RESEARCH METHODOLOGY
RESEARCH METHODOLOGY
Steps in Research : 1. objectivity2. Problem formulation3. Literature study4. Research design5. Formulation of Hypothesis 6. Sampling7. Data collection8. Processing and analysis of data9. Interpretation and recommendation10. Report writing
Survey
A survey is a process by which certain quantitative/qualitative facts pertaining to certain field of enquiry are collected to throw light on the objectives of a research problem.
A descriptive surveys are fact finding surveys
An analytical surveys deal with interrelations among different variables of interest and their interaction
A survey is a planned observation of objects that are not controlled by the observer.
These objects are not themselves treated but the ‘Nature’ is assumed to have applied the treatments and all that analysts can do it to observe the consequences.
A Survey of complete enumeration of population of interest is called Census.
A Survey based on a subset of the population which is also called as a sample is termed as sample survey.
Sampling or Sampling techniques
A sample as the name implies is smaller representative of a larger whole.
The method of selecting a portion of the universe for the study is known as sampling.
It helps to draw conclusions about the said universe
The entire group from which a sample is chosen is known as the population or universe
Census: A complete enumeration of all items in the population is known as census enquiry
Sampling frame: It is a list of items from which the sample is to be drawn.
Sampling methods or Sampling techniques Sampling Designs:
Two generic types:1. Probability or random sampling, and 2. Non-probability or Non-random sampling
Probability or random sampling
A. Simple designs1. Simple random sampling2. Stratified random sampling3. Systematic random sampling
B. Complex designs4. Cluster sampling5. Area sampling6. Multi-stage and sub-sampling
Non-probability or Non-random sampling
A. Simple designs Convenience or accidental sampling Purposive (or Judgement ) samplingB. Complex designs1. Quota sampling2. Snow-ball sampling
Reasons for choosing different sampling designs.
1. Nature of population2. Simplicity in adoption3. Availability of frame4. Representativeness5. Nature of sampling unit6. Cost of enumeration7. Precision criterion
Probability or random sampling
A. Simple designs1. Simple random sampling Simple random sampling is the simplest of
all sampling designs Each and every item in the population has
an equal and independent chance of inclusion
This can be done for a homogenous population.
However for heterogeneous population a simple random sampling may not give the desired results.
2. Stratified random sampling This is used for a heterogeneous
population. Here the population is stratified
(Grouped) into a number of overlapping sub-populations or strata and sample items are selected from each stratum.
Ex: In survey of business establishments, one may form large, medium and small establishments.
Further the sample selection from each strata is based on simple random selection.
3. Systematic random sampling Only the first unit is selected randomly and the
remaining units of the sample are selected at fixed intervals.
Ex: To choose every 10th name or 15th item and so on
In this method the entire list of the universe is given numbers
It is easier and less expensive It is spread more evenly over the entire
population The main disadvantage is if there is a hidden
periodicity in the population, this may prove inefficient.
B. Complex designs1. Cluster sampling : This involves grouping of population and then
selecting the groups or clusters rather than individual elements for inclusion in the sample.
That is the total population is divided into a number of relatively small subdivisions which are themselves clusters of smaller units.
Further some of these clusters are randomly selected for inclusion in the overall selection
2. Area sampling Cluster sampling in the form of grids
imposed on maps in certain forms are is termed as Area sampling.
It will not be grouped by type of establishments like villages, industries, hospitals etc but based on areas.
Ex: National population or well defined political or natural boundaries.
Non-probability sampling
This sampling does not provide a chance of selection to each population
The selection probability is knownA non-probability sample may not be true
representativePopulation parameters cannot be estimated
from the sample valuesIt suffers from sampling bias which suffers
from bias.Hence generally not advisable
When there is no other feasible method for collection of data or non-availability of population for collection of data.
When study does not need generalisation of conditions
When cost is a considerationWhen probability sampling needs more time.
Non-probability or Non-random sampling
A. Simple designs1. Convenience or accidental sampling2. Judgment samplingB. Complex designs3. Quota sampling4. Snow-ball sampling
Non-probability or Non-random sampling
A. Simple designs1. Convenience or accidental sampling: This method is employed to get information
quickly and inexpensively Depends on the convenience of the
researcher Keeps in view of the general population
3. Judgment sampling: Judgment sampling is very appropriate
when it is necessary to reach small and specialized populations.
The researcher uses judgment to identify representative samples
A judgmental sampling is likely to be more reliable and representative than a probability sample.
