Marketing Research ch-5, 6, 7 ,8, 10, & 12.ppt

8/10/2019 Marketing Research ch-5, 6, 7 ,8, 10, & 12.ppt

1/396

CHAPTER-FIVE

QUALITATIVE RESEARCH METHODS

5.1. QUALITATIVE RESEARCH

is a systematic mode of inquiry intocomplex social structures, interactions, or

processes by employing observational,

interpretive, and naturalistic approaches.

1


2/396

Qualitative Researchinvolves finding out

what people think, and how they feel - or

at any rate, what they say they think and

how they say they feel. This kind of information is subjective.

It involves feelings and impressions,rather than numbers.

2


3/396

Qualitative Researchers study things(people

and their thoughts) in their natural settings,attempting to make sense of, or interpret,

phenomena in terms of the meanings people

bring to them.

qualitative refers to the type of data being

collected (which is often textual data, as

opposed to quantitative or numeric data),

3


4/396

Distinctions from Quantitative

Research

The distinction lies on

1. paradigmatic sense and in a

2. data-or iented sense

4


5/396

1. PARADIGMATIC SENSE

qualitative is based on the assumption that social

reality is not singular or objective,

but is rather shaped by human experiences and

social contexts (ontology), and

is therefore best studied within its socio-historic

context by reconciling the subjective

interpretations of its various participants

(epistemology). 5


6/396

In contrast, quantitative research assumes

that the reality is relatively independent of

the context, and can be abstracted from their

contexts and studied using objective

techniques such as standardized measures.

6


7/396

The control and generalizability of

quantitative research are traded in qualitative

research for contextual detail and deeper

understanding of the phenomenon of

interest.

7


8/396

2. DATA-ORIENTED SENSE

qualitative research relies mostly on nonnumeric

data,

however, quantitative research relies numericdata for

Hence, qualitative research is not amenable to

statistical procedures such as computation of means or

regression coefficients.

8


9/396

Although qualitative data is sometimes coded

quantitatively by ratters into categories and

frequencies, the coded data is not statistically

analysed,

9


10/396

OTHER MINORDIFFERENCESQualitative Research Quantitative research

S

ampling

Techn

ique

employs Purposivesampling strategy

cases are selected based on

whether they possess

certain desired contextualcharacteristics

convenience samples and

small samples are

considered acceptable inqualitative research as long

as they fit the unique

requirements of a given

context

random sampling (or avariation of this technique)

cases are chosen randomly

from a population

but not in quantitativeresearch

10


11/396

.

11

Qualitative Research Quantitative research

role

of

therese

arc

her

receives critical attention

considered part of the socialphenomenon, and her/his specific

role and involvement in the

research process must be made

clear during data analysis such as ethnography, action

research, and participant

observation

qualitative methods, such as caseresearch, the researcher must take

a neutral or unbiased stance

during the data collection and

analysis processes

the researcher is

considered to beexternal to and

independent of

data collectionand analytic

procedures


12/396

Analysis is holistic and contextual reductionist andisolationist

Interpretations

tend to focus on language,signs, and meanings, from the

perspective of the actors

involved in the social

phenomenon

Heavily statisticaltechniques

Benefit ability to modify the research

process or even change the

research questions at a late

stage of the project during orafter data collection

data collection and analysis is

often done simultaneously

and iteratively

research project cannot

be modified or changed

once the data collection

has started withoutredoing the entire project

from the start

12


13/396

Benefits and Challenges of Quantitative Re.

Advantages

1. well-suited for exploring hiddenreasons behind complex, interrelated,

or multifaceted social processes such as inter-firm relationships or

inter-office politics

where quantitative evidence may be

biased, inaccurate, or otherwise

difficult to obtain. 13


14/396


15/396

Disadvantage

1.tends to consume more time andresources

Care should be taken to collect

adequate data: too little data can lead to false or

premature assumptions,

too much data may not be effectively

processed by the researcher

15


16/396

2. requires well-trained researchers

who can conduct such research

without injecting their personalbiases or preconceptions into the

studys design,

data collection, or

data analytic procedures

16


17/396

Given the subjective nature of

qualitative interpretation, theresearcher must be careful to interpret

the social phenomenon from theperspectives of the actors embedded in

that phenomenon, and not from her

own personal viewpoints, since she is

not part of the social context 17


18/396

3. all participants or data sources may not be

equally credible,

unbiased, or

knowledgeable about the phenomenon of

interest,

or may have undisclosed political agendas,

which may lead to misleading or false

impressions. 18


19/396

4. given the heavily contextualized nature of

inferences drawn from qualitative research,

such inferences do not lend themselves well to

replicability or generalizability.

