Learning Outcomes of the course
What is research?
Need for research
Types of Research
What is a good research?
What is Research?
Research means a systematic investigation, including research development, testing and evaluation, designed to develop or contribute to generalizable knowledge.
Research is disciplined inquiry.
The generic characteristics of this kind of inquiry that are useful criteria for shaping and evaluating our research are the following:
Research should be accessible a public activity, open to scrutiny by peers
transparent clear in its structure, process and outcomes
transferable useful beyond the specific research project, applicable in principles (if not specifics) to other researchers and research contexts.
What is Research?
Research and experimental development comprises creative work undertaken on a systematic basis in order to increase the stock of knowledge, including knowledge of man, culture and society, and the use of this stock of knowledge to devise new applications.
Any activity classified as research and experimental development is characterised by originality; it should have investigation as a primary objective and should have the potential to produce results that are sufficiently general for humanity's stock of knowledge (theoretical and/or practical) to be recognisably increased.
Need for research
To find more information and evidences
To find solutions for problems
To make effective decisions
Components of Research
Applied Research Problem solving - specific
Pure Research or Basic Research
Problem solving non specific/general
Systematic, controlled, empirical, and critical investigation of natural phenomena guided by theory and hypothesis
Types of Study
What is a good research?
Purpose clearly defined
Research process detailed
Research design thoroughly planned
High ethical standards applied
Limitations frankly revealed
Adequate analysis is made
Findings presented unambiguously
Recommendations/suggestion provided for future course of action
Researchers experience reflected
Styles of Thinking
l Empirical study observation and experience Communication Process
l Rational study Facts, known laws or basic truth
l Exposition descriptive statements but no reasons provided Argument: Two types
l Argument allows us to explain, interpret, defend, challenge and explore meaning
Types of Arguments
Deduction: - Conclusive necessarily follow from the reasons given
l These reasons said to imply the conclusion and to represent the proof
l It must be both true and valid
The premises (reason) given for the conclusion must agree with the real world (be true)
Types of Argument
Premise 1 All regular employees can be trusted not to steal
Premise 2: John is a regular employee
Conclusion: John can be trusted not to steal
Types of Argument
Induction: To induce is to draw a conclusion from one or more particular facts or pieces of evidence.
Conclusion explains the facts and facts support the conclusion
The conclusion in an induction, however, is merely a hypothesis
Types of Argument
l Suppose you push the light switch in your room and the light fails to go on.
l This is a fact the light does not go on.
l Conclusion: The light bulb has burnt out
l Reason 1: The light should go on we you push the switch
l Reason 2: If the bulb is burned out the light will not function
l However there could be other reasons
l Therefore the conclusion is a hypothesis (assumption)
Fcat1: Push the light switch and find no light
Induction: ask the question why no light?
Hypothesis: Infer a conclusion (hypothesis) to answer the question the bulb is burned out (hypothesis)
Deduction: Use this hypothesis to conclude that the light will not go on when you push the switch. Know from experience that a burned out bulb will not light.
Refer: Figure 2-2 (page 32)
Understanding Theory: Concepts and Connections
Concept: set of characteristics associated with certain events, objects, or situations
l Concepts should be clear, commonly shared and unambiguous
Importance to Research: (Concepts should be clear)
l Estimating a familys total income.Understanding Theory
l Time period
l Before or after taxes
l Head of the family only or all members
l Income from other sources (salary and wages only of income in kind)
Constructs: Abstract Concepts
l Personality, leadership, motivation, LoveUnderstanding Theory
l Example: Refer Figure 2-4
l To define concepts in the same meaning/synonymUnderstanding Theory
l Helps reduce confusion
l Example: Customer, client, patron, buyer, consumer
l These words might give different meaning in different context, therefore a clear definition is required in a research environment.