However unwelcome bias might creep into results if not honestly judged.
Complex designs1. Quota sampling: We observe the responding units non-
randomly according to some fixed quota It is to assure that the smaller groups are
adequately represented Bias can exist
2. Snow-ball sampling First someone is identified who meets
the criteria and further asked to include others.
Useful where representatives are inaccessible or hard to find
Inherent problem is one who is socially visible are likely to be selected.
Data Collection
Data are facts, figures and other relevant materials, past and present serving as basis for study and analysis.
Types of sources of data1. Primary data2. Secondary Data
1. Primary data are those which are collected afresh and for the first time and thus happens to be original in character
2. Secondary data are those which have already been collected by someone else and which have salready been passed through statistical process.
Primary data
1. Primary data Primary data are those which are collected afresh, for the first time and thus happens to be original in character.
2. First formal appearance of results in the print or electronic literature.
Secondary data
1. Secondary data are those which have already been collected by someone else and which have already been passed through statistical process.
2. Secondary sources are works that describe, interpret, analyse primary data
3. Comments and discussion of the evidence provided by primary sources
Processing of Data
Data processing is an intermediary stage of work between data collection and data interpretation
The steps involved in processing of data may be stated as:1. Identifying data structures2. Editing the data3. Coding and classifying the data4. Transcriptions of data5. Tabulation of data
Editing the data Data editing at he time of recording the data Data editing at the time of analysis of data
CompletenessAccuracyUniformity
Coding and Numeric coding Alphabetic coding Zero coding
Classification
Tabulation Manual tabulation
Graphs/Charts/DiagramsLine GraphsBar chartsHistogramsFrequency plygonOgiveLorenz curveBar charts
Vertical bar charts Horizontal bar charts
Pie chartspictograms
Line graphs are useful for showing changaes in data relationships.
The horizontal line is the x-axis and verical line is the y-axis
A bar chart or bar graph is a chart with rectangular bars with lengths proportional to the values that they represent. The bars can be plotted vertically or horizontally.
Bar charts are used for plotting discrete (or 'discontinuous') data i.e. data which has discrete values and is not continuous.
A histogram is a graphical representation, showing a visual impression of the distribution of data. It is an estimate of the probability distribution of a continuous variable and was first introduced by Karl Pearson.
A histogram consists of tabular frequencies, shown as adjacent rectangles, erected over discrete intervals (bins), with an area equal to the frequency of the observations in the interval.
Frequency polygonIn laying out a frequency polygon instead of
drawing a histogram, the frequency of each class is located at the midpoint of the interval and straight line to connect the plotted points.
An Ogive is a line chart plotted on graph paper from a cumul;ative ferquency distribution
Lorenz Curve is a line chart used to compare the proportionality in two quantities variables.
The circle or pie chart is a component parts bar chart from the segments of the circle.
It is usually a percentage chart
A pictogram uses symbols which may be appropriate for the type of data.
Statistical analysis of data
PurposeTypes of statistical analysis
Descriptive analysis Inferential analysis
Statitiacl estimation Testing of hypothesis
Types of Statistical analysis Measures of central tendency Measures of dispersion Measures of association/ relations Analysis of variance Hypothesis testing Tests of significance Time series analysis
Methods of collecting Primary data.
In many cases the secondary data are inappropriate, inadequate or obsolete, primary data have to be gathered.
Primary data are directly collected by the researcher from their original source
Method is different from a tool One or more methods can be chosen No method is universal but has its own
uniqueness
1. Observation2. Interviewing3. Mail survey4. Experimentation5. Simulation6. Projective technique
Observation:Observation is defined as a systematic
viewing of a specific phenomenon in its proper setting for the specific purpose of gathering data for a particular study.
Observation includes both seeing and hearing.
The main body of knowledge has been developed by observing the nature
Observation
Participant observation
Non- participant observation
Direct observation
Indirect observation
Controlled observation
Un-controlled observation
Researcher’s Role
Mode of Observation
System Adopted
Interviewing
One of the prominent method of data collectionPeople are generally more willing to talk than to
writeIt is two way systematic conversation between an
investigator and an informant initiated for obtaining information relevant to a specific study.
It is not only conversation, but also learning from the respondent's gestures, expressions, pauses and environment
It is carried out in a structured scheduleIt calls for interviewing skills
Interviewing can be used as a main method or a supplementary method
It is the only method for gathering information from illiterate and uneducated method.