Finally, qualitative research may sometimes

fail to answer the research questions of

interest or predict future behaviours

19


20/396

Characteristics of qualitative

research1. NATURALISTIC INQUIRY:

assumes that social phenomena is situated within

and cannot be isolated from its social context,

the findings of such research must be interpreted

within the socio-historical context in which the

phenomena are embedded 20


21/396

This implies that contextual variables should

be observed and considered in seeking

explanations of a phenomenon of interest

although context sensitivity limits

generalizability of inferences

21


22/396

2. RESEARCHER AS INSTRUMENT:

Observations must be interpreted through the eyes of the

social actors embedded in the social phenomenon

being studied.

Interpretation must occur at two levels.

involves viewing or experiencing the phenomenon

from the subjective perspectives of the social

participants. is to understand the apparent meaning of the

participants experiences to provide a thick

description

22


23/396

3. USE OF EXPRESSIVE LANGUAGE:

Documenting the verbal and non-verbal language

of participants and

the analysis of such language are integral

components of qualitative analysis.

The study must depict the emotions and

experiences of that person, so that readers can

understand and relate to that person.

23


24/396

Use of

imageries,

metaphors,

sarcasm, and

other figures of speech is very common in

qualitative analysis.

24

4 TEMPORAL NATURE


25/396

4. TEMPORAL NATURE:

Qualitative research is often not concerned with

searching for specific answers, but with

understanding a dynamic social process as it

unfolds over time

Hence, such research requires an immense

involvement of the researcher at the study site foran extended period of time,

and is necessary to capture the entire evolution of

the phenomenon of interest.25


26/396

QUALITATIVE DATA COLLECTION

Data is collected in variety forms

The most frequently used technique isinterviews

face-to-face,

telephone, or

focus groups

26


27/396

A second technique is observation.

direct observation, where the researcher is a

neutral and passive external observer and is not

involved in the phenomenon of interest

participant observation, where the researcher is

an active participant in the phenomenon

e.g., her inputs or mere presence influence the

phenomenon being studied

27


28/396

A third technique is documentation- where

external and internal documents, such as

memos, electronic mails,

annual reports,

financial statements,

newspaper articles,

websites,

may be used as independent data sources or for

corroboration of other forms of evidence.

28

TYPES OF QUALITATIVE


29/396

TYPES OF QUALITATIVE

RESEARCH

A. CASE RESEARCH is an intensive longitudinal study of a

phenomenon at one or more research sites

for the purpose of

deriving detailed,

contextualized inferences and

understanding the dynamic process

underlying a phenomenon of interest

29

C h h i di i i f h


30/396

Case research has some unique distinctions from other

qualitative methods:

First, this method can be used for either inductive

theory building or deductive theory testing

Second, the researcher is a neutral observer

Please refer to the previous chapter for further

details on this method.

30


31/396

B. ACTION RESEARCH

is an interactive method of inquiry that

assumes complex social phenomena are bestunderstood by introducing changes,

interventions, or actions into thosephenomena and observing the effects of

those actions on the phenomena of interest.31


32/396

the researcher is usually a consultant or an organizational

member embedded into a social context (such as an

organization),

the researcher initiates an action in response to a social

problem,

He/she examines how his/her action influences the

phenomenon

while also learning and generating insights about the

relationship between the action and the phenomenon.

32


33/396

Examples include

organizational change programs, such as

the introduction of new organizational processes,

procedures,

people, or

technology or replacement of old ones,

initiated with the goal of improving an

organizationsprofitability or performance33


34/396

The researchers choice of actions must be

based on theory,

which should explain why and how such

actions may bring forth the desired social

change

34


35/396

The theory is validated by the extent to which the

chosen action is successful in relieving the targeted

problem. Simultaneous problem solving and insight

generation is the central feature that distinguishes

action research from all other qualitative researchmethods.

Hence, action research is an excellent method for

bridging research and practice.