l E.g.. Billion, market, weekend
Variables: a symbol to which numbers or values are assigned
l Dichotomous having only two valuesUnderstanding Theory
l Example: male or female, yes or no, employed or unemployed, married or unmarried
l Discrete: having different values but whole number
l Number of students in a class
l Continuous variable: may take any value (infinite)
l Exchange rates, income, weight of gold
Independent variable (IV)
Dependent variable (DV)
The introduction of the four-day work week (IV) will lead to increased office productivity per worker hour (DV)
Performance in exams
Proposition: a statement about concepts that may be judged as true or false if it refers to observable phenomena
Hypothesis: A proposition tested empirically
l Descriptive HypothesisA Good Hypothesis
l Example: Executives in company Z have a higher than average achievement motivation
l Relational Hypothesis
l Example: Foreign cars are perceived by American consumers to be of better quality than domestic cars.
l Case; American consumers
l Variables: country of origin, perceived quality (the nature of relationship between the two variables are not specified)
l Co relational Hypothesis (unspecified relationship)
l Example: No country specific, no size specific, no quality indicator
l Explanatory (causal) Hypothesis (predictable relationship): a price reduction in Japanese cars would lead to their increased demand
Adequate for its purpose
Better than its rivals
Requiring few conditions or assumptions
Theory and Models
Theory: set of interrelated concepts, definitions and propositions that are advanced to explain and predict phenomena (facts)
l Examples (weather theory page 47)
The difference between theory and hypothesis is based on the level of complexity and abstraction. Theories tend to be abstract and involve multiple variables. Hypotheses tend to be simple, two variable propositions involving concrete instances.
Theory and Models
Model: a representation of a system that is constructed to study some aspect of that system or the whole system.
Example: Consumer Buying Behavior Model (AIDA = Awareness, Interest, Desire, and Action)
Lecture 3 The Research Process Refer The Research Process Model Handout Lecture 4 What is a Research Proposal?
A proposal is an offer to produce a product or render a service to the potential buyer or sponsor. The research proposal presents a problem, discusses related research efforts, outlines the data needed for solving the problem, and shows the design used to gather and analyze the data. Research proposals may be Internal or ExternalSections of a Research Proposal
Executive Summary Problem Statement Research Objectives Literature Review Importance/Benefits of the Study Scope of the Study Research Design Data Analysis Nature and Form of Results Qualifications of Researchers Budget Schedule Facilities and Resources Required Limitations of the Study BibliographyEvaluation of a Proposal
Does the proposal offer a focused research question? Where a number of aims are stated, is the primary question clearly specified? Does the proposal convey evidence that the methodological issues raised by the research question have been thought through. Does the student appreciate what kind of data will be required? Is the proposed methodology justified? Does the proposal indicate a familiarity with the appropriate theoretical concepts needed to underpin the project? Is discussion of the theoretical concepts supported by reference to the appropriate literature? Does the proposal include an appropriate preliminary structure? Is there an appreciation of the business issues inherent in the proposalQuestions ? Lecture 5 Research Design
Research design is a plan for selecting the sources and types of information used to answer the research question.
It is a framework for specifying the relationships among the variables under study.
It is a blueprint that outlines each procedure from the hypotheses to the analysis of data. Research Design provides answers for questions like:
What techniques will be used to gather data ?
What kind of sampling will be used?
How will time and cost constraints be dealt with ? Etc.
Major Types of Research Design
1. Exploratory Studies
2. Descriptive Studies
3. Causal Studies
Through exploration researchers develop concepts more clearly, establish priorities, develop operational definitions, and improve the final research design
Exploration helps is
Clarifying management dilemma Finding the practicality of the study Saving time, money and effort
Techniques of exploration may be Qualitative or Quantitative
Secondary Data Analysis Experience Surveys Focus Groups
Secondary Data Analysis
1.Organizations own data archives
2.Prior research studies
3.Published documents like books, journals, periodicals, magazines, government publications
4.Online and electronic sources
Example: If looking for trends in the copper industry, then search for not only copper consumption or copper production but also information about mines and minerals, countries producing copper, information about forecasting techniques, companies dealing in copper etc.
Interview experienced people about ideas, issues or aspects of the subject
Explore various aspects in a flexible investigation format
When studying an automobile assembly plant, the researcher can find information, through interviews, from:
New employees to the plant
Extremely high/low productive employees
First line supervisors
Managers of the plant
A panel of 6 to 10 people led by a trained moderator who meet for 90 minutes to 2 hours exchanging ideas, feelings and experiences on a specific topic
Highly useful in generation and evaluation of new ideas.