It can be used for collecting personal and intimate information relating to a person’s opinions, attitudes, values, future intentions etc.
Questionnaire
A questionnaire is a series of questions asked to individuals to obtain statistically useful information about a given topic.
When properly constructed and responsibly administered, questionnaires become a vital instrument
Questionnaires are frequently used in quantitative research.
They are a valuable method of collecting a wide range of information from a large number of individuals, often referred to as respondents. Good questionnaire construction is critical to the success of a survey.
Types of questions1.Contingency questions - A question that is
answered only if the respondent gives a particular response to a previous question. This avoids asking questions of people that do not apply to them
2.Matrix questions - Identical response categories are assigned to multiple questions.
3.Closed ended questions - Respondents’ answers are limited to a fixed set of responses. Most scales are closed ended. Other types of closed ended questions include: 1. Yes/no questions - The respondent answers with a “yes”
or a “no”. 2. Multiple choice - The respondent has several option
from which to choose. 3. Scaled questions - Responses are graded on a
continuum (example : rate the appearance of the product on a scale from 1 to 10, with 10 being the most preferred appearance). Examples of types of scales include the Likert scale, semantic differential scale, etc
Open ended questions - No options or predefined categories are suggested. The respondent supplies their own answer without being constrained by a fixed set of possible responses. Examples of types of open ended questions include:
1. Completely unstructured - For example, “What is your opinion of questionnaires?”
2. Word association - Words are presented and the respondent mentions the first word that comes to mind.
3. Sentence completion - Respondents complete an incomplete sentence. For example, “The most important consideration in my decision to buy a new house is . . .”
4. Story completion - Respondents complete an incomplete story.
5. Picture completion - Respondents fill in an empty conversation.
6. Thematic apperception test - Respondents explain a picture or make up a story about what they think is happening in the picture
Question sequence1. Questions should flow logically from one to the
next. 2. The researcher must ensure that the answer to
a question is not influenced by previous questions.
3. Questions should flow from the more general to the more specific.
4. Questions should flow from the least sensitive to the most sensitive.
5. Questions should flow from factual and behavioral questions to attitudinal and opinion questions.
6. Questions should flow from unaided to aided questions.
7. The sandwich theory - three stage theory : Initial questions should be screening and rapport questions. Then in the second stage you ask all the product specific questions. In the last stage you ask demographic questions
Research Design- Data collectionObservational researchEthnographic group ResearchFocus group ResearchSurvey researchBehavioral dataExperimental research( cause & effect
relationships)
- Research instrumentQuestionnaires:Close-endOpen-endMechanical instruments: like,Galvanometers-emotionsTachistoscopes flashesEye camerasAudiometer-TV- Sampling plan
Field work- Planning and supervisionData Analysis- Classifying raw data- Summarising data- Analytical methods to analyse and then
make an inference
Iceberg principle Observation that in many (if not most) cases only a very
small amount (the 'tip') of information is available or visible about a situation or phenomenon, whereas the 'real' information or bulk of data is either unavailable or hidden. The principle gets its name from the fact that only about 1/10th of an iceberg's mass is seen outside while about 9/10th of it is unseen, deep down in water.
Formulation of Hypothesis
Hypotheses is an imaginary, verifiable statement which is a possible answer to the research question.
It is a tentative proposition formulated for empirical testing.
It is tentative because its veracity can be tested only after it has been tested empirically
They are useful and they guide the research process in the particular direction
In exploratory and Descriptive studies hypothese may not be required but it is essential in all analytical and experimental studies
Types of Hypotheses
With reference to their function:Discreptive and Relational
hypotheses, Casual HypothesesWith ref. to working
Null hypotheses, working hypotheses and Statistical hypotheses
Level of abstraction:Common sense Hypotheses, Complex
Hypotheses and analytical Hypotheses
Types of Hypotheses
With reference to their function:Dicretive and Relational hypotheses,
Casual HypothesesWith ref. to working
Null hypotheses, working hypotheses and Statistical hypotheses
Level of abstraction:Common sense Hypotheses, Complex
Hypotheses and analytical Hypotheses
Types of Hypotheses
With reference to their function:Dicretive and Relational hypotheses,
Casual HypothesesWith ref. to working
Null hypotheses, working hypotheses and Statistical hypotheses
Level of abstraction:Common sense Hypotheses, Complex
Hypotheses and analytical Hypotheses
Types of Hypotheses
With reference to their function:Dicretive and Relational hypotheses,
Casual HypothesesWith ref. to working
Null hypotheses, working hypotheses and Statistical hypotheses
Level of abstraction:Common sense Hypotheses, Complex
Hypotheses and analytical Hypotheses
Six Thinking Hats The de Bono Hats system (also known as "Six Hats" or
"Six Thinking Hats") is a thinking tool for group discussion and individual thinking. Combined with the idea of parallel thinking which is associated with it, it provides a means for groups to think together more effectively, and a means to plan thinking processes in a detailed and cohesive way. The method is attributed to Dr. Edward de Bono and is the subject of his book, Six Thinking Hats.