35


36/396

Action research cycle

36


37/396

A. DIAGNOSING PHASE

involves identifying and defining a problem in

its social contextB. ACTION PLANNING

involves identifying and evaluating alternative

solutions to the problem and deciding on a future course of action (based

on theoretical rationale)

C. ACTION TAKING

is the implementation of the planned course of

action

37


38/396

D. EVALUATION STAGE

examines the extent to which the initiated

action resolves the original problem i.e., whether theorized effects are indeed

realized in practice

E. LEARNING PHASE

the experiences and feedback from the action

evaluation phase are used to generate insightsabout the problem and suggest future

modifications or improvements to the action38


39/396

The problem is then re-examined based on

the outcomes of the previous action, and

the action research cycle is repeated with a

new or modified action sequence.

learning from the first cycle can be

implemented in the second cycle

39


40/396

the primary mode of data collection is

participant observation,

although other techniques such asinterviews and documentary

evidence may be used to support

the researchersobservations

40


41/396

C. ETHNOGRAPHY emphasizes studying a phenomenon within the

context of its culture

The researcher must be deeply immersed in the

social cul ture over an extended per iod of time

(usually 8 months to 2 years) and

should engage, observe, and record the daily

l i fe of the studied culture and social actors in

the within their natural setting 41

The primary mode of data collection is


42/396

The primary mode of data collection is

participant observation,

data analysis involves asense

-making

approach

the researcher must take extensive f ield notes,

and narrate her exper ience in descriptive

the researcher has two roles:

rely on her unique knowledge and

engagement to generate insights (theory), convince the scientific community of the

trans-situational nature of the studied

phenomenon42


43/396

It i d ith th t ti fl ti d l i


44/396

It is concerned with the systematic reflection and analysis

of phenomena associated with conscious experiences,

such as

human judgment,

perceptions, and

actions,

with the goal of appreciating and describing social reality from the

diverse subjective perspectives of the participants

involved, and

understanding the symbolic meanings (deep

structure)underlying these subjective experiences.

44


45/396

45


46/396


47/396

F. HERMENEUTICS

Derived from rel igious studies and linguistics,

is the study of interpretation as an art and the

theory and practice of interpretation Traditional hermeneutics, such as biblical

hermeneutics, refers to the interpretation of

written texts, especial ly in the areas of l i terature,

rel igion and law (such as the Bible)

47

RIGOR IN QUALITATIVE RESEARCH


48/396

RIGOR IN QUALITATIVE RESEARCH

Qualitative interpretation is subjective, and is

therefore often considered less r igorous by manyfunctionalistic researchers

functionalist research employs a reductionist

approach by simplifying social reality intoparsimonious theories and laws,

interpretive or quali tative research attempts to

interpret social reality within the context inwhich the reality is situated and from the

subjective viewpoints of the embedded actors.

48

A. DEPENDABILITY


49/396

A. DEPENDABILITY

Qualitative research can be viewed as

dependable or authentic

if two researchers assessing the same

phenomenon using the same set of evidence

independently arr ive at the same conclusions

or same researcher observing the same/

simi lar phenomenon at different times arr ives

at simi lar conclusions. 49


50/396

To ensure dependability, interpretive

researchers must provide adequate detai ls

about their phenomenon of interest and

the social context in which it is embedded

so as to allow readers to independently

authenticate their interpretive inferences.

50

B CREDIBILITY


51/396

B. CREDIBILITY

Qualitative research can be

considered credible if readers find its

inferences to be believable

Credibilitycan be improved by:

providing evidence of the researchersextended engagement in the field,

51


52/396

C CONFIRMABILITY


53/396

C. CONFIRMABILITY

refers to the extent to which the findings

reported in qualitative research can be

independently confirmed by others (typically,participants)

