Seminar In Research Methodology

Marketing Research

Scope of Business Research n

What is your definition of business? For profit corporations l Not for profit organizations l Government Departments l

Definition

Marketing Research is defined as the systematic and objective process of gathering, recording, recording, and analyzing data for aid in making Marketing decisions. decisions.

Basic vs. Applied n

Basic / Pure Research l

n

Research that is intended to expand the boundaries of knowledge itself or to verify the acceptability of a given theory.

Applied Research l

Research undertaken to answer questions about specific problems or to make decisions about a particular course of action or policy decision.

When is Business Research Needed? n

Time Constraints l

n

Availability of data l

n

Many African nations have never conducted population census

Nature of Decision l

n

Urgency of situation precludes the use of research

Tactical vs. Strategic

Benefits vs. Costs

n

Data l

n

Information l

n

Recorded measures of certain phenomenon A body of facts that in a format suitable for decision making

Knowledge l

A blend of information, experience and insight that provide a framework that can be thoughtfully applied when assessing new information or evaluating relevant situations

Types of Business Research n

Exploratory l

l

l

l

Initial research conducted to clarify and define the nature of a problem “Absenteeism is increasing and we don’t know why” “Would people be interested in our new product idea?” “What task conditions influence the leadership process in our organization?”

Types of Business Research n

Descriptive l

l

l

l

Research designed to describe characteristics of a population or a phenomenon “What kind of people favor our services?” “Did last year’s product recall have an impact on our company’s stock price?” “Has the average rate of savings and loans increased in the past decade?”

Types of Business Research n

Causal Research l

l

l

l

Research conducted to identify cause and effect relationships among variables when the research problem has been narrowly defined. “Which of the two training programs is more effective?” “Can I predict the value of energy stocks if I know the current dividends growth rates of dividends?” “Will buyers purchase more of our product in a new package?”

Which Type of Research? n

n

n

n

Establishing the functional relationship between advertising and sales Identifying targettarget-market demographics for a shopping centre Learning the extent of job satisfaction in a company Investigating reactions to the idea of a new telecom policy

You work for CHILDCO, a corporation that is considering the acquisition of a toy manufacturer. The senior vice president for development asks you to head a task force to investigate six companies that are potential candidates. You assemble a team composed of representatives from the relevant functional areas. Pertinent data are collected from public sources because of the sensitive nature of the project. You examine all of the following: company annual reports; articles in business journals, trade magazines, and newspapers; financial analysts’ assessments; and company advertisements. The team members then develop summary profiles of the candidate firms based on the characteristics gleaned from the sources. The final report highlights the opportunities and problems that acquisition of the target firm would bring to all areas of the business.

n

What is the dilemma facing the manager? l

the senior vice president for development must make a proposal to the president or possibly the board of directors about whether to acquire a toy manufacturer and, if one is to be acquired, which one of the six under consideration is the best candidate.

n

What must the research accomplish? l

l

l

l

the researcher needs to know what information should be evaluated in order to value a company. In the study of management, this knowledge would be acquired primarily in courses in financial management, accounting, and marketing. Knowing the type of information needed, the researcher in CHILDCO identifies sources of information, like trade press articles and annual reports. Because of the possible effect of the toy manufacturer evaluation on the stock prices of the conglomerate instigating the study and each toy company, only public sources are used.

Case 2

ColorSplash, a paint manufacturer, is having trouble maintaining profits. The owner believes inventory management is a weak area of the company’s operations. In this industry, the many paint colors, types of paint, and container sizes make it easy for a firm to accumulate large inventories and still be unable to fill customer orders. The owner asks you to make recommendations. You look into the present warehousing and shipping operations and find excessive sales losses and delivery delays because of out-of-stock conditions. An informal poll of customers confirms your impression. You suspect the present inventory database and reporting system do not provide the prompt, usable information needed for appropriate production decisions.