The paternity of this method is disputed by the School of Thinking.
The method is finding some use in the UK innovation sector, is offered by some facilitation companies and has been trialled within the UK civil service.
Six distinct states are identified and assigned a color: Information: (White) - considering purely what
information is available, what are the facts? Emotions (Red) - instinctive gut reaction or statements
of emotional feeling (but not any justification) Bad points judgment (Black) - logic applied to
identifying flaws or barriers, seeking mismatch Good points judgment (Yellow) - logic applied to
identifying benefits, seeking harmony Creativity (Green) - statements of provocation and
investigation, seeing where a thought goes Thinking (Blue) - thinking about thinking
Data Collection
Data are facts, figures and other relevant materials, past and present serving as basis for study and analysis.
Types of sources of data1. Primary data2. Secondary Data
1. Primary data are those which are collected afresh and for the first time and thus happens to be original in character
2. Secondary data are those which have already been collected by someone else and which have salready been passed through statistical process.
Primary data
1. Primary data Primary data are those which are collected afresh, for the first time and thus happens to be original in character.
2. First formal appearance of results in the print or electronic literature.
Secondary data
1. Secondary data are those which have already been collected by someone else and which have already been passed through statistical process.
2. Secondary sources are works that describe, interpret, analyse primary data
3. Comments and discussion of the evidence provided by primary sources
Methods of collecting Primary data.
In many cases the secondary data are inappropriate, inadequate or obsolete, primary data have to be gathered.
Primary data are directly collected by the researcher from their original source
Method is different from a tool One or more methods can be chosen No method is universal but has its own
uniqueness
1. Observation2. Interviewing3. Mail survey4. Experimentation5. Simulation6. Projective technique
Observation:Observation is defined as a systematic
viewing of a specific phenomenon in its proper setting for the specific purpose of gathering data for a particular study.
Observation includes both seeing and hearing.
The main body of knowledge has been developed by observing the nature
Observation
Participant observation
Non- participant observation
Direct observation
Indirect observation
Controlled observation
Un-controlled observation
Researcher’s Role
Mode of Observation
System Adopted
Interviewing
One of the prominent method of data collectionPeople are generally more willing to talk than to
writeIt is two way systematic conversation between an
investigator and an informant initiated for obtaining information relevant to a specific study.
It is not only conversation, but also learning from the respondent's gestures, expressions, pauses and environment
It is carried out in a structured scheduleIt calls for interviewing skills
Interviewing can be used as a main method or a supplementary method
It is the only method for gathering information from illiterate and uneducated method.
It can be used for collecting personal and intimate information relating to a person’s opinions, attitudes, values, future intentions etc.
Questionnaire
A questionnaire is a series of questions asked to individuals to obtain statistically useful information about a given topic.
When properly constructed and responsibly administered, questionnaires become a vital instrument
Questionnaires are frequently used in quantitative research.
They are a valuable method of collecting a wide range of information from a large number of individuals, often referred to as respondents. Good questionnaire construction is critical to the success of a survey.
Types of questions1.Contingency questions - A question that is
answered only if the respondent gives a particular response to a previous question. This avoids asking questions of people that do not apply to them
2.Matrix questions - Identical response categories are assigned to multiple questions.
3.Closed ended questions - Respondents’ answers are limited to a fixed set of responses. Most scales are closed ended. Other types of closed ended questions include: 1. Yes/no questions - The respondent answers with a “yes”
or a “no”. 2. Multiple choice - The respondent has several option
from which to choose. 3. Scaled questions - Responses are graded on a
continuum (example : rate the appearance of the product on a scale from 1 to 10, with 10 being the most preferred appearance). Examples of types of scales include the Likert scale, semantic differential scale, etc
Open ended questions - No options or predefined categories are suggested. The respondent supplies their own answer without being constrained by a fixed set of possible responses. Examples of types of open ended questions include:
1. Completely unstructured - For example, “What is your opinion of questionnaires?”
2. Word association - Words are presented and the respondent mentions the first word that comes to mind.
3. Sentence completion - Respondents complete an incomplete sentence. For example, “The most important consideration in my decision to buy a new house is . . .”
