. Dec. 4 Extra sum of squares F-tests (10.3) R-squared statistic (10.4.1) Residual plots (11.2) Influential observations (11.3,
Basic Business Statistics, 11e © 2009 Prentice-Hall, Inc. Chap 14-1 Chapter 14 Introduction to Multiple Regression Basic Business Statistics 11 th Edition.
Summarizing Empirical Estimation EconS 451: Lecture #9 Transforming Variables to Improve Model Using Dummy / Indicator Variables Issues related to Model.
Economics 310 Lecture 7 Testing Linear Restrictions.
Chapter 4: Demand Estimation The estimation of a demand function using econometric techniques involves the following steps Identification of the variables.
Chapter 11 Multiple Regression.
Linear Regression Example Data
Ch. 14: The Multiple Regression Model building
Introduction to Regression Analysis, Chapter 13,
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 13-1 Chapter 13 Introduction to Multiple Regression Statistics for Managers.
Regression Analysis. Regression analysis Definition: Regression analysis is a statistical method for fitting an equation to a data set. It is used to.
Chapter 13: Inference in Regression
Regression Method.
© 2002 Prentice-Hall, Inc.Chap 14-1 Introduction to Multiple Regression Model.
Statistical Significance R.Raveendran. Heart rate (bpm) Mean ± SEM n In men ± In women ± The difference between means.
How do Lawyers Set fees?. Learning Objectives 1.Model i.e. “Story” or question 2.Multiple regression review 3.Omitted variables (our first failure of.
Statistics for Business and Economics Chapter 10 Simple Linear Regression.
Statistics for Business and Economics 7 th Edition Chapter 11 Simple Regression Copyright © 2010 Pearson Education, Inc. Publishing as Prentice Hall Ch.
Chapter 14 Introduction to Multiple Regression
Regression Examples. Gas Mileage 1993 SOURCES: Consumer Reports: The 1993 Cars - Annual Auto Issue (April 1993), Yonkers, NY: Consumers Union. PACE New.
Regression For the purposes of this class: –Does Y depend on X? –Does a change in X cause a change in Y? –Can Y be predicted from X? Y= mX + b Predicted.
© 2001 Prentice-Hall, Inc. Statistics for Business and Economics Simple Linear Regression Chapter 10.
Chap 14-1 Statistics for Business and Economics, 6e © 2007 Pearson Education, Inc. Chapter 14 Additional Topics in Regression Analysis Statistics for Business.
Welcome to Econ 420 Applied Regression Analysis Study Guide Week Six.
Chapter 11 Linear Regression Straight Lines, Least-Squares and More Chapter 11A Can you pick out the straight lines and find the least-square?
Chap 14-1 Copyright ©2012 Pearson Education, Inc. publishing as Prentice Hall Chap 14-1 Chapter 14 Introduction to Multiple Regression Basic Business Statistics.
Part 2: Model and Inference 2-1/49 Regression Models Professor William Greene Stern School of Business IOMS Department Department of Economics.
6-1 Introduction To Empirical Models Based on the scatter diagram, it is probably reasonable to assume that the mean of the random variable Y is.
Statistics for Business and Economics 8 th Edition Chapter 11 Simple Regression Copyright © 2013 Pearson Education, Inc. Publishing as Prentice Hall Ch.
Discussion of time series and panel models
Lecture 11 Preview: Hypothesis Testing and the Wald Test Wald Test Let Statistical Software Do the Work Testing the Significance of the “Entire” Model.
Multiple Regression. Simple Regression in detail Y i = β o + β 1 x i + ε i Where Y => Dependent variable X => Independent variable β o => Model parameter.
Environmental Modeling Basic Testing Methods - Statistics III.
Multiple Regression I 1 Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc. Chapter 4 Multiple Regression Analysis (Part 1) Terry Dielman.
Copyright ©2011 Pearson Education, Inc. publishing as Prentice Hall 14-1 Chapter 14 Introduction to Multiple Regression Statistics for Managers using Microsoft.
MEASURES OF GOODNESS OF FIT The sum of the squares of the actual values of Y (TSS: total sum of squares) could be decomposed into the sum of the squares.
Basic Business Statistics, 10e © 2006 Prentice-Hall, Inc.. Chap 14-1 Chapter 14 Introduction to Multiple Regression Basic Business Statistics 10 th Edition.
The Assessment of Improved Water Sources Across the Globe By Philisile Dube.
Introduction to Multiple Regression Lecture 11. The Multiple Regression Model Idea: Examine the linear relationship between 1 dependent (Y) & 2 or more.
Multiple Regression Learning Objectives n Explain the Linear Multiple Regression Model n Interpret Linear Multiple Regression Computer Output n Test.
Statistics for Managers Using Microsoft Excel, 5e © 2008 Prentice-Hall, Inc.Chap 14-1 Statistics for Managers Using Microsoft® Excel 5th Edition Chapter.
Lecturer: Ing. Martina Hanová, PhD. Business Modeling.
Predicting Energy Consumption in Buildings using Multiple Linear Regression Introduction Linear regression is used to model energy consumption in buildings.
Chapter 20 Linear and Multiple Regression
Correlation and Simple Linear Regression
Prediction and Prediction Intervals
24/02/11 Tutorial 3 Inferential Statistics, Statistical Modelling & Survey Methods (BS2506) Pairach Piboonrungroj (Champ)
Correlation and Simple Linear Regression
Statistical Inference about Regression
Full Model: contain ALL coefficients of interest
BEC 30325: MANAGERIAL ECONOMICS
BEC 30325: MANAGERIAL ECONOMICS
Introduction to Regression
Adding variables. There is a difference between assessing the statistical significance of a variable acting alone and a variable being added to a model.
Presentation transcript:

