深圳大学管理学院：《运筹学》课程教学资源（PPT课件讲稿）决策与对策（决策论）运筹学3类 EXPLORING RELATIONSHIPS

CHAPTER 15 EXPLORING RELATIONSHIPS 15.1 INTRODUCTION EXPLANATORY VARIABLE tribute Measured R Measured E Measured M easured s Atribute Measured 0 Atribute N Attribute Atribute Attribute E easure

CHAPTER 15 EXPLORING RELATIONSHIPS 15.1 INTRODUCTION EXPLANATORY VARIABLE

The most common data analysis situations in the business arena os Response variable is measured oG Explanatory variable is either attribute or measured

❖ The most common data analysis situations in the business arena Response variable is measured Explanatory variable is either attribute or measured

152.COMMONDATA-ANALYSIS METHODOLOGY o sTEP 1 Framework for defining a Data-Analysis oo a clear idea of what is meant by a connection between the response variable and the explanatory variable o StEP 2 Initial Data Analysis (IDA) 6 To use some simple sample descriptive statistics to have a first look at the nature of the link between the variables g Strong evidence to support a link .& No evidence of a link Inconclusive and further more sophisticated data analysis is required

15.2 COMMON DATA-ANALYSIS METHODOLOGY ❖ STEP 1 Framework for defining a Data-Analysis A clear idea of what is meant by a connection between the response variable and the explanatory variable. ❖ STEP 2 Initial Data Analysis (IDA)  To use some simple sample descriptive statistics to have a first look at the nature of the link between the variables ❖ Strong evidence to support a link ❖ No evidence of a link ❖ Inconclusive and further more sophisticated data analysis is required

STEP 3 Further Data Analysis(FDA s The sample evidence is consistent with there being no link/connection/relationship between the response variable and the explanatory variable s The sample evidence is consistent with there being a link/connection/relationship between the response variable and the explanatory variable &o STEP 4 Describe Relationshil oo How to undertake and interpret the I.D.A 6 How to undertake and interpret the further data Analysis

❖ STEP 3 Further Data Analysis (FDA) The sample evidence is consistent with there being no link/connection/relationship between the response variable and the explanatory variable. The sample evidence is consistent with there being a link/connection/relationship between the response variable and the explanatory variable ❖ STEP 4 Describe Relationship  How to undertake and interpret the I.D.A. How to undertake and interpret the Further Data Analysis

F,,,、, Initial data Analysis Yes-- there is evidence a relationship, in Which case the link Further data needs to be described Analysis No es No- No evidence of a relationship Describe Relationship

No– No evidence of a relationship Yes-- there is evidence of a relationship, in which case the link needs to be described

多 EXample1 osA university investigates the salary of its graduates five years after graduating Response Variable: Type Current salary Measured Explanatory Variables: Ty ype of analysIs s Starting Salary Measured y measured Class of Degree' Measured v Attribute(5)* Graduate's Gender Measured v Attribute(2)*

❖ Example 1 A university investigates the salary of its graduates five years after graduating

, Example 2 66 CREDIT Scenario Response variable Type,测 The amount borrowed on credit Measured ExplanatoryVariables Customer's age Measured y Measured Household Income(E per annum) Measured y measured Estimated monthly outgoing Measured v Measured Does the customer own their own house? Measured v Attribute( 2) The Region in which the customer is resident Measured v Attribute(5

❖ Example 2  CREDIT Scenario

15.3 EXPLORING RELATIONSHIPS 1 令 MEASURED RESPONSE VARIABLE一 ATTRIBUTE EXPLANATORY VARIABLE ☆ Definition s There is a relationship between a measured response and an attribute explanatory variable if the average value of the response is dependent on the level of the attribute explanatory variable

15.3 EXPLORING RELATIONSHIPS 1 ❖ MEASURED RESPONSE VARIABLE ---- ATTRIBUTE EXPLANATORY VARIABLE ❖ Definition There is a relationship between a measured response and an attribute explanatory variable if the average value of the response is dependent on the level of the attribute explanatory variable

B There is no link 6 Given a measured response and an attribute explanatory variable with two levels, 1&2. If the statistical distribution of the response variable for attribute level 1 and attribute level 2 are exactly the same then the level of the attribute variable has no influence on the value response Attribute eve 1 Attn bute leve 2 ,L,,,,,, Igure

❖ There is no link Given a measured response and an attribute explanatory variable with two levels, 1 & 2. If the statistical distribution of the response variable for attribute level 1 and attribute level 2 are exactly the same then the level of the attribute variable has no influence on the value response

There is a link o6 Given a measured response and an attribute explanatory variable with two levels, 1 &2. If the statistical distribution of the response variable for attribute level 1 and attribute level 2 have different means then the level of the attribute variable does influence the response varlable. Attribute leve 1 Attrbute level 2 Figure 4

❖ There is a link  Given a measured response and an attribute explanatory variable with two levels, 1 & 2. If the statistical distribution of the response variable for attribute level 1 and attribute level 2 have different means then the level of the attribute variable does influence the response variable