conformability is demonstrated in terms of

inter-subjectivity, i .e., if the studysparticipants agree with the

inferences der ived by the researcher

53

D TRANSFERABILITY


54/396

D. TRANSFERABILITY

refers to the extent to which the findings can

be generalized to other settings The researcher must provide r ich, detailed

descriptions of the research context and

thoroughly describe the structures,

assumptions, and processes revealed from

the data

so that readers can independently assess

whether and to what extent the reported

f indings are transferable to other settings.54

Q A A A A S S


55/396

QUALITATIVE ANALYSIS

Unlike quanti tative analysis, which is statistics

driven and largely independent of the

researcher,

quali tative analysis is heavi ly dependent on the

researchersanalytic and integrative ski l ls and

personal knowledge of the social context where

the data is collected

55


56/396

emphasis in quali tative analysis is sense

makingor understanding a phenomenon,rather than predicting or explaining

creative and investigative mind set is

needed for quali tative analysis

56

CHAPTER SIX


57/396

CHAPTER SIX

QUANTITATIVE RESEARCH

Quantitative research is the systematic and

scientific investigation of quantitative properties

and phenomena and their relationships

The objective is to develop and employ

mathematical models, theories and hypotheses

pertaining to natural phenomena

57


58/396

It usually starts with a theory or a general

statement proposing a general relationshipbetween variables.

With this approach it is likely that the

researchers wil l take an objective position and

their approach wi l l be to treat phenomena as

hard and real.

58

CHARACTERISTICS OF QUALITATIVE AND QUANTITATIVE RESEARCH


59/396

CHARACTERISTICS OF QUALITATIVE AND QUANTITATIVE RESEARCH

Characteris

tics

Qualitative Research Quantitative Research

Typical Data

Collection

Methods

Participant observation, semi-

structured interviews,

introspection

Laboratory observ.,

questionnaire, schedule

orstructured interviews

Formulationof

Questions

and

Answers

Open loosely specifiedquestions and possible

answers.

Questions and answers

are exchanged intwo way

comm. b/n researcher and

participant.

Closed questionsand answer

categories to be

prepared inadvance.

59

Selection of Infn. maximization Representativeness as proportion


60/396

Responden

ts

guides the selection

ofrespondent.

Every respondent

may be unique (key

person).

of population N. Sample

selection, sample size according

to assumptions about distribution

in population N. Respondents

should be directly comparable.

Timing of

Analysis

Parallel with data

collection

After data collection

Application

of

StandardMethods of

Analysis

Are rarely used.

Methods of analysis

are formulatedduring the data

collection process.

Standard statistical methods are

frequently used

60


61/396


62/396

CH APTER - SEVENMEASUREMENTS IN RESEARCH

62 62

5 1 DEFINITION OF CONCEPTS /


63/396

5.1 DEFINITION OF CONCEPTS /CONCEPTUAL AND OPERATIONAL

INTRODUCTION:

A manager has to take many decisions in his day-

to-day life.

decisions may relate to:

the manufacturing ormarketing of products,

hiring or firing of employees, and so on.63


64/396

Some of these decisions depend on thequantitative data for which the units of

measurement can be subjected to a statisticalanalysis.

However, there are decisions, which depend on

behavioural data, which is not suitable for directstatistical analysis.

Thus, for management purposes the manager hasto measure physical objects as well as abstract

concepts.

Measurement is a relatively difficult when itconcerns qualitative or abstract phenomena.

64


65/396

MEASUREMENTmay be defined as the process of assigning

numbers to objects or observations,

is a process of mapping aspects of a domainon to other aspects of a range according tosome rule of correspondence.

It is easy to assign numbers in respect ofcharacteristics of some objects, but it isrelatively difficult in respect of others.

65


66/396

DEFINITION OF CONCEPT:

A concept or a construct is a generalized idea about a class

of

objects,

attributes,

occur rences, or

processes.

Some concepts are concrete and quanti f iable while others are

abstract and qualitative

The nature of concepts calls for clearly defining them

conceptual ly and operationally.66

O ti l D fi iti


67/396

Operational Definition:

Specifies what the researcher must do tomeasure the concept under investigation

A concept must be made operational in order

to be measured.

An operational definition gives meaning to a

concept by specifying the activities or

operations necessary to measure it.67

Concepts like grievances may be difficult to


68/396

Concepts like grievances may be difficult to

operationalize,

whereas a concept like personnel turnover is less

difficult.

An operational definition is like a manual of

instructions or a recipe.

For Example: Media Skepticism: Conceptual defini tion

Media skepticism - the degree to which individuals are

skeptical toward the reali ty presented in the mass

media. 68


69/396


70/396

Media Skepticism: Operational def ini tion

Please tell me how true each statement is aboutthe media. I s it very true, not very true, or not at

al l true?

1. The program was not very accurate in itsportrayal of the problem.

2. Most of the story was staged for entertainment

purposes.