Based on this supposition, you familiarize yourself with the latest inventory management techniques in a local college library. You ask the warehouse manager to take an accurate inventory, and you review the incoming orders for the last year. In addition, the owner shows you the production runs of the last year and his method for assessing the need for a particular color or paint type. Modeling the last year of business using production, order, and inventory management techniques, you choose the method that provides the best theoretical profit. You run a pilot line using the new control methodology. After two months, the data show a much lower inventory and a higher order fulfillment rate. You recommend that the owner adopt the new inventory method.

n

What is the dilemma facing the manager? l

the owner of the paint manufacturer must decide whether to implement a new inventory management system.

n

What must the research accomplish? l

l

l

believing the problem with paint stockouts is the result of inventory management, the owner asks the researcher to detail warehousing and shipping processes. This would be a descriptive study if it had stopped here. But if problems in the processes could be linked with sales losses due to an inability to make timely deliveries to retail or wholesale customers, then an explanatory study would emerge. The researcher tests this hypothesis by modeling the last year of business using the relationships between processes and results.

Research Process

Clarifying the Research Question

Research Proposal

Research Design Strategy Data Collection Design Sampling Design Instrument Design & Testing

Data Collection & Preparation

Data Analysis & Interpretation

Research Reporting / Management Decision

Management Research Question Hierarchy

Management Decision Measurement Questions Investigative Questions Research Question(s) Management Question Management Dilemma

1

2

3

4

5

6

Recommended course of Action

What should be asked or observed to obtain the information the manager needs?

What does the manager need to know to select the best alternative?

What plausible courses of action are available to management?

How can management eliminate the negative symptoms?

What symptoms cause management concern?

Problem Discovery n n n n

“A problem well defined is a problem half solved” “The formulation of problem is often more essential than its solution” Most important and frequently neglected area of research Exploratory research to transform the discovered problem into defined ones, incorporating specific research objectives

Research Design n

A master plan specifying the methods and procedures for collecting and analyzing the needed information Surveys l Experiments l Secondary Data Studies l Observation Techniques l

Survey Research n

A method of gathering primary data based on communication with a representative sample of individuals.

Classification

Structured Undisguised

Unstructured Undisguised

Structured Disguised

Unstructured Disguised

Temporal Basis n

Cross Sectional Studies l

n

Various segments of a population are sampled at a single point in time.

Longitudinal Studies l

Respondents are questioned at different moments of time

Methods of Communication n

Human Interactive Media Personal Interview l Door Door--to to--Door Interviews l Mall Intercept Interviews l

n

Electronic Interactive Media Telephone Interview l Computer Assisted Telephone Interviewing (CATI) l

Methods of Communication n

Non Interactive Media Self Administered Questionnaires l Mail Questionnaires l Email Surveys l Internet Surveys l Kiosk Surveys l

Errors in Survey Research Respondent Error

Respondent Error Respondent Error

Random Sampling Error

Data Processing Error

Total Error

Sample Selection Error

Systematic Error (Bias) Administrative Error

Interviewer Error Interviewer Cheating

Sampling n

Process of using a small number of items or parts of a larger population to make conclusions about the whole population

Stages in Selection of Sample n

Define the target population l

n

The Sampling Frame l

n n

The specific, complete group relevant to the research project Working population

Sampling Unit Sampling Technique

Sampling Methods n

Probability Sampling l

n

In which every member of the population has a known, non zero probability of selection

Non Probability Sampling l

In which units of the sample are selected on the basis of personal judgment or convenience

Non Probability Sampling n n

n n

Convenience Sampling Judgment or Purposive Sampling Quota Sampling Snowball Sampling

Probability Sampling n n

Simple Random Sampling Systematic Sampling l

n

Stratified Sampling l

n n

Every 5th name from the list would be drawn Simple random sub samples are drawn from within different strata’s

Cluster Sampling Multistage Area Sampling

Sampling Error n

The absolute value of the difference between an unbiased estimate and the corresponding population parameter. l

Because sample results (statistics) are based on partial or incomplete analysis of population features (or characterstics)

n

Population Parameter l

n

An exact, but generally unknown measure (or value) which describes the entire population or process characteristic

Sample Statistic l

A measure (or value) found from analyzing sample data.

