Tailored Products Group Analysis Silver Chung Marshall Shen.

Slides:



Advertisements
Similar presentations
Multiple Regression. Introduction In this chapter, we extend the simple linear regression model. Any number of independent variables is now allowed. We.
Advertisements

Lecture 17: Tues., March 16 Inference for simple linear regression (Ch ) R2 statistic (Ch ) Association is not causation (Ch ) Next.
Kin 304 Regression Linear Regression Least Sum of Squares
10-3 Inferences.
6-1 Introduction To Empirical Models 6-1 Introduction To Empirical Models.
EPI 809/Spring Probability Distribution of Random Error.
PROC GLIMMIX: AN OVERVIEW
The Power of Proc Nlmixed. Introduction Proc Nlmixed fits nonlinear mixed-effects models (NLMMs) – models in which the fixed and random effects have a.
© 2009, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH Getting to Know Your Data Basic Data Cleaning Principles.
April 25 Exam April 27 (bring calculator with exp) Cox-Regression
Some Terms Y =  o +  1 X Regression of Y on X Regress Y on X X called independent variable or predictor variable or covariate or factor Which factors.
LINEAR REGRESSION: Evaluating Regression Models Overview Assumptions for Linear Regression Evaluating a Regression Model.
© 2000 Prentice-Hall, Inc. Chap Multiple Regression Models.
Multiple Regression Models. The Multiple Regression Model The relationship between one dependent & two or more independent variables is a linear function.
Regression Diagnostics Using Residual Plots in SAS to Determine the Appropriateness of the Model.
EPI 809/Spring Multiple Logistic Regression.
Topics: Regression Simple Linear Regression: one dependent variable and one independent variable Multiple Regression: one dependent variable and two or.
Unsorted Treatments Random Numbers Sorted Sorted Experimental Treatments Random Units Numbers.
OLS versus MLE Example YX Here is the data:
Lecture 17 Interaction Plots Simple Linear Regression (Chapter ) Homework 4 due Friday. JMP instructions for question are actually for.
Variance and covariance Sums of squares General linear models.
GEE and Generalized Linear Mixed Models
SAS Lecture 5 – Some regression procedures Aidan McDermott, April 25, 2005.
5-1 Introduction 5-2 Inference on the Means of Two Populations, Variances Known Assumptions.
G Lecture 81 Example of Random Regression Model Fitting What if outcome is not normal? Marginal Models and GEE Example of GEE for binary outcome.
ALISON BOWLING THE GENERAL LINEAR MODEL. ALTERNATIVE EXPRESSION OF THE MODEL.
Applied Quantitative Analysis and Practices LECTURE#23 By Dr. Osman Sadiq Paracha.
April 6 Logistic Regression –Estimating probability based on logistic model –Testing differences among multiple groups –Assumptions for model.
Multilevel Linear Models Field, Chapter 19. Why use multilevel models? Meeting the assumptions of the linear model – Homogeneity of regression coefficients.
4-Oct-07GzLM PresentationBIOL The GzLM and SAS Or why it’s a necessary evil to learn code! Keith Lewis Department of Biology Memorial University,
Logistic Regression Database Marketing Instructor: N. Kumar.
Different Distributions David Purdie. Topics Application of GEE to: Binary outcomes: – logistic regression Events over time (rate): –Poisson regression.
Linear vs. Logistic Regression Log has a slightly better ability to represent the data Dichotomous Prefer Don’t Prefer Linear vs. Logistic Regression.
Inference for Regression Simple Linear Regression IPS Chapter 10.1 © 2009 W.H. Freeman and Company.
April 4 Logistic Regression –Lee Chapter 9 –Cody and Smith 9:F.
Chapter 4 Linear Regression 1. Introduction Managerial decisions are often based on the relationship between two or more variables. For example, after.
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.
Multilevel Modeling Software Wayne Osgood Crime, Law & Justice Program Department of Sociology.
Introduction to Multiple Imputation CFDR Workshop Series Spring 2008.
GEE Approach Presented by Jianghu Dong Instructor: Professor Keumhee Chough (K.C.) Carrière.
Topic 26: Analysis of Covariance. Outline One-way analysis of covariance –Data –Model –Inference –Diagnostics and rememdies Multifactor analysis of covariance.
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.
Examining Relationships in Quantitative Research
Logistic Regression. Linear Regression Purchases vs. Income.
Multiple Logistic Regression STAT E-150 Statistical Methods.
Treat everyone with sincerity,
1 Statistics 262: Intermediate Biostatistics Regression Models for longitudinal data: Mixed Models.
Multiple Imputation using SAS Don Miller 812 Oswald Tower
Linear Regression Linear Regression. Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc. Purpose Understand Linear Regression. Use R functions.
Armando Teixeira-Pinto AcademyHealth, Orlando ‘07 Analysis of Non-commensurate Outcomes.
Biostatistics Case Studies Peter D. Christenson Biostatistician Session 3: Missing Data in Longitudinal Studies.
G Lecture 71 Revisiting Hierarchical Mixed Models A General Version of the Model Variance/Covariances of Two Kinds of Random Effects Parameter Estimation.
1 Statistics 262: Intermediate Biostatistics Mixed models; Modeling change.
Lecturer: Ing. Martina Hanová, PhD.. Regression analysis Regression analysis is a tool for analyzing relationships between financial variables:  Identify.
Lecture 11: Simple Linear Regression
Chapter 14 Introduction to Multiple Regression
AP Statistics Chapter 14 Section 1.
Correlation, Regression & Nested Models
Linear Mixed Models in JMP Pro
Multiple Regression A curvilinear relationship between one variable and the values of two or more other independent variables. Y = intercept + (slope1.
6-1 Introduction To Empirical Models
Statistical Models for the Analysis of Single-Case Intervention Data
Tutorial 8 Table 3.10 on Page 76 shows the scores in the final examination F and the scores in two preliminary examinations P1 and P2 for 22 students in.
Chapter 4, Regression Diagnostics Detection of Model Violation
Adequacy of Linear Regression Models
Adequacy of Linear Regression Models
Adequacy of Linear Regression Models
Nazmus Saquib, PhD Head of Research Sulaiman AlRajhi Colleges
Statistical Models for the Analysis of Single-Case Intervention Data
Presentation transcript:

Tailored Products Group Analysis Silver Chung Marshall Shen

Introduction of TPG products

Tailor Product vs. Standard Product  Company has a set of furniture portfolios for chairs, desks, etc, with specific size and colors.  But sometimes customers request a slight change based on the standard products.  “Can you make this chair 2 inches higher?”  “Can you paint this desk black and gold? I am a proud Hawkeye!”

Tailored Product Cont’d  Allsteel received the request from the customers, and they make decision whether to accept/deny the business

Project Overview  So, what’s the problem: “It’s cool that we are making Tailored Products for out customers, but… Are we making profits on TPG? What are the right strategies for TPG market?

Statistical Analysis

Questions we want to answer: Who are buying Tailored Products? -There are four major customer types in our dataset: 1)Dealer 2) Federal Government 3) Direct 4) State How likely is it for each customer types to purchase Tailored Products? - We fit logistic regression to analyze our data.

SAS Code (logistics within GEE) proc genmod data=INVOICE_2010 descending ; class DEALER FEDERAL DIRECT STATE NUM_CUST_BAS CLASS; model SPECIAL = CLASS / dist=binomial link=logit type3 alpha=0.05; repeated subject= NUM_CUST_BAS / type=cs; output out=INVOICE2011_OUTPUT2 p=pred lower=low upper=up; ESTIMATE 'DEALER vs. DIRECT' CLASS /EXP; ESTIMATE 'DEALER vs. FEDERAL' CLASS /EXP; ESTIMATE 'DEALER vs. STATE' CLASS /EXP; ESTIMATE 'FEDERAL vs. DIRECT' CLASS /EXP; ESTIMATE 'STATE vs. DIRECT' CLASS /EXP; ESTIMATE 'FEDERAL vs. STATE' CLASS /EXP; run;

SAS Output Year 2010 ParametersCustomers Class 1Dealer Class 2Federal Class 3State Class 4Direct

SAS Output 2010 (logistics within GEE) Customer ClassP(special orders) Dealer Federal State Direct Output 2011 Customer ClassP(special orders) Dealer Federal State Direct

Next question to answer: what is the percentage of TPG inside special orders? We tried to applied normal linear mixed model to incorporate the correlation within same division (one customer might have multiple special orders) SAS code: ODS html; ods graphics on; proc mixed data=PERCENTAGE2 method=reml covtest plots=boxplot(student); class DEALER FEDERAL DIRECT STATE NUM_CUST_BAS CLASS; model SPECIAL_DOLLAR_PCT = CLASS / solution cl influence(effect=NUM_CUST_BAS est)outpm=PAfit outp=SSfit residual ; random intercept /subject=NUM_CUST_BAS; repeated/type=cs subject=NUM_CUST_BAS ; ODS output influence=influence1; ods output solutionr=solutionr; run; ods graphics off; ODS html close;

SAS Ouput

BUT WAIT…We need to check the assumption… Our model assumes that the error follows a normal distribution, but does it? The assumption for normality is voilated.

We need a better model that doesn’t require normality assumption: Semi-Parametric Model using GEE SAS Code: ODS html; ods graphics on; proc genmod data=PERCENTAGE2 plots=all; CLASS NUM_CUST_BAS CLASS; model SPECIAL_DOLLAR_PCT = CLASS; repeated subject=NUM_CUST_BAS / type=cs ; run; ods graphics off; ods html close;

SAS Output

SAS Output (Cont’d)

Conclusion & Future Work  The likelihood for different customer classes to have special orders is different  The likelihood for customers to have special orders are generally increasing from 2010 to  The percentage of TPG products inside invoices is statistically different for different customer classes.  Due to the nature of the data set, we need to find a better statistical model 18

Questions?