Analysis and Communication of US News Rankings using Monte Carlo Simulations II: An Update Presented by Chris Maxwell Purdue University AIR 2011.

Slides:



Advertisements
Similar presentations
Managerial Economics in a Global Economy
Advertisements

Objectives 10.1 Simple linear regression
General Linear Model Introduction to ANOVA.
Learning Math Through Wildlife Learning Math Through Wildlife Have you seen my MOOSE?
Regression Analysis Module 3. Regression Regression is the attempt to explain the variation in a dependent variable using the variation in independent.
A Short Introduction to Curve Fitting and Regression by Brad Morantz
Simple Linear Regression 1. Correlation indicates the magnitude and direction of the linear relationship between two variables. Linear Regression: variable.
Analysis and Communication of US News Rankings using Monte Carlo Simulations: A Comparison to Regression Modeling Presented by Chris Maxwell Purdue University.
CONFIDENCE INTERVALS HONORS ADVANCED ALGEBRA PRESENTATION 1-9.
Chapter 12 - Forecasting Forecasting is important in the business decision-making process in which a current choice or decision has future implications:
The Basics of Regression continued
Variability Measures of spread of scores range: highest - lowest standard deviation: average difference from mean variance: average squared difference.
Lecture 5 Curve fitting by iterative approaches MARINE QB III MARINE QB III Modelling Aquatic Rates In Natural Ecosystems BIOL471 © 2001 School of Biological.
Statistical Evaluation of Data
Educational Research by John W. Creswell. Copyright © 2002 by Pearson Education. All rights reserved. Slide 1 Chapter 8 Analyzing and Interpreting Quantitative.
PSY 307 – Statistics for the Behavioral Sciences Chapter 7 – Regression.
1 Chapter 17: Introduction to Regression. 2 Introduction to Linear Regression The Pearson correlation measures the degree to which a set of data points.
Chapter 9: Introduction to the t statistic
Simple Linear Regression Least squares line Interpreting coefficients Prediction Cautions The formal model Section 2.6, 9.1, 9.2 Professor Kari Lock Morgan.
Chapter 6 (cont.) Regression Estimation. Simple Linear Regression: review of least squares procedure 2.
Introduction to Linear Regression and Correlation Analysis
Elements of Multiple Regression Analysis: Two Independent Variables Yong Sept
Chapter 8 Introduction to Hypothesis Testing
EC339: Lecture 6 Chapter 5: Interpreting OLS Regression.
Linear Trend Lines Y t = b 0 + b 1 X t Where Y t is the dependent variable being forecasted X t is the independent variable being used to explain Y. In.
Montecarlo Simulation LAB NOV ECON Montecarlo Simulations Monte Carlo simulation is a method of analysis based on artificially recreating.
Statistics and Quantitative Analysis U4320 Segment 8 Prof. Sharyn O’Halloran.
Managerial Economics Demand Estimation. Scatter Diagram Regression Analysis.
Analyzing and Interpreting Quantitative Data
Regression Maarten Buis Outline Recap Estimation Goodness of Fit Goodness of Fit versus Effect Size transformation of variables and effect.
Algebra By : Monte. Term The number or an Expression that are added in a sum.
Multiple Regression The Basics. Multiple Regression (MR) Predicting one DV from a set of predictors, the DV should be interval/ratio or at least assumed.
© 2004 Prentice-Hall, Inc. Chapter 7 Demand Forecasting in a Supply Chain Supply Chain Management (2nd Edition) 7-1.
“WHY ARE PROJECTS ALWAYS LATE?” (“and what can the Project Manager DO about that?) Craig Henderson, MBA, PMP ARVEST Bank Operations.
Xuhua Xia Polynomial Regression A biologist is interested in the relationship between feeding time and body weight in the males of a mammalian species.
DAVIS AQUILANO CHASE PowerPoint Presentation by Charlie Cook F O U R T H E D I T I O N Forecasting © The McGraw-Hill Companies, Inc., 2003 chapter 9.
Center for Sustainable Transportation Infrastructure Harmonization of Friction Measuring Devices Using Robust Regression Methods Samer Katicha 09/09/2013.
Ch 6-1 © 2004 Pearson Education, Inc. Pearson Prentice Hall, Pearson Education, Upper Saddle River, NJ Ostwald and McLaren / Cost Analysis and Estimating.
Summary of introduced statistical terms and concepts mean Variance & standard deviation covariance & correlation Describes/measures average conditions.
1 Chapter 10: Introduction to Inference. 2 Inference Inference is the statistical process by which we use information collected from a sample to infer.
1 Everyday Statistics in Monte Carlo Shielding Calculations  One Key Statistics: ERROR, and why it can’t tell the whole story  Biased Sampling vs. Random.
Educ 200C Wed. Oct 3, Variation What is it? What does it look like in a data set?
Chapter 13 Multiple Regression
Chapter 11 Correlation and Simple Linear Regression Statistics for Business (Econ) 1.
Akram Bitar and Larry Manevitz Department of Computer Science
Chapter 6 (cont.) Difference Estimation. Recall the Regression Estimation Procedure 2.
Chapter 6: Analyzing and Interpreting Quantitative Data
Linear Prediction Correlation can be used to make predictions – Values on X can be used to predict values on Y – Stronger relationships between X and Y.
Regression Analysis Intro to OLS Linear Regression.
From the population to the sample The sampling distribution FETP India.
Intro to Statistics for the Behavioral Sciences PSYC 1900 Lecture 7: Regression.
Method 3: Least squares regression. Another method for finding the equation of a straight line which is fitted to data is known as the method of least-squares.
Term Project Math 1040-SU13-Intro to Stats SLCC McGrade-Group 4.
Chapter 4 Variability PowerPoint Lecture Slides Essentials of Statistics for the Behavioral Sciences Seventh Edition by Frederick J Gravetter and Larry.
Chapter 11 Linear Regression and Correlation. Explanatory and Response Variables are Numeric Relationship between the mean of the response variable and.
Correlation and Linear Regression
Linear Regression Special Topics.
Regression and Correlation
Regression Chapter 6 I Introduction to Regression
Regression.
Analyzing and Interpreting Quantitative Data
Maths Unit 9 – Forming & Solving Equations
LESSON 24: INFERENCES USING REGRESSION
Linear Regression and Correlation
15.1 The Role of Statistics in the Research Process
Linear Regression and Correlation
Algebra Review The equation of a straight line y = mx + b
Introduction to Regression
Regression and Correlation of Data
Akram Bitar and Larry Manevitz Department of Computer Science
Presentation transcript:

Analysis and Communication of US News Rankings using Monte Carlo Simulations II: An Update Presented by Chris Maxwell Purdue University AIR 2011

Presentation Overview Recap original Monte Carlo method Demonstrate the updated Monte Carlo method Review modeling results over multiple years and implications of US News methodology changes Questions/Discussion

Introduction What changes in submitted data most influence our US News rankings? Identify key data elements Provide realistic expectations of future rank This presentation will focus on the US News graduate program in education rankings Results will also be presented for graduate business and national universities rankings

Initial Analysis Use US News data from website and model the US News score with ordinary linear regression (OLS) OLS Problems: variable rejections, multicollinearity, counterintuitive results, model variability Models can be extremely accurate, but communication of results becomes very problematic Is there another way to model the score using the same data?

US News Methodology US news scores are z-score based: (observation - mean)/standard deviation In general, each institution’s z-scores are: multiplied by the US News weight totaled the highest total is scaled to 100 Not all calculation details are known and some data may be missing

Monte Carlo Simulation I Can a US News-type equation be simulated that calculates the US News scores? 18 unknowns, but 50 observations… A US News-type equation framework is input into an iterative Excel VBA program Reasonable ranges are defined for the 18 unknown standard deviations and “means”

Monte Carlo Simulation I (continued) For each iteration (~40,000) in a run: Randomly chose all unknowns Compute score for each institution Rescale so top score is100 Compute sum of squared errors The best-fit equation is saved, algebraically rearranged, and compared to regression Refine the model and repeat the process

Monte Carlo Simulation I: Issues A lot of unknowns, with the ranges for the population means especially hard to determine US News rescaling can keep the means in the simulated equations from having real world connections The means are also irrelevant to differences in scores between institutions It was decided to alter the Monte Carlo process to eliminate the means as unknowns

A Little Math… A regression of the Actual US News score as a function of the no means Monte Carlo result provides the needed Intercept and scaling factor

Year to Year Trends

* Updated Monte Carlo method (no means)

Summary Conclusions Cautions Questions / Discussion