Quantitative Analysis Introduction

Introduction to Quantitative Analysis

• Quantitative analysis is a scientific approach to managerial decision-making.
• Raw data are processed and manipulated to create meaningful information.
• Analysis uses statistical/mathematical methods and computational processes.
• This process helps understand patterns, connections, and how things change over time.
• Insights from analysis help guide managerial decisions.

Introduction

• Mathematical tools have been used for centuries.
• Quantitative analysis applies to many problems.
• Understanding the technique, its limitations, and assumptions are vital.
• Successful quantitative analysis is timely, accurate, flexible, economical, reliable, and easy to understand.

Examples of Quantitative Analyses

• Taco Bell saved over $150 million using forecasting and employee scheduling.
• Netflix uses quantitative analysis for movie and season production.
• Pakistan's polio eradication strategy uses business analytics and a population database.
• Continental Airlines saved over $40 million annually through quantitative analysis models.

Quantitative Factors

• Quantitative factors are measurable data.
• Relevant factors include: different investment alternatives, interest rates, financial ratios, cash flows, and rates of return.
• Other factors include flow of materials through a supply chain.

Qualitative Factors

• Qualitative factors are difficult to quantify but impact decision-making.
• Examples include: the weather, state/federal legislation, technological breakthroughs, and election outcomes.

Quantitative Analysis in Management

• Quantitative and qualitative factors have different roles.
• Quantitative data allows for automation of decisions.
• Quantitative analysis aids the decision-making process.
• Important in many areas of management, such as Production/Operations, Supply Chain Management, and Business Analytics.

Business Analytics

• A data-driven approach to decision-making.
• Large amounts of data necessitate the use of information technology.
• Statistical and quantitative analysis help understand the data and provide useful information.
• Different types of business analytics include descriptive, predictive, and prescriptive.

Descriptive Analytics

• Study and consolidation of historical data.

Predictive Analytics

• Forecasting future outcomes from past patterns.

Prescriptive Analytics

• Use optimization methods.

The Quantitative Analysis Approach

• Defining the Problem: Clear and concise statement, identify true causes, prioritize issues, and develop measurable objectives.
• Developing a Model: Realistic, solvable, and understandable mathematical representations of a situation.
• Acquiring Input Data: Data accuracy is crucial, GIGO ("Garbage In, Garbage Out") rule applies. Sources include company reports, documents, interviews, direct measurement, or statistical sampling.
• Developing a Solution: Manipulate the model to achieve the optimal solution. Techniques include solving equations, trial and error, complete enumeration, or using algorithms.
• Testing the Solution: Verify both input data and model for accuracy. Collect new data to test the model to validate results.
• Analyzing the Results: Determine implications of the solution. Consider changes to an organization. Sensitivity & postoptimality analysis reveals how model results change based on input data modifications.
• Implementing the Results: Integrate the solution into the company. Consider that implementation can be challenging. People can be resistant to changes, so management support is crucial.

Developing a Model

• Mathematical models are sets of mathematical relationships.
• Variables are either control-able or decision-related.
• Parameters are known quantities in the model (like quantities needed to place an order).

Acquiring Input Data

• Accurate input data is critical.
• Data sources include company reports, documents, employee interviews, direct measurement, and statistical sampling.

Developing a Solution

• Manipulate the model to generate the optimal solution.
• Common techniques include solving equations, trial-and-error methods, and algorithms.

Testing the Solution

• Both input data and models need to be tested.
• Collect new data to test the model's accuracy.
• Results need to be consistent and represent the true situation.

Analyzing the Results

• Analyze the implications of the solution.
• Implementations often require organizational changes, and their impact needs to be studied.
• Sensitivity analysis investigates how model results change in response to alterations in input data or model assumptions.

Implementing the Results

• Involve the company in the solution.
• Implementation challenges can arise from people's resistance to change.
• Management support and staff engagement are crucial.

Modeling in the Real World

• Quantitative analysis is widely used in organizations for problem-solving.
• Practical models can be complex and challenging to implement in real-world situations.
• Following the steps in the process is crucial for successful implementation.

How to Develop a Quantitative Analysis Model

• Profit = Revenue – Expenses.
• Profit = Selling Price per Unit * Number of Units Sold – (Fixed Cost + Variable Cost per Unit * Number of Units Sold).

Example - Time Pieces

• Company buys, sells, and repairs old clocks.
• Profit equation: Profit = 8X – 1000 – 3X (Assuming 8 is the sales price per unit, 1000 is fixed costs, and 3 is variable costs per unit. Variable "x" is the units sold).
• Break-even point (BEP): The point where profit equals zero. (In the example BEP = $1,000/($8 – $3) = 200 units.)

Advantages of Mathematical Modeling

• Accuracy in representing reality.
• Aids in problem definition for decision-makers.
• Provides valuable insights and information.
• Saves time and cost in decision-making and problem-solving.
• Can solve large or complex problems efficiently.
• Useful communication tool for problems and solutions.

Models Categorized by Risk

• Deterministic models: No risk or chance involved; all model values are definitively known.
• Probabilistic models: Involve risk or chance; model values are estimates based on probabilities.

Possible Problems in the Quantitative Analysis Approach

• Defining the problem can be difficult and may involve conflicting viewpoints or impacting other departments.
• The model developed may be outdated or fail to fit the real-world context.
• Acquiring appropriate, accurate data can be challenging or difficult (inaccurate or invalid).
• Developed solutions can be hard to interpret.
• Results may not accurately represent the intended situation.

Implementation - Not Just the Final Step

• Lack of commitment and resistance to change among people in the company can complicate the implementation process.
• Quantitative analysis efforts sometimes fail because a sound solution isn’t understood or correctly put into place.
• A manager's focus on “quick solutions” can compromise long-term viability.
• Quantitative analysts must understand the users and their concerns for successful implementation.