Empirical Modeling Process 1 - Identify Problem / Question 2 - Conceptualize model 3 - Collect data 4 - Examine and Summarize data 5 - Estimate model 6 - Examine model performance 7 - Revise model as needed

Demand Curve Price Quantity

Price: Deflated Constant Dollar Price Quantity: Per Capita Consumption

Mathematical Conceptual Model: Model 1 TP = b 0 + b 1 TQ + e Where: TP= real quarterly retail turkey price (cents/lb.) TQ=quarterly per capita turkey consumption (lbs./capita) b 0, b 1 are parameters to be estimated e is an error term

Turkey Demand Curve TP TQ b0b0 b1b1 TP = b 0 + b 1 TQ

Objective: To quantify determinants of quarterly retail price of Turkey over Estimate the demand curve

Empirical Modeling Process 1 - Identify Problem / Question 2 - Conceptualize model 3 - Collect data 4 - Examine and Summarize data 5 - Estimate model 6 - Examine model performance 7 - Revise model as needed

Empirical Modeling Process 1 - Identify Problem / Question 2 - Conceptualize model 3 - Collect data 4 - Examine and Summarize data 5 - Estimate model 6 - Examine model performance 7 - Revise model as needed

Summary Statistics of Quarterly Real Turkey Price and Per Capita Turkey Consumption,

Goodness of Fit Measures

Residual Summary

Parameter Estimates

Model 1 Regression Estimates: TP = – TQ (0.00) (0.00) p-values Adj. R-Sq.=0.33 RMSE=29.35 cents/lb. Observations=116

Turkey Demand Curve TP TQ TP = – TQ

Diagnostic Testing of Regression 1. Predicted vs. Actual Graph 2. Graphical analysis of residuals

Predicted TP = – TQ Residual = TP – Predicted TP Predicted Values & Residuals (Errors)

Performance Summary Model 1 Adj. R-square only 0.33 RMSE = cents/lb (std dev TP=35.8) Sign on coefficient is as expected TQ is statistically significant Not predicting well We suspect we have left out some relevant important factors (omitted relevant variable problem)

Empirical Modeling Process 1 - Identify Problem / Question 2 - Conceptualize model 3 - Collect data 4 - Examine and Summarize data 5 - Estimate model 6 - Examine model performance 7 - Revise model as needed

Mathematical Conceptual Model Model 2 TP = b 0 + b 1 TQ + b 2 BfQ + b 3 PkQ + b 4 ChQ + b 5 INC + e Where: TP and TQ are as defined in model 1, BfQ, PkQ, ChQ quarterly beef, pork and chicken consumption (lbs./capita) INC = real disposable income ($/capita)

Mathematical Conceptual Model Model 2 TP = b 0 + b 1 TQ + b 2 BfQ + b 3 PkQ + b 4 ChQ + b 5 INC + e Sign Expectations: b 1 b 2 b 3 b 4 b 5