Principles of Sampling n

Principle of Statistical Regularity l

n

That moderately large number of items chosen at random from a large group are almost sure on the average to process the characteristics of a large group

Principle of Inertia of Large Numbers

Sampling Distribution n

n

A probability distribution consisting of all possible values of a sample statistic Standard Error of Statistic – Standard Deviation of sampling distribution of sampling statistic

Central Limit Theorem n

n n

When a random sample of observations are drawn from a nonnonnormal population with finite mean µ, and as the sample size n is increased, the sampling distribution of the sample mean is approximately normally distributed, with mean and standard deviation as Mean = µ and Standard Deviation = s / vn

Value of n n

n

If the sampled population is normal, then the sampling distribution of mean will also be normal regardless of the size of the sample If the sampled population is not normal or is skewed, the sample size must be larger, with atleast 30 before the sampling distribution of mean becomes approximately normal

I) Population - Normal n

n n n

n n

(A) – Population Standard Deviation s is known Standard Normal Variate Z = (x(x-µ)/( µ)/(s s /vn) (B) – Population Standard Deviation is not known t= (x(x-µ)/(s/vn), where s= v( (x(x-mean)2 /(n /(n--1)

Case I n

n

A motorcycle manufacturing company claims that its particular brand of motorcycle gave an average highway km per litre rating of 90. An independent agency tested it to verify the claim. Under controlled conditions, the motor cycle was driven for a distance of 100 km on each of 25 different occasions.

Case I n

n

n

The actual km per litre achieved during the trip were recorded on each occasion. Over 25 trials, the average and the standard deviation turned out to be 87 and 5 respectively If the rating of 90 km is correct, find the probability that the average kms per litre over a random sample of 25 trials would be 87 or less.

Case II n

n

The strength of wire produced by company A has a mean of 4500 Kg and a standard deviation of 200 Kg. Company B has a mean of 4000 Kg and a standard deviation of 300 Kg If 50 wires of company A and 100 wires of company B are selected at random, what is the probability that the sample mean strength of A will be atleast 600 Kg more than that of B?

Case III n

A manufacturer of watches has determined from experience that 3 percent of the watches he produces are defective. If a random sample of 300 watches is examined, what is the probability that the proportion defective is between 0.02 and 0.035?

Standard Values Confidence Level (1--a)% (1

Acceptable Error Level (a (a)

a/2

Z

90%

0.10

0.05

+/-- 1.64 +/

95%

0.05

0.025

+/-- 1.96 +/

98%

0.02

0.01

+/-- 2.33 +/

99%

0.01

0.005

+/-- 2.58 +/

Confidence Interval

s is not known

s is known

Large n>=30

Small n<30

Z -distribution

Z-distribution

Z – distribution

t-distribution

(s is estimated by s) (s is estimated by s)

Case n

The following data have been collected for a sample of normal population : 5,10, 8, 11, 12, 6, 15, 13 What is the point estimate of population mean and standard deviation? l What is the confidence interval for population mean at 95% confidence interval? l

Case n

n

n

The HRD department of a company developed an aptitude test for screening potential employees. The person who devised the test asserted that the mean mark attained would be 100. The following results were obtained with a random sample of applications (mean = 96, s=5.2, n=13). Calculate a 95% confidence interval for the mean mark for all candidates and use it to see if the mean mark could be 100

Case n

n

n

In a survey carried out in a large city, 170 households out of a random sample of 250 owned at least one pet. Find the 95% confidence interval for the percentage of households in the city who own at least one pet. Does the result support a pet manufacturer claim that 75 percent of all households have at least one pet

Hypothesis Testing n

n

A statistical hypothesis is a claim (assertion, statement, belief or assumption) about an unknown population parameter The process that enables a decision maker to test the validity of his claim is called hypothesis testing

Formats of Hypothesis n

n

n

n

If inflation rate has decreased, then wholesale price index will also decrease If employees are healthy, then they will take sick leave less frequently Greater the stress experienced in the job, lower the job satisfaction to employees Directional Hypothesis

Formats of Hypothesis n

n

n

There is relationship between age and job satisfaction There is difference between average pulse rates of men and women Non--Directional Hypothesis Non

General Procedure n

n n n

n

State the Null Hypothesis (H0) and Alternative Hypothesis (H1) State the Level of Significance (a (a ) Establish Critical or Rejection Region Select the suitable test of significance or Test statistic Formulate the Decision Rule to Accept Null Hypothesis

Errors in Hypothesis Testing Decision

State of Nature H0 is true

H0 is False

Accept H0

Correct

Type II Error (ß (ß)

Reject H0

Type I Error (a )

Correct

Case n

n

The mean life of a sample of 400 bulbs produced by a company is found to be 1600 hours, with a standard deviation of 150 hours Test the hypothesis that the mean life time of the bulbs produced in general is higher than the mean life of 1570 hours at 1% level of significance