Showing posts with label Quantitative Analysis. Show all posts
Showing posts with label Quantitative Analysis. Show all posts

Linear Programming Problem

It is a mathematical technique for choosing the best alternative from a set of feasible alternatives in situation where the objective function as well as the constraints can be expressed as linear mathematical functions.

Requirements
1)   All problems seek to maximize or minimize some quantity (the objective function).
2)   Restrictions or constraints that limit the degree to which we can pursue our objective are present.
3)   There must be alternative courses of action from which to choose.
4)   The objective and constraints in problems must be expressed in terms of linear equations or inequalities.

Three Components of Linear Programming
1)   The Objective Function
2)   Constraints
3)   Non-negativity Constraint

Applications of LPP
Production management
Company can produce several products with each requiring the use of certain resources. It is formulated, determining the number of units to be produced, with an objective- maximization of profits or minimization of cost with constraints in the form of resources.

Financial management
Portfolio selection dealing with choosing of investment option with an objective to maximise the total expected return or minimizing risk.

Marketing Management
Determining the advertising media mix so as to maximize effective exposure, subject to limitation of budget and specified exposure rates.

Queuing Theory

Queuing theory is the study of waiting lines. It is one of the oldest and most widely used quantitative analysis techniques. Waiting lines are an everyday occurrence, affecting people shopping for groceries, buying petrol, making a bank deposit or waiting to buy movie tickets.

The theory is applicable to situations where the customers arrive at some service station for some service; wait (occasionally not) and then leave the system after getting the service. In such ‘arrival and departure’ problems, the customers might be people waiting to deposit their electricity bills at a cash counter, machines waiting to be repaired in a factory’s repair shop, patients in a hospital who need treatment and so on…The service stations in such problems are the cash counters in the electricity office, repairman in shop and doctors attending the patients respectively.

The waiting lines develop because the service to a customer may not be rendered immediately as the customer reaches the service facility. Thus lack of adequate service facility would cause waiting lines of customers to be formed. The only way that the service demand can be met with ease is to increase the service capacity to a higher level. But that will mean higher cost of servicing. A manager therefore, has to decide on an appropriate level of service which is neither too low nor too high.

Basic Characteristics:
1)   Queue Length
2)   System Length
3)   Waiting time in the queue
4)   Total time in the system

Various types of Queuing System
1)   A Single Service facility
2)   Multiple Parallel Facilities with Single Queue
3)   Multiple Parallel Facilities with Multiple Queue
4)   Service Facilities in a Series

Network Models

All types of networks use a common terminology. The points on a network are called nodes and may be represented as circles of squares. The lines connecting the nodes are called arcs. There are  basically three network models.

Types of Network Model
1. Minimum spanning Tree
2. Shortest-Route Technique
3. Maximum Flow technique

1.- Minimum spanning Tree
The minimum spanning tree technique determines the path through the network that that connects all the points while minimizing total distance. When the points represent houses in a subdivision, the minimal –spanning tree technique can be used to determine the best way to connect all of the houses to electrical power, water systems and so on, in a way that minimizes the total distance or length of power lines or water pipes. There is no origin or destination, the objective is inter connectivity.

2.- Shortest-Route Technique
This technique finds the shortest path through a network. There is an origin and a destination. For example, this technique can find the shortest route from one city to another through a network of roads.

3.- Maximum Flow technique
The maximal-flow technique finds the maximum flow of any quantity or substance through a network. This technique can determine for example, the maximum number of vehicles( cars, trucks and so forth) that can go through a network of roads from one location to another.

Simulation Theory

 Simulation is one of the most widely used quantitative analysis tools. To simulate is to try to duplicate the features, appearance, and characteristics of a real system. We will build a mathematical model that comes as close as possible to representing the reality of the system. Physical models can also be built to test systems.

Advantages of simulation
1)   It is relatively straightforward and flexible.
2)   Recent advances in computer software make simulation models very easy to develop.
3)   Can be used to analyze large and complex real-world situations.
4)   Allows “what-if?” type questions.
5)   Does not interfere with the real-world system.
6)   Enables study of interactions between components.
7)   Enables time compression.