3. The presentation was slanted and unfair .

70

7 2 TYPES OF SCALES


71/396

7.2 TYPES OF SCALES

SCALE may be defined as Series of items arranged

according to value for the purpose ofquantification.

is a continuous spectrum or ser ies of categories.

The purpose of scaling is to represent, usuallyquanti tatively, an i tem's, a person' s, or an event' s

place in the spectrum.

71


72/396

Thus a scale is measur ing instrument, intended to

measure and record the extent to which test products,

possess character istics

I n the process of measurement one has to devise

some form of scale in the range and,

then map the properties of objects from the

domain onto this scale. The scales of

measurement can be considered in terms of their

mathematical properties. 72


73/396

The primary scales of measurement are:

(a) Nominal Scale

(b) Ordinal Scale(c) Interval Scale

(d) Ratio Scale

73


74/396

A. NOMINAL SCALE :

is simply a system of assigning numbers

symbols or letters to events in order to label

them.

These numbers are just convenient labels for

the particular class of events and as such have

no quantitative value.

Thus the nominal scale simply allows the

categorization of responses into a number of

mutually exclusive categories.

74

W t d h ith th b i l d


75/396

We cannot do much with the numbers involved.

For example, onecannot usefully average the numbers on

the back of a group of football players and come up with a

meaningful value.

Neither can one usefully compare the numbers assigned to

one group with the numbers assigned to another.

The typical applications of nominal scale is in

classification of responses by a social class, like of dislike,

yes or no, male or female and so on.

75

The counting of members in each group is the


76/396

The counting of members in each group is the

only possible arithmetic operation when a

nominal scale is employed. Accordingly, we are restricted to use mode as the

measure of central tendency.

There is no generally used measure of dispersionfor nominal scales.

Chi--square test is the most common test of

statistical significance of association and for themeasures of correlation we calculate the

contingency coefficient.

76

Nominal scale is the least powerful level of


77/396

Nominal scale is the least powerful level of

measurement.

It indicates no order or distance relationship and hasno arithmetic origin.

nominal scale simply describes differences between

units by assigning them to categories.

In spite their limitations, nominal scales are very

useful and widely used in surveys when data are

being classified by major sub-groups of the

population.

77

A Scale in which the numbers or letters are assigned


78/396

A Scale in which the numbers or letters are assigned

to objects serve as labels for identification or

classification. Yakob kebede # 21 - Tomas Tariku # 25

Male : 1 - Female : 2

Numerical Operation: CountingTypical Statistics: Descriptive :

Frequencies in each category

Percentages in each category

Mode & Cross tabulation

For Analyzing: Chi-Square test.

78

B ORDINAL SCALE :


79/396

B. ORDINAL SCALE : allows the respondents to rank some alternatives

by some common characteristics.

It simply places events in order, but there is no

attempt to make the intervals of the scale equal in

terms of some rule. Rank orders represent ordinal scales and are

frequently used in research relating to qualitative

phenomena.

For example, a group of consumers may rank the

three brands of toothpaste on the basis of the

perceived taste.79


80/396

only permit the ranking of items from highest to

lowest.

Ordinal measures have no absolute values, and

the real differences between adjacent ranks

may not be equal.

All that can be said is that one person is higheror lower on the scale than another,

but more precise comparisons cannot be made.

Thus, the use of an ordinal scale implies a

statement of greaterthanor lessthan.

80

However the magnitude of difference in ranks


81/396

However, the magnitude of difference in ranks

cannot be determined.

The real dif ference b/n ranks 1 & 2 may be more

or less than the dif ference between ranks 5 & 6.

Since the numbers of this scale have only a rank

meaning, the appropriate measure of central

tendency is the positional average i.e. median.

A measure of dispersion can be based on the

percenti les or quarti les of the distr ibution.

81


82/396

Correlations are restricted to various rank

order methods.

Statistical signi f icance is tested through the

use of non-parametr ic methods.

Numerical Operation:Rank ordering

Typical Statistics:

For Descr ibing:Median, Mode and Percentile.

For Analyzing: Rank order correlation, Sign test,Multi dimensional scaling.

82

C. INTERVAL SCALE :


83/396

I n the case of interval scale, the intervals are

adjusted in terms of some rule that has been

established as a basis for making the units equal.

I nterval scales can have an arbitrary zero point

with numbers placed at equally appearing

intervals.

I t Measures strength of the equali ty of

dif ferences between ranks.