Homogeneity within focus groups should be maintained based on the target population under study
Recording and analysis of information can be done through notepads, audio-visual equipments.
Trends in Focus Groups include:
Telephone Focus Groups
Videoconferencing Focus Groups
Online Focus Groups (BMW Club)
The objective of a descriptive study is to learn the who, what, when, where, and how of a topic.
E.g. If studying the accounts of people at a bank, the researcher might want to get information about:
Number and types of accounts,
Size of accounts,
Number of accounts opened in last six months,
Number of transactions and their purpose etc.
Descriptive studies can help develop hypothesis:
E.g. Why do people living far off have accounts in a particular bank
Hypothesis 1: They used to live close by when account was opened by them
Hypothesis 2: They live far but work close to the bank
Hypothesis 3: They use internet banking which makes them feel near to bank.
Seeks to discover the effect that a variable(s) has on another (or other), or why certain outcomes are obtained.
A, B AND C LEADS TO Z
B, C AND D LEADS TO Z C, D AND E LEADS TO Z A, B AND D DOES NOT LEAD TO Z Thus there is a causal relationship between C and Z
(But there may be other external factors too)
Causal Relationships Symmetrical Relationships : Two variables fluctuate together, not because of changes in the other, but due to some other third factor.
E.g. Low attendance in class and poor participation in college events events due to work pressure among evening students.
Reciprocal Relationship: Mutual influence over each other
E.g. Reading an advertisement leads to use of a particular brand, which in turn sensitizes user to notice and read more advertisements of that particular brand.
Asymmetrical Relationships : Changes in one variable (Independent Variable) is responsible for changes in another variable (Dependent Variable)
Types of Asymmetrical Relationships
StimulusResponse: A price rise leads to decreased demand
Property-Disposition: Effects of age (property) on attitude towards saving (disposition)
Disposition-Behavior: Opinion about brand (disposition) and its purchase (behavior)
Property-Behavior: Stage of family life-cycle (property) and purchase of furniture (behavior)
What is Measurement?
To measure is to discover the extent, dimensions, quantity, or
capacity of something, especially by comparison with a standard.
Steps in Measurement
Select the events you want to measure
Use numbers/symbols to represent aspects of the events.
E.g. What is your opinion of the styling of the Jaguar Car ?
Very Desirable 5 4 3 2 1 Very Undesirable
Errors in Measurement
The Respondent as an Error Source: E.g. the respondent may be bored, tired, hungry, getting late for meeting etc.
Situational Factors: is anonymity being maintained?, where is the research being conducted at home, in street?, are other people present too?
The Measurer as a Source of Error: Bias of interviewer, rephrasing of questions, prompting with smiles, nods etc - encouraging or discouraging responses, data entry errors.
The Instrument as a Source of Error: confusing, ambiguous, poor printing, limited space, too little/too much choice, color, layout etc.
Validity: refers the extent to which a test measures what we actually wish to measure.
Reliability: accuracy and precision of a measurement
Practicality: is the research economic, convenient and interpretable.
Weigh yourself using a bathroom scale
If the scale measures your weight correctly, then it is both reliable and valid.
If it consistently overweighs you by six pounds, then the scale is reliable but not valid.
If the scale measures erratically from time to time, then it is not reliable and not valid.
If you use a kitchen scale for weighing yourself, then it is not even practical, leave alone reliable and valid !!!
The procedure by which we assign numbers to opinions, attitudes,
and other concepts.
Types of Rating Scales (See Handout)
- E.g. Yes or No Multiple Choice
- E.g. Single, Engaged, Married, Divorced, Likert Scale
- E.g. Strongly disagree, Disagree, Neither agree nor disagree, Agree, Strongly agree Semantic Differential
- E.g. Modern ---------------------------- Old Fashioned Importance Scale
- E.g. Extremely important, Very important, Somewhat important, Not very important, Not at all important Rating Scale
- E.g. Excellent, Very good, Good, Fair, Poor Intention-to-buy Scale
- E.g. Definitely buy, Probably buy, Not sure, Probably not buy, Definitely not buy Graphic Rating Scale
- using various methods like sentence completion, word association, picture completion, thematic apperception test, story completion etc.