Disadvantages of simulation
1)   It does not generate optimal solutions; it is a trial-and-error approach.
2)   It requires managers to generate all conditions and constraints of real-world problem.
3)   Each model is unique and the solutions and inferences are not usually transferable to other problems.

Monte Carlo Simulation
When systems contain elements that exhibit chance in their behavior, the Monte Carlo method of simulation can be applied. The basis of the Monte Carlo simulation is experimentation on the probabilistic elements through random sampling.

Some examples/Applications 
1)   Inventory demand.
2)   Lead time for inventory.
3)   Times between machine breakdowns.
4)   Times between arrivals.
5)   Service times.
6)   Times to complete project activities.
7)   Number of employees absent.

Steps of Monte Carlo Simulation
1)   Establishing a probability distribution for important variables.
2)   Building a cumulative probability distribution for each variable.
3)   Establishing an interval of random numbers for each variable.
4)   Generating random numbers.
5)   Actually simulating a series of trials. 

Projective Techniques in Qualitative Research

Qualitative Research includes an array of interpretative techniques which seek to describe, decode, translate, and otherwise come to terms with the meaning, not the frequency, of certain more or less naturally occurring phenomena in the social world.

Qualitative techniques are used at both the data collection and data analysis stages of a research project. Because researchers are often looking for hidden or suppressed meanings, Projective Techniques can be used within the interview structures. Some of these techniques include

Types of Projective Techniques
Word or Picture association: Participants are asked to match images, experiences, emotions, products and services, even people and places, to whatever is being studied.

Sentence completion: Participants are asked to complete a sentence.

Cartoons or empty balloons: Participants are asked to write the dialogue for a cartoon like picture.

Thematic Apperception Test: Participants are confronted with a picture (usually a photograph or drawing) and asked to describe how the person in the picture feels and thinks.

Component sorts: Participants are presented with flash cards containing component features and asked to create new combinations.

Sensory Sorts: Participants are presented with scents, textures, and sounds, usually verbalized on cards, and asked to arrange them by one or more criteria.

Laddering or benefit chain: Participants are asked to link functional features to their physical and psychological benefits, both real and ideal.

Imagination exercises: Participants are asked to relate the properties of one thing/person/brand to another.

Imaginary Universe: Participants are asked to assume that the brand and its users populate an entire universe; they then describe the features of this new world.

Visitor from another planet: Participants are asked to assume that they are aliens and are confronting the product for the first time: they then describe their reactions, questions, and attitudes about purchase or retrial.

Personification: Participants are asked to imagine inanimate objects with the traits, characteristics and features, and personalities of humans.

Authority figure: Participants are asked to imagine that the brand or product is an authority figure and to describe the attributes of the figure.

Ambiguities and paradoxes: Participants are asked to imagine a brand as something else, describing its attributes and position.

Semantic mapping: Participants are presented with a four-quadrant map where different variables anchor the two different axes; they then spatially place brands, product components, or organizations within the four quadrants.

Brand Mapping: Participants are presented with different brands and asked to talk about their perceptions, usually in relation to several criteria. They may also be asked to spatially place each brand on one or more semantic maps.                       

Poisson Distribution

Useful in estimating the number of occurrences over a specified interval of time or space.

Characteristics
1.   It is a discrete distribution.
2.   It describes rare events.
3.   Each occurrence is independent to other occurrence.
4.   It describes discrete occurrences over an interval.
5.   The occurrences in each interval can range from zero to infinity.
6.   The expected number (average=mean) of occurrences are constant throughout the experiment.

Application of Poisson Distribution
Some of the common examples where Poisson random variable can be used to define the probability distribution are
1.   Number of accidents per day on expressway.
2.   Number of earthquakes occurring over fixed time span.
3.   Number of misprints on a page.
4.   Number of arrivals of calls on telephone exchange per minute.
5.   Number of interrupts per second on a server.