I nterval scale takes care of the limitations of the

nominal and the ordinal scales.83

I t l l l i t th t f


84/396

I nterval scale also incorporates the concept of

equality of interval and so provides more

powerful measurement than ordinal scales.

A number of mathematical and statistical

operations including addition, subtractions and

computations of the mean can be performed on

the interval-scaled data.

84

Mean is the appropr iate measure of central


85/396

Mean is the appropr iate measure of central

tendency, while standard deviation is the most

widely used measure of dispersion. The generally used tests for statistical

signif icance are theZ,ttest and F.

Correlation is studied by the product momentcorrelation coeff icient.

The pr imary limitation of the interval scale is the

lack of an absolute or true zero of measurement. That is it does not have the capacity to measure

the complete absence of a character istic.

85

For example;


86/396

For example;

How important is pr ice to you while buying furni ture?

Numerical Operation: I ntervals between numbers.

Consumer Price I ndex (Base 100)Typical Statistics:

For Descr ibing: Mean, Standard Deviation, Variance.For Analyzing: Correlation analysis, Discriminate analysis,

ANOVA and multi dimensional scaling.

86

D. RATIO SCALE :


87/396

We can conceive of an absolute zero of length or

that of time. For example, the zero point on a centimetre scaleindicates the complete absence of length orheight.

But an absolute Zero of temperature istheoreticall y unobtainable.

Ratio scale has an absolute or true zero ofmeasurements.

I t represents the actual amounts of variables. Measures of physical dimensions such as weight,height, distance etc. come under this category.

87

I n general, al l statistical techniques are


88/396

applicable with ratio scales and

all mathematical operations that one cancarry out with real numbers can also be

carr ied out wi th ratio scale values.

Multiplication and division can only beused with the ratio scale, but not with other

scales.

Geometric and harmonic means can beused as measures of central tendency and

coefficients of variation may also be88

Ratio scale measurements are the most powerful


89/396

measurement discussed so far

as they possess all the properties of the measurementscales which we have discussed.

Ratios of the numbers on these scales have meaningful

interpretation.

They possess an unambiguous star ting point.

The number of minor traf f ic-rule violations and the

number of incorrect letters in a page of type script

represent scores on ratio scales.

89

Both these scales have absolute zeros and as such all


90/396

Both these scales have absolute zeros and as such all

minor traff ic violations and all typing errors can be

assumed to be equal in signi f icance.

With ratio scales involved one can make statements l ike

Dawitstyping performance was twice as good as that of

Rebka.

The ratio involved does have significance and

facilitates a kind of comparison which is not

possible in case of an interval scale.90

Numerical Operation: Actual Quantities


91/396

Numerical Operation: Actual Quantities

Typical Statistics:

For Describing: Geometric Mean, Coefficient ofvariation.

For Analyzing: Correlation analysis, Discriminateanalysis,

ANOVA and multi dimensional scaling.

Sources of Error in Measurement:

(a) Respondent

(b) Situation

(c) Measurer

(d) Instrument

91


92/396

7.3 CRITERIA FOR GOOD MEASUREMENT:


93/396

VALIDITY, RELIABILITY AND PRACTICALITY

Sound measurement must meet the tests of

validity, reliability and practicality.

In fact, these are the three major

considerations one should use in evaluating

a measurement tool.

93


94/396


95/396

Th b th t k th l t


96/396

The answer may be that we seek other relevant

evidence that confirms the answers we have

found with our measur ing tool.

What is relevant, evidence often depends upon

the nature of the research problem and the

judgment of the researcher.

But one can certainly consider three types of

validity in this connection:

(i) Content val idity;

(i i) Criter ion-related validity and

(ii i ) Construct validity.

96

A. CONTENT VALIDITY


97/396

is the extent to which a measur ing instrument provides

adequate coverage of the topic under study.

I f the instrument contains a representative sample of

the universe, the content validity is good.

I ts determination is pr imar i ly judgmental and intui tive.

I t can also be determined by using a panel of persons

who shall judge how well the measuring instrument

meets the standards,

but there is no numerical way to express it. 97


98/396

The concerned criterion must possess the following qualities:


99/396

Relevance:A criterion is relevant if it is defined

in terms we judge to be the proper measure.

Freedom from bias: Freedom from bias is

attained when the criterion gives each

subject an equal opportunity to score well.