The basic idea of sampling is that by selecting some of the elements in a population, we
may draw conclusions about the entire population.
Population: The total collection of elements about which we wish
to make some inferences.
Census: Counting all the elements in a population.
A good sample has no bias
A good sample may have an error that is not more than the
acceptable limits for the studs purpose.
Types of Sampling
Simple Random Sampling - Each population element has a known & equal chance of being selected in the sample. E.g Lottery
Complex Random Sampling:
Systematic : Every nth item is chosen in the sample, beginning with a random start for the choice of n. E.g. 4, 8, 12, 16
Stratified : Divide population into subpopulations (strata) and use simple random on each strata. E.g. UAE divided into seven strata i.e. the seven emirates.
Cluster : Population is divided into groups, and some groups are randomly selected for study. E.g. Select any two emirates randomly from the seven clusters and study them in detail.
Double/Sequential/Multiphase: Collect some information by sample and then use this information as the basis for selecting a sub-sample. E.g. Sample of Nissan car owners, sub sample of Nissan car owners who have more than one car.
Convenience Sampling Researchers freely choose whomever they find according to their convenience. E.g. Friends in a class, locality etc.
Purposive Sampling A non-probability sample that conforms to certain
criteria. It includes:
Judgment Sampling: Researcher selects sample members to conform to some criterion. E.g. Studying problems of employees who faced on-the-job discrimination in a study of labor problems.
Quota Sampling: Subjects are selected to conform to certain pre-designated control measures that secure a representative cross section of the population. E.g. Studying Skyline college students satisfaction, we could divide the population into four quotas CIW, BAM, BAI, BAT
Snowball Sampling: referral approach to reach hard-to-find respondents. E.g. Reaching ministers through a reference of another minister.
Lecture 7 Secondary Data Sources
Secondary Data - Data gathered and recorded by someone else prior to and for a purpose other than the current project
Secondary Data is often:
Needs no access to subjects
Advantages of Secondary Data
Information is not Otherwise Accessible
Disadvantages of Secondary Data
Data Not Consistent with Needs
Inappropriate Units of Measurement
Time Period Inappropriate (Outdated/Obsolete)
Objectives of Secondary Data Studies
Data Based Marketing
Identify consumer behavior
Analysis of trade areas
Data Based Marketing - Practice of maintaining a customer data base
Responses to past efforts
Data from numerous sources
Created, recorded, or generated by an entity other than the researchers organization
Newspapers and journals
Books and periodicals
Market share data companies like A.C. Nielsen provide information about sales volume and brand share over time
Demographic and census updatesmany organizations supply census updates, in easy-to-use or custom formats
Commercial Sources - Attitude and public opinion researchsyndicated services report the findings of opinion polls
Consumption and purchase behavior data
Advertising researchreadership and audience data
Secondary Data Collection Example
Lecture 8 Data Collection Methods
Surveys - asking respondents
for information using
verbal or written questioning
Gathering Information Via Surveys
Tree Diagram of Total Survey Error
Random Sampling Error - A statistical fluctuation that occurs because of change variation in the elements selected for the sample
Errors in Data Collection
Sample bias - when the results of a sample show a persistent tendency to deviate in one direction from the true value of the population parameter
Respondent error - a classification of sample bias resulting from some respondent action or inaction
l Non-response bias
l Response bias
Nonrespondents - people who refuse to cooperate
l Over-represents extreme positions
l Under-represents indifference
Response Bias - a bias that occurs when respondents tend to answer questions with a certain slant that consciously or unconsciously misrepresents the truth
Acquiescence Bias - A category of response bias that results because some individuals tend to agree with all questions or to concur with a particular position. YES YES YES
Extremity Bias - A category of response bias that results because response styles vary from person to person; some individuals tend to use extremes when responding to questions.