4. Story completion - Respondents complete an incomplete story.
5. Picture completion - Respondents fill in an empty conversation.
6. Thematic apperception test - Respondents explain a picture or make up a story about what they think is happening in the picture
Question sequence1. Questions should flow logically from one to the
next. 2. The researcher must ensure that the answer to
a question is not influenced by previous questions.
3. Questions should flow from the more general to the more specific.
4. Questions should flow from the least sensitive to the most sensitive.
5. Questions should flow from factual and behavioral questions to attitudinal and opinion questions.
6. Questions should flow from unaided to aided questions.
7. The sandwich theory - three stage theory : Initial questions should be screening and rapport questions. Then in the second stage you ask all the product specific questions. In the last stage you ask demographic questions
Research Design- Data collectionObservational researchEthnographic group ResearchFocus group ResearchSurvey researchBehavioral dataExperimental research( cause & effect
relationships)
- Research instrumentQuestionnaires:Close-endOpen-endMechanical instruments: like,Galvanometers-emotionsTachistoscopes flashesEye camerasAudiometer-TV- Sampling plan
Field work- Planning and supervisionData Analysis- Classifying raw data- Summarising data- Analytical methods to analyse and then
make an inference
Application of research :- Sales and market analysis- Product research- Corporate research- Advertising research
Barriers to the use of MR
A narrow conception of Marketing ResearchUneven caliber of Marketing researchersPoor framing of the problemLate and erroneous findings by marketing
researchPersonality and presentational differences.
3. Decomposition method:The company’s previous periods sales data is
broken into four major components Trend, cycle, seasonal and erratic
4. Naive/Ratio method: Time seriesSales forecast for next year=Actual sales of this year x Actual sales of this year
Actual sales of last year
6. Regression analysis: Company sale is dependent on many factors such as price, promotional expenditure, population etc. Statistical forecasting - SPSS used- Multiple regression analysis is used
7. Econometric analysis : Many regression equations are built to forecast industry sales. A forecast is prepared by solving these equations on computer software.
To improve forecasting accuracy:
1. Use multiple forecasting methods2. Identify suitable method3. Obtain a range of forecasts4. Use computer hardware and software.
Steps in sales forecastingAs per the conference board of America report 1978, 10 steps
are listed.
1. Determine the Purpose for which Forecasts are used
2. Divide the company products into homogenous groups
3. Determine the factors affecting the sales of each product and their relative importance
4. Choose the forecasting methods5. Gather the available data6. Analyse the data7. Check and recheck the deductions8. Make assumptions regarding other factors9. Convert deductions and assumptions into
forecasts10. Apply the forecast to company operations
Sales Budget
A sales budget consists of estimates of expected volume of sales and selling expenses.
Sales budget is generally fixed slightly lower than the sales forecast to avoid risk
Selling expense budget consists of the selling expense budget and sales department administrative budget
The sales budget is the key factor for the successful performance of the sales department
Sales Budget
Sales volume budgetSales department
Administrative budget Selling expense budget
Purposes of the sales budget
1. Planning: From total corporate plan marketing and sales budgets are developed considering sales goals, sales strategy, action plan, expense, etc.
2. Coordination: Coordinating among various functions
3. Control : Evaluation of performance
Methods used for deciding sales expenditure budget
Sales managers are required to decide expenditure levels for each item of selling expenses.
1. Percentage of sales method
2. Executive judgment method
3. Objective and task method
Review Situation
Communication
Subordinate budgets
Approval of budget
Other departments
Sales Budget Process
STATISTICS
The word Statistics means an ‘organised political state’ in German
Organised numerical dataIt is a numerical statement of facts in any
department of enquiry placed in relation to each other.
Interview Guides and Schedules
Interview Guides Schedules Types of Interviews
Structured directive Interviews Unstructured or Non-directive Interview Focused Interview Clinical interview Depth Interview
Interviewing process1. Preparation 2. Introduction3. Developing rapport4. Carrying the interview forward5. Recording the interview
6. Closing the Interview
Interview problemsInadequate responseInterviewer’s biasNon-responseNon-availabilityRefusalInaccebility
Telephonic interview