Reliability:A reliable criterion is stable or

reproducible

Availability:The information specified by the criterion must

be available 99


100/396


101/396

Criterion-related validity is expressed as

the coeff icient of correlation between test

scores and some measure of future

performance or

between test scores and scores on another

measure of known validity 101

C CONSTRUCT VALIDITY


102/396

C. CONSTRUCT VALIDITY

is the extent to which your items are tapping

into the under lying theory or model of behavior

Its how well the items hang together

(convergent validity) or distinguish different

people on certain traits or behaviors

(discr iminant val idity)

102


103/396

Its the most difficult validity to achieve.

You have to either do years and years of

research or f ind a group of people to test that

have the exact opposite traits or behaviors

youreinterested in measur ing.

103


104/396

For determining construct val idity, we associate a set

of other propositions with the results received from

using our measurement instrument.

I f measurements on our devised scale correlate in a

predicted way with these other propositions, we can

conclude that there is some construct validity

104

I f the above stated criter ia and tests are met


105/396

I f the above stated criter ia and tests are met

with, we may state that our measuringinstrument is valid and will result in correct

measurement;

otherwise we shall have to look for more

information and/or resort to exercise of

judgment

105


106/396

Accordingly rel iabi l i ty is not as valuable as


107/396

Accordingly rel iabi l i ty is not as valuable as

validity, but it is easier to assess rel iabil i ty

in comparison to validity.

I f the quali ty of reliabi l i ty is satisf ied by an

instrument, then while using it we can be

confident that the transient and situational

factors are not inter fer ing.

107

Two aspects of reliability viz., stability and


108/396

p f y , y

equivalence deserve special mention.

The stability aspect is concerned with securing consistent

results with repeated measurements ofthe same person and with the same

instrument.

We usually determine the degree ofstability by comparing the results of

repeated measurements.

108


109/396

The equivalence aspect

considers how much error may get

introduced by dif ferent investigators or

different samples of the items being

studied.

A good way to test for the equivalence of

measurements by two investigators is tocompare their observations of the same

events.

109

Reliability can be improved in the


110/396

Reliability can be improved in the

following two ways:(i)By standardizing the conditions under

which the measurement takes place

i.e., we must ensure that external

sources of variation such as boredom,

fatigue, etc., are minimized to theextent possible. That will improve

stabi l i ty aspect.110


111/396

(ii) By carefully designed directions for

measurement with no variation from group to

group,

by using trained and motivated persons to

conduct the research and

also by broadening the sample of items used.

This wil l improve equivalence aspect.

111

3. TEST OF PRACTICALITY:


112/396

The practicali ty character istic of a measur ing instrument

can be judged in terms of economy, convenience and

interpretability.

From the operational point of view, the measur ing

instrument ought to be practical

i.e., it should be economical, convenient and

interpretable.

112

Economy consideration


113/396

y

suggests that some trade-of f is needed between the ideal

research project and that which the budget can afford.

Length of measur ing instrument is an important area

where economic pressures are quickly felt. Although more items give greater reliability as stated

earl ier , but in the interest of l imiting the interview or

observation time, we have to take only few items for our

study purpose.

Simi larly, data-col lection methods to be used are also

dependent at times upon economic factors.

113

Convenience test


114/396

suggests that the measur ing instrument should be

easy to administer.

For this purpose one should give due attention to

the proper layout of the measur ing instrument.

For instance, a questionnaire, with clear

instructions (illustrated by examples), is certainly

more effective and easier to complete than onewhich lacks these features.

114

I nterpretabi l i ty consideration is specially important when persons other than


115/396

is specially important when persons other than

the designers of the test are to interpret the

results.

The measuring instrument, in order to be

interpretable, must be supplemented by

detailed instructions for administer ing the test;

scor ing keys;

evidence about the rel iabi l i ty and

guides for using the test and for interpretingresults.

115

7.4 ATTITUDE MEASUREMENT SCALES


116/396

7.4 ATTITUDE MEASUREMENT SCALES

Attitude may be defined as the degree of positive

or negative affect associated with some

psychological object.

I t is a pre-disposition of the individuals to

evaluate some object or symbol or aspect of his

world in a favorable or unfavorable manner.

116


117/396

The study and measurement of atti tudes is important

since it is assumed that there is a relationship between


118/396

since it is assumed that there is a relationship between

atti tude and behavior.