Social Desirability Bias - Bias in responses caused by respondents desire, either conscious or unconscious, to gain prestige or appear in a different social role.
Interviewer Bias - A response bias that occurs because the presence of the interviewer influences answers.
Auspices Bias - Bias in the responses of subjects caused by the respondents being
influenced by the organization conducting the study.
Improper administration of the research task
Interviewer cheating - filling in fake answers or falsifying interviewers
Data processing error - incorrect data entry, computer programming, or other procedural errors during the analysis stage.
Sample selection error -improper sample design or sampling procedure execution.
Interviewer error - field mistakes
Time Period for Surveys
Cross Sectional Study
A study in which various segments of a population are sampled
Data are collected at a single moment in time
A survey of respondents at different times, thus allowing analysis of changes over time.
Tracking study - compare trends and identify changes
l consumer satisfaction
A longitudinal survey of the same sample of individuals or households to record (in a diary) their attitudes, behavior, or purchasing habits over time
Communicating with Respondents
l Shopping mall intercepts
l Mail Survey
l E-mail Survey
l Internet Survey
Door-to-Door Personal Interview
Speed - Moderate to fast
Geographical flexibility - Limited
Respondent cooperation Excellent
Questionnaire length - Long
Item non-response - Low
Respondent misunderstanding Low
Degree of interviewer influence - High
Supervision of interviewers - Moderate
Anonymity of respondent Low
Ease of call back or follow-up - Difficult
Cost - Highest
Special features - Visual materials may be shown extended probing possible
Mall Intercept Personal Interview
Speed of Data Collection - Fast
Geographical Flexibility - Confined, urban bias
Respondent Cooperation - Moderate
Versatility of Questioning Extreme
Questionnaire length - Moderate to long
Item non-response -Medium
Respondent misunderstanding -Lowest
Interviewer influence of answers -Highest
Supervision of interviewers - Moderate to high
Anonymity of respondent - Low
Ease of call back or follow-up - Difficult
Cost - Moderate to high
Special features - Taste test, viewing of TV commercials possible
Speed of Data Collection - Very fast
Geographical Flexibility -High
Respondent Cooperation - Good
Versatility of Questioning - Moderate
Questionnaire Length - Moderate
Item Non-response -Medium
Respondent Misunderstanding - Average
Interviewer Influence of Answer - Moderate
Interviewers Supervision - High with central location
Anonymity of respondent - Moderate
Ease of call back or follow-up- Easy
Cost - Low to moderate
Special features - Fieldwork & supervision simplified; Computer-assisted/ Voice activated interviews
Speed - no control over return of questionnaire; slow
Geographical flexibility - High
Respondent cooperation - Moderate--poorly designed questionnaire will have low response rate
Questionnaire length - Varies
Item non-response - High
Respondent misunderstanding no clarification
Degree of interviewer influence - None
Supervision of interviewers - Not applicable
Anonymity of respondent -High
Ease of call back or follow-up - Easy, but takes time
Cost - Lowest
E-Mail Questionnaire Surveys
Speed of data collection - Instantaneous
Geographic flexibility - worldwide
Cheaper distribution and processing costs
Flexible, but - Extensive differences in the capabilities of respondents computers and e-mail software limit the types of questions and the layout
E-mails are not secure and eavesdropping can possibly occur
Respondent cooperation is e-mail spam?
Speed of data collection - Instantaneous
Cost effective, worldwide flexibility
Respondent cooperation varies
Versatility of questioning - extreme
Questionnaire length flexible
Respondent misunderstanding -high
Interviewer influence of answers - none
Anonymity of Respondent anonymous/known
Ease of Follow-up easy if e-mail known
Special Features - allows graphics and streaming media but limited internet availability, poor computer skills of people
Determine Appropriate Technique
There is no best form of survey; each has advantages and disadvantages.
Is the assistance of an interviewer necessary?
Are respondents interested in the issues being investigated?
Will cooperation be easily attained?
How quickly is the information needed?
Will the study require a long and complex questionnaire?
How large is the budget?
Do Pretesting - A trial run with a group of respondents to iron out fundamental problems in the instructions of survey design
Research Methods Academic Home Page