l1

• Traditionally business decision have been based on subjective factors - considering factors that are present during that day
• Formal study of mathematics to make management decisions began in twentieth century.
• Quantitative analysis 


  refers to numeric data analysis, modeling, and mathematical calculations
• Quantitative analysis helps sectors in decision-making problems in business, government, health care, and education.
• QUANTITATIVE DATA ANALYSIS


  Scientific approach to managerial decision making - no whim, emotion, and guesswork.
• • The heart of QA is processing and manipulating of raw data into meaningful information.
• QUANTITATIVE ANALYSIS

  A) raw data

  B) quantitative analysis

  C) meaningful information

  
• Involves the investigation of factors in  a decsion-making problem that cannot be quantified.
• Quantitative factors

  measurable ones like investment alternatives, interest rates, inventory levels, demand, or labor cost
• Qualitative factors


  cannot quantify  such as weather condition, state and federal legislation, the outcome of an election, technology breakthroughs
• Qualitative factors


  may be difficult to quantify but may affect decision-making
• In most cases, quantitative analysis will be an aid to the decision-making process
• The results will be combined with other (qualitative) information in making the final decisions.
• TYPES OF DATA

  1. Alphanumeric
  2. Text
  3. Image
  4. Audio
• Alphanumeric 


  combination of numbers and letters
• Text 


  sentences and paragraphs used in written communication
• Image 


  graphics, shapes, figures, etc
• Audio 


  human voice and other sounds
• QUANTITATIVE ANALYSIS APPROACH

  A) Defining the problem

  B) Developing a model

  C) Acquiring input data

  D) Developing a solution

  E) Testing the solution

  F) Analyzing the results

  G) Implementing results

  
• Defining the problem


   a clear and concise statement of the problem that gives direction and meaning to the subsequent steps.
• Defining the problem


  Most important and difficult step. It is essential to go beyond the symptoms of the problem and identify true causes.
• If the problem is difficult to quantify, specific and measurable objectives may have to be developed
• • Possible in defining a problem:

  1. Conflicting viewpoints
  2. Impact on other Departments
  3. Beginning assumptions
  4. Solution outdated
• Developing a model


  quantitative models are realistic, solvable, and understandable mathematical representations of a situation.
• Developing a model

  • Mathematic models
  • Scale models
  • Schematic models
• Problem in developing a model:

  1. Fitting the model textbooks
  2. Undestanding the model
•  Acquiring Input Data


   input data must be obtained for the model to make it useful and they must be accurate
• GIGO rule

  A) garbage in

  B) process

  C) garbage out

  
• • Data may come from a variety of sources such as company reports, company documents, interviews, on-site direct measurement, or statistical sampling
• Developing a Solution


  the best (optimal) solution to a problem is found by manipulating the model until a solution is found that is practical and can be implemented.
• Common techniques for developing solution are:

  1. Solving equations
  2. Trial and Error - trying various approaches and picking the best result
  3. Complete enumeration - trying all possible values
  4. Using an algorithm - series of repeating steps to reach a solution
• Input data and model determine the accuracy of the solution
• • There are two potential roadblocks that quantitative analytics face 

  1. Hard to understand mathematics
  2. Only 1 answer is limiting
• Hard to understand mathematics - mathematics always shuns as lot of people even managers.
• Only 1 answer is limiting - QA models tend to give one solution to a problem. One way to offset this is to come up with alternative scenarios or sensitivities to give managers options to choose from
• Testing the Solution


  both input data and the model should be tested for accuracy before the solution can be analyzed and implemented
• Testing the Solution

  Collect additional data from a different source  to validate the accuracy of both model and model input.
• Results should be logical, consistent, and represent the real situation.
• Analyzing the results


  determine the implications of the solution
• Implementing the results often requires actions and changes in an organization