The research, however, indicates that such a

relationship hold more at aggregate level than at the

individual level.

Atti tude may only be one of the factors inf luencing

behavior - there could be other factors beside atti tude

which may be more powerful in inf luencing behavior.

118


119/396

Many of the questions in a questionnaire are designed

t tti t d


120/396

to measure atti tudes.

Attitudes are a persons general evaluation of

something.

Customer attitude is an important factor

for the fol lowing reasons:

Atti tude helps to explain how ready one is to

do something.

Atti tudes do not change much over time Atti tudes produce consistency in behavior.

Atti tudes can be related to preferences.

120

Attitudes can be measured using the


121/396

following procedures / approaches:

Self-reporting:

subjects are asked directly about their

attitudes.

Self-reporting is the most common

technique used to measure atti tude.

121


122/396

Performance of objective tasks:

assumes that ones performance depends on


123/396

assumes that ones performance depends on

attitude.

For example, the subject can be asked to memor ize

the arguments of both sides of an issue.

He/she is more likely to do a better job on the

arguments that favor his/her stance. Physiological reactions:

subjectsresponse to a stimulus is measured using

electronic or mechanical means. While the intensity can be measured, it is dif f icult to

know if the atti tude is positive or negative.

123


124/396

Scale: While measur ing atti tudes and opinions,we face the problem of their val id measurement.

Similar problems are faced while measuringphysical and insti tutional concepts.

Thus we need procedures, which may enable usto measure abstract concepts more precisely.

A scale is a continuum consisting of the highestpoint and lowest point along with severalintermediate points between the extreme points.

124

The scale-point positions are so related to each


125/396

other that when the f irst point happens to be the

highest point, the second point indicates a

higher degree in terms of a given character istics

as compared to the third point and so on.

Scaling describes the procedures of assigning

numbers to var ious degrees of opinion, atti tudes

and other concepts.

125

Scaling can be done in the following two ways:


126/396

i) Making a judgment about some character istic of

an individual and then placing him directly on a

scale that has been defined in terms of that

characteristic.

i i ) Constructing questionnaires in such a way that

the score of individualsresponses assigns him a

place on a scale.

126

I n practice the commonly used atti tude


127/396

measurement scales are ordinal in nature.

These scales are basically self-report

inventories, with a list of favourable and

unfavourable statements towards the subject

under study.

The different types of attitude measurement

scales are:

127

Scaling Techniques


128/396

Scaling techniques are broadly classif ied as

comparative and non-comparative.

Comparative scales

involve the direct measurement of stimulus objects

and

data have only ordinal or rank-order properties.

These scales are further classif ied as

paired comparisons,

rank-order and

Q-sort procedures.

128


129/396


130/396

Non-comparative scales include:

continuous rating and

i temized rating scales. I temized rating scales are fur ther

classif ied as:

L iker t Type and

Semantic Dif ferential scales.

130

The Attitude Measuring Process


131/396

Ranking - Rank order preference

Rating - Estimates magnitude of a characteristic

Rating is a measurement task that presents respondents withseveral concepts and requires the respondent toestimate the magnitude of a characteristic orquality that an object possesses.

Sorting - Arrange or classify concepts

Choice - Selection of preferred alternative

131

1. Comparative scaling techniques: The following scaling techniques are used to do a


132/396

The following scaling techniques are used to do a

comparative study among different sets of

variables

i. Paired Comparisons :

I n this method the respondent can express his

atti tude by making a choice between two objects,

say between Coke and Pepsi according to some

criterion.

I n general, if there are nstimuli to judge, thenumber of judgements required in a paired

comparison is N= n (n1)/2.

132

Paired comparison provides ordinal data,

but the same may be converted into an interval


133/396

but the same may be converted into an interval

scale by the method of the Law of

Comparative Judgement developed by L.L.

Thurstone.

This technique involves the conversion of

frequencies of preferences into a table of

proportions which are then transformed into Z

matrix by referr ing to the table of area under

the normal curve.

133


134/396


135/396

Brand A B C D E


136/396

A 0 0 1 0

B 1* 0 1 0

C 1 1 1 1

D 0 0 0 0

E 1 1 0 1

Total of times

referred

3 2 0 4 1

136

L imitations :


137/396

Paired comparisons techniques areuseful when the number of brands