Summary Statistics of Data Used to Explain Quarterly Real Turkey Price,

Performance Summary of Model 2 Adj. R-square 0.94 better than twice 1 RMSE = 8.68 cents/lb less than 1 / 3 of 1 BfQ & PkQ unexpected signs & statistically significant Appears to be seasonality not accounted for in other regressors

Mathematical Conceptual Model Model 3 Seasonality Adjustment TP = b 0 + b 1 TQ + b 2 BfQ + b 3 PkQ + b 4 ChQ + b 5 INC + b 6 Q1Dum + b 7 Q2Dum + b 8 Q3Dum + e Where: Q1Dum = 1 in qtr 1 and 0 otherwise Q2Dum = 1 in qtr 2 and 0 otherwise Q3Dum = 1 in qtr 3 and 0 otherwise

Dummy variables in spreadsheet YearQtr Q1Dum Q2Dum Q3Dum Q4Dum etc.... Drop one dummy variable column when estimate regression

Performance Summary of model 3 Adj. R-square 0.94 comparable to 2 RMSE = 8.46 cents/lb bit less than 2 Signs on coeff. ok except BfQ & PkQ See what happens when we drop BfQ

Mathematical Conceptual Model Model 4 TP = b 0 + b 1 TQ + b 2 BfQ + b 3 PkQ + b 4 ChQ + b 5 INC + b 6 Q1Dum + b 7 Q2Dum + b 8 Q3Dum + e or TP = b 0 + b 1 TQ + b 2 PkQ + b 3 ChQ +b 4 INC + b 5 Q1Dum + b 6 Q2Dum + b 7 Q3Dum + e

Performance Summary of model 4 Adj. R-square 0.94, about as high as any other RMSE = 8.85 cents/lb bit more than 3 Signs on coeff. o.k. except pork Pork marginally statistically significant Income not close to statistically significant All rest are significant What do you think????

Testing Between Models We use an F-test to statistically compare two NESTED models. Nested models are those in which one is a subset of the other and both models have same dependent variable and were estimated over same time period.

Nested vs Nonnested Models Model 1 TP = f (TQ) Model 2 TP = f (TQ, BfQ, PkQ, ChQ, INC) Model 3 TP = f (TQ, BfQ, PkQ, ChQ, INC, Q1D, Q2D, Q3D) Model 4 TP = f (TQ, PkQ, ChQ, INC, Q1D, Q2D, Q3D) Nested Model pairs: 1 is nested in 2; 2 is nested in 3; 4 is nested in 3; 1 is nested in 4, etc.

Testing Between Models 2 and 3 Model 2 TP = f (TQ, BfQ, PkQ, ChQ, INC) Model 3 TP = f (TQ, BfQ, PkQ, ChQ, INC, Q1D, Q2D, Q3D) Null Hypothesis:Alternative Hypothesis: H o : b 6 =b 7 =b 8 =0Not H o Use an F-test to test this hypothesis.

F - Test: (SSRr- SSRf ) / (q) (SSRf / DFf) Where: SSR r is the sum of squared residuals from reduced or smaller model SSR f is the sum of squared residuals from full or bigger model q is the number of restrictions DF f is the degrees of freedom full model F =

F - Test Criteria: (SSRr - SSRf ) / (q) (SSR f / DF f ) Compare to critical F-table value of F (q, DF f, alpha) or F(v 1, v 2, 0.05). If F > F(q, DF f, 0.05) then reject null and conclude that full model is better than reduced model F =

Testing Between Models 2 and 3: Null Hypothesis:Alternative Hypothesis H o : b 6 =b 7 =b 8 =0Not H o F = (8,295.5 – 7,664.4) / 3 (7,664.4 / 107 ) =2.94 F (3, 107, 0.05) = ~2.70 Conclusion: Reject H o, 95% certain model 3 is better, i.e., seasonal variables significant

Summary of Regression Performance R-square RMSE Signs on parameters correct? Statistical Significance of Parameters? Comparison between models Economic logic consistency Economic importance of estimates

Summary of Regression Challenges Conceptual model wrong Fail to include important variable(s) Patterns in residuals Omitted Relevant Variables Spurious relationships? other problems…..