Data Measurement Techniques

Nominal Level
The lowest level of data measurement is the Nominal Level. Numbers representing nominal level data can be used only to classify or categorize. The numbers are used only to differentiate or categorize items or persons but not to make value statement about them. Many demographic questions in surveys result in data are nominal because the questions are used for classification only. Examples of nominal level data are as follows:

Gender, Religion, Ethnicity, Geographical Location, Place  of Birth, Employee Ids, Student Roll Numbers, Telephone Numbers, Security Numbers etc.

Statistical techniques that are appropriate for analyzing nominal data are limited and that is Chi-Square analysis.

Ordinal Level
Ordinal level data is higher than the nominal level. In addition to nominal level capabilities, ordinal level can be used to rank or order objects. For example, using ordinal data, a supervisor can evaluate three employees by ranking their productivity with the number 1 through 3. The supervisor could identify one employee as the most productive, one as least productive and one as somewhere between by using ordinal level data. However, the supervisor could not say the exact difference in the amount of productivity between the employees ranked 1, 2 and 3.

Because nominal and ordinal data are often derived from measurements such as demographic questions, the categorization of people or objects or the ranking of items, nominal and ordinal data are Non-Metric data and sometimes referred to as Qualitative Data.

Interval Level
Interval level data measurement is the next to the highest level of data in which the distances between consecutive numbers have meaning and the data are always numerical. The differences between consecutive numbers are always equal in interval level data means interval data have equal intervals. Interval level data is not having a Zero as fixed point and zero does not mean the absence of the characteristic. For example, zero degree temperature does not mean absence of heat or cold.

Ratio Level
Ratio level data measurement is the highest level of data measurement. Ratio data have the same properties as interval data, but ratio data have an absolute zero and that is fixed and that means absence of the characteristic being studied. The value of zero cannot be arbitrarily assigned because it represents a fixed point. Examples are height, weight, time, volume etc.

Mean, Median and Mode

Mean
It is the average of a group of numbers and is computed by summing all numbers and dividing by total numbers.

Advantages
1)   Easy to understand.
2)   Simple to compute.
3)   Based on all the observation.
4)   Uniquely defined.

Disadvantages
1)   Affected by extreme value.
2)   Unable to compute mean for open-ended clases.
3)   Tedious to compute.

Median
It is the middle value in an ordered array of numbers.

Advantages
1)   Extreme values do not affect the median.
2)   Easy to understand.
3)   Calculated from any kind of data with open-ended classes unless median follows in that class.
4)   Can be used even for qualitative descriptions.

Disadvantages
Median is the value at average position. So array (ascending or descending order) is required prior to calculation, which is time consuming.

Mode
It is the most frequently occurring value in a set of data. It can be classified as Uni-modal, Bimodal and Multi-Modal

Advantages
1)   Extreme values do not affect the mode.
2)   Easy to understand.
3)   Calculated from any kind of data with open-ended classes
4)   Can be used even for qualitative descriptions.

Disadvantages
If it is bimodal or multi-modal, it can create confusion in taking decision as two or more options are available.

Binomial Distribution

Binomial Distribution is used when there are exactly two mutually exclusive outcome of trial, These outcomes are appropriate labeled success and failure.

 Characteristics
1.   It is a discrete distribution.
2.   Trials are finite (and not very large), performed repeatedly for ‘n’ times.
3.   Each trial (random experiment) should be a Bernoulli trial, the one that results in either success or failure.
4.   Probability of success in any trial is ‘p’ and is constant for each trial.
5.   Sampling is done with replacement.
6.   All trials are independent.

Assumption
 Binomial distribution deals with only two events  Probability of success P and Probability of failure Q = 1- P So here we assume that P (Probability of success will never change as different trails take place. So sampling is always done with replacement in binomial distribution.

Application of Bernoulli distribution
Situations where Bernoulli distribution is commonly used are
1.   Sex of newborn child; Male = 0, Female = 1 say.
2.   Items produced by a machine are Defective or Non-defective.
3.   During next flight an engine will fail or remain serviceable.
4      Student appearing for examination will pass or fail.