Best in Market Pricing. What is Best in Market Pricing ? An extension of parametric modeling for negotiating lowest pricing for a statement of work consisting.

Slides:



Advertisements
Similar presentations
Sampling: Final and Initial Sample Size Determination
Advertisements

Chap 8-1 Statistics for Business and Economics, 6e © 2007 Pearson Education, Inc. Chapter 8 Estimation: Single Population Statistics for Business and Economics.
QUANTITATIVE DATA ANALYSIS
Chapter 12 Simple Regression
Basic Business Statistics, 10e © 2006 Prentice-Hall, Inc. Chap 8-1 Chapter 8 Confidence Interval Estimation Basic Business Statistics 10 th Edition.
SIMPLE LINEAR REGRESSION
Chapter Topics Types of Regression Models
Chapter 8 Estimation: Single Population
Chapter 3 Hypothesis Testing. Curriculum Object Specified the problem based the form of hypothesis Student can arrange for hypothesis step Analyze a problem.
AP Statistics Section 10.2 A CI for Population Mean When is Unknown.
Chapter 10, sections 1 and 4 Two-sample Hypothesis Testing Test hypotheses for the difference between two independent population means ( standard deviations.
Today Concepts underlying inferential statistics
1 BA 555 Practical Business Analysis Review of Statistics Confidence Interval Estimation Hypothesis Testing Linear Regression Analysis Introduction Case.
Business Statistics, A First Course (4e) © 2006 Prentice-Hall, Inc. Chap 8-1 Chapter 8 Confidence Interval Estimation Business Statistics, A First Course.
Statistics for Managers Using Microsoft® Excel 7th Edition
ECONOMETRICS I CHAPTER 5: TWO-VARIABLE REGRESSION: INTERVAL ESTIMATION AND HYPOTHESIS TESTING Textbook: Damodar N. Gujarati (2004) Basic Econometrics,
AM Recitation 2/10/11.
Copyright © 2013, 2009, and 2007, Pearson Education, Inc. Chapter 12 Analyzing the Association Between Quantitative Variables: Regression Analysis Section.
Statistical inference: confidence intervals and hypothesis testing.
Linear Regression Inference
©2010 Prentice Hall Business Publishing, Auditing 13/e, Arens//Elder/Beasley Audit Sampling for Tests of Details of Balances Chapter 17.
©2012 Pearson Education, Auditing 14/e, Arens/Elder/Beasley Audit Sampling for Tests of Details of Balances Chapter 17.
1 Least squares procedure Inference for least squares lines Simple Linear Regression.
Fundamentals of Data Analysis Lecture 4 Testing of statistical hypotheses.
Confidence Interval Estimation
Chapter 9 Hypothesis Testing and Estimation for Two Population Parameters.
Individual values of X Frequency How many individuals   Distribution of a population.
University of Ottawa - Bio 4118 – Applied Biostatistics © Antoine Morin and Scott Findlay 08/10/ :23 PM 1 Some basic statistical concepts, statistics.
Various topics Petter Mostad Overview Epidemiology Study types / data types Econometrics Time series data More about sampling –Estimation.
Managerial Economics Demand Estimation & Forecasting.
Basic Business Statistics, 10e © 2006 Prentice-Hall, Inc. Chap 8-1 Confidence Interval Estimation.
IMPORTANCE OF STATISTICS MR.CHITHRAVEL.V ASST.PROFESSOR ACN.
Confidence Interval Estimation For statistical inference in decision making: Chapter 9.
Chapter 9: Introduction to the t statistic. The t Statistic The t statistic allows researchers to use sample data to test hypotheses about an unknown.
Fundamentals of Data Analysis Lecture 4 Testing of statistical hypotheses pt.1.
NURS 306, Nursing Research Lisa Broughton, MSN, RN, CCRN RESEARCH STATISTICS.
©2012 Prentice Hall Business Publishing, Auditing 14/e, Arens/Elder/Beasley Audit Sampling for Tests of Details of Balances Chapter 17.
Tom.h.wilson Department of Geology and Geography West Virginia University Morgantown, WV.
Slide 1 Copyright © 2004 Pearson Education, Inc.  Descriptive Statistics summarize or describe the important characteristics of a known set of population.
Yandell – Econ 216 Chap 8-1 Chapter 8 Confidence Interval Estimation.
1 Simple Linear Regression Chapter Introduction In Chapters 17 to 19 we examine the relationship between interval variables via a mathematical.
Virtual University of Pakistan
Outline Sampling Measurement Descriptive Statistics:
Sampling and Sampling Distribution
STAT 312 Chapter 7 - Statistical Intervals Based on a Single Sample
Hypothesis Testing: One-Sample Inference
Statistics in Management
Chapter 7 Confidence Interval Estimation
Confidence Intervals and Sample Size
ESTIMATION.
Chapter 9 Audit Sampling: An Application to Substantive Tests of Account Balances McGraw-Hill/Irwin ©2008 The McGraw-Hill Companies, All Rights Reserved.
Lecture Nine - Twelve Tests of Significance.
Data Mining: Concepts and Techniques
Hypothesis Testing I The One-sample Case
Assumptions For testing a claim about the mean of a single population
Audit Sampling for Tests of Details of Balances
APPROACHES TO QUANTITATIVE DATA ANALYSIS
Simulation-Based Approach for Comparing Two Means
Chapter 11 Simple Regression
Module 8 Statistical Reasoning in Everyday Life
Introduction Second report for TEGoVA ‘Assessing the Accuracy of Individual Property Values Estimated by Automated Valuation Models’ Objective.
Review: What influences confidence intervals?
Geology Geomath Chapter 7 - Statistics tom.h.wilson
Confidence Interval Estimation
Data analysis and basic statistics
SIMPLE LINEAR REGRESSION
Chapter Outline Inferences About the Difference Between Two Population Means: s 1 and s 2 Known.
The Normal Distribution
Presentation transcript:

Best in Market Pricing

What is Best in Market Pricing ? An extension of parametric modeling for negotiating lowest pricing for a statement of work consisting of many items assessing a supplier’s market position in absence of competitive bids A mathematical model which simulates the competitive bid process shows the effect of bidding scenarios quantifies the likelihood of achieving desired pricing

Why is Best in Market Pricing Needed ? Cost analysis approach is expensive and ambiguous extensive analysis of suppliers costs suppliers reluctant to share costs costs often obscured by suppliers accounting timeliness and resources dictate different approach Estimate of market competition is needed potential market is not reflected in current costs RFI/RFQs often requested to establish target no dominate low cost supplier exists

Predicted Price = Constant $ + $s x Attribute 1 + …. Mathematical equations used to predict the prices of parts as a function of one or more of their attributes. An Extension of Parametric Models…

How Are Parametric Models Developed ? Samples of price data are drawn from a population Prices are regressed against part attributes to identify equations that explain the pricing variation Equations are used to predict the prices of remaining parts

Parametrics Used to Predict Market Prices… Average market prices vary from actuals due to market competition variance represented by bell curve. market $’s are at center width is determined by variance between actual and predicted $’s. Regression models can be used to predict average market prices competitive range of market. lowest Probable $’s

Best in Market Pricing Sets the Negotiation Range… The Strategy For a supplier’s Statement of Work, estimate range of lowest pricing likely to be seen in the marketplace i.e. 5 RFQ’s extended with lowest accepted Negotiate price within competitive range Initial position Don’t leave money on table = 10% probability Maximum position Don’t reject a reasonable offer = 80% probability The Model

Similar to Best-in-Class (BIC) Method… The Strategy For each group of similar parts find the supplier with lowest market ratio (observed/predicted) & broad model coverage Offer BIC supplier prices for all parts. Negotiate between market and BIC

BIC is the lowest market ratio demonstrated over the relative range of the parametric model Determine BIC Market Ratio… Calculate each supplier’s relationship to market

How Best in Market Price is Determined… First Estimate the Distribution of Supplier Prices of Each Part Predicted prices vary from actual due to market competition Variance represented by bell curve. Market $ is at center Width is determined by variance between actual and predicted $s. Regression models can be used to predict Average market prices Competitive range of market.

Normal Distribution is Assumed for Predictions

How Best in Market Price is Determined…

Forming Similar “Mega-Parts”… The variance summation of individual parts assumes independence. To validate this assumption, similar parts with identical pricing are considered to be the same part.

Distribution of Total Market $s…. Note: Independence assumption requires parts to be into similar “Mega-parts”

Basics behind Order Statistics… Odds of receiving at least one low price out of n independent bids i.e. 1- odds of not getting any bids that low Example: If the odds of getting a single supplier bid  $100 is 5% then, the odds of at least one bid in 6 supplier bids being that low is

Applying Order Statistics to Best in Market Pricing… Let $ 1, $ 2, …., $ n be a random sample of mutually independent bids from the population of suppliers capable of producing the statement of work. It is assumed that the suppliers bids would follow the same cumulative normal distribution. Arrange bids in ascending order so that $ 1 ’, $ 2 ’, …., $ n ’. It is considered unlikely that any two bids would be equal. Although order Statistics would be concerned with the properties of all bids, Best in Market Pricing is concerned primarily with the smallest.

Applying Order Statistics to Best in Market Pricing… The cumulative and probability distribution functions of the smallest of n bids $ i ’ for some value < T are The mean and variance of $ i ’ are

Distribution of Lowest $’s in Sample… Number (n) Mean (u zi,n ) Variance(  2 zi,n )

Distribution of Lowest $s in Sample…

Comparison of Lowest $s to Normal Distribution… Conclusions : Skewness & Kurtosis are insignificant at levels of interest. As bids increase Negative skew increases Peak sharpens, tails fatten Differences decrease further out in tails At 95% interval difference for 5 bids is.00036

Computing Negotiation Range for Lowest $... Using expectation rules to convert back to the Lowest $ distribution

To determine the desired negotiation range, select the normalized mean and standard deviation from table which corresponds to the expected number of bids, translate them into $ units and apply standard confidence interval techniques using the critical values associated with the desired management risk of.10 for the initial offer and.8 for the final. 1. Select Normalized Extreme Value Constants for n=5 For the case when n = 5 bids and total market dollars is Normal($1M,$100K) 2. Compute Distribution Statistics for Lowest Bid $s Computing Negotiation Range for Lowest $...

To determine the desired negotiation range, select the normalized mean and standard deviation from table which corresponds to the expected number of bids, translate them into $ units and apply standard confidence interval techniques using the critical values associated with the desired management risk of.10 for the initial offer and.8 for the final. 3. Compute Negotiation Range for Lowest Bid $ Computing Negotiation Range for Lowest $...

Applying Best in Market Pricing… The Strategy -For a supplier’s Statement of Work, estimate range of lowest supplier pricing likely to be seen if competitively bid. i.e. 5 RFQs extended with lowest accepted - Negotiate price within competitive range Initial position Don’t leave money on table = 10% probability Maximum position Don’t reject a reasonable offer = 80% probability The Model

An Example Statement of Work…

Verify Estimates of Cost Passengers…

A Single Part Number Case Study… Decision: To RFI parts

Analyzing the Resulting RFIs for Outliers… One bid identified as outlier

Comparison of RFI Data to Parametrics… Difference being investigated for potential model enhancement

Important Best in Market Price Considerations… Does not always predict lowest prices May be a dominant supplier (Best-in-Class) Limited Market Place Other supplier requirements precludes low cost Current supplier may not be capable of low prices Strategy may be to bid instead of negotiate Non-recurring costs should be considered Expected gains may be driven by a few parts Pareto techniques are valuable Predicted prices for high drivers should be verified

Best in Market Price Summary Logical Extension of Parametric Modeling Models Competitive Bidding Process Provides estimate of Market Competition without RFI/RFQ data or existence of “Best in Class” Supplier Quantifies likelihood of obtaining desired price in marketplace

& ANSWERS QUESTIONS & ANSWERS