Effective Business Decisions Using Data Analysis

Objectives

• Support strategic initiatives
• Inform on policy formulation
• Direct operational decision making
• Appreciate the role of Data Analysis as a Decision Support tool
• Explain the scope and structure of the discipline of Statistics
• Understand the importance of data quality in data analysis
• Select an appropriate Data Analysis methodology to apply to specific management situations
• Apply a cross-section of Data Analysis tools and techniques
• Meaningful interpret statistical output to inform decision making
• Critically assess statistical findings with confidence
• Interact meaningfully and with confidence with Data Analysts
• Initiate with confidence their own Data Analysis projects

Outline

 Setting the Scene and Observational Decision Making
• Setting the Quantitative Scene
• The Decision Support Role of Quantitative Methods in Management
• “Thinking Statistically” about Applications in Business Practice
• The Elements and Scope of Quantitative Management
• Data and the importance of Data Quality
 Exercise and Discussion 1:-
“Within your work decision area, how could Data Analysis enhance your decision making capabilities?”
• Observational Decision Making – Using Excel’s Exploratory Data Techniques “Given the inherent variability in data, there is a need to profile it to understand it”
“Given the inherent variability in data, there is a need to profile it to understand it”.

 Using Excel to Paint a Picture of your Data
• Summary Methods Using Tables and Graphs to Profile Data
 (One-way, Two-way and Multi-way Pivot Tables)
 (Graphic Displays and Breakdown Analysis)
• Numeric Descriptors
 (Central (and non-central) locations; Dispersion; Distribution Shapes)
 (Graphical summary using Box plots)
 Exercise and Discussion 2:-
Case Studies (Cadillac and Sappi): Use Exploratory Data Analysis methods in Excel to analyse and gain insights into the management problems of each organization.

 Statistical (Inferential) Decision Making – by harnessing Uncertainty
• Using sample evidence to address management issues through statistical inference”
 How to measure and quantify Uncertainty (using Probability Distributions)
 The importance of Sampling
 Statistical Decision Making methods
 (Approaches: Confidence Intervals and Hypothesis Testing)
 (Techniques: z- and t-statistics, Analysis of Variance, Chi-Square)
• Addressing Practical Management Issues
 Estimation; Testing for Differences; Multiple Sample Comparisons)
 Exercise and Discussion 3:-
Case-based exercises will be used for each Statistical Decision Making scenario. The statistical findings will be generated by Excel and emphasis will be placed on their valid interpretation and implications for managers.

 Predictive Decision Making – Using Models to Build Relationships
• “Statistical models exploit statistical relationships between measures to prepare forecasts and make predictions”.
• The Value of Statistical Modelling
• Modelling Approaches
• (Regression Models, Time Series Analysis; Autoregressive Models)
 Exercise and Discussion 4:-
Case-based exercises will be used for each Predictive Decision Modelling scenario. The statistical findings will be generated by Excel and NCSS and emphasis will be placed on their valid interpretation and implications for managers.

 Data Mining – A brief Overview
Potentially valuable knowledge for strategic gain is imbedded in organizational databases. Data Mining can be used to “mine” these large (terabyte-size) databases to extract value for competitive advantage. An explanation of how data mining techniques work and what kinds of business problems each one can solve is provided.
• An Overview of Data Mining
 Definition; the Data Mining process; data preparation)
• Data Mining Functions
 (Prediction / Estimation / Classification / Descriptive)
• Overview of Selected Data Mining Techniques (analysis by NCSS)
 Purpose; Methodology; Interpretation; Likely Applications)
• Descriptive Modeling (Segmentation Strategies)
 (Cluster Analysis; Discriminant Analysis)
• Predictive Modeling (Classification; Estimation; Prediction Strategies)
 (Logistic Regression; Classification Trees; Neural Networks)
• Typical Applications
 (Market Basket Analysis; Customer Relationship Management (CRM)
 Exercise and Discussion 5:-
Case-based exercises will be used for each Data Mining technique. Emphasis will be placed on their valid interpretation and implications for managers.

 Decision Analysis for Management Judgment
Using Decision Models to structure / evaluate complex decision scenarios
• Multi-Criteria Decision Modelling (Illustrations of Two Practical Tools)
 SMART (Simple Multi Attribute Rating Technique)
 AHP (Analytical Hierarchy Process)

 Workshop Review Session
• Presentation:
 Review further analyses and insights gained on delegates’ databases.

Who Should Attend ?

Professionals in management support roles
Analysts who typically encounter data / analytical information regularly in their work environment
Those who seek to derive greater decision making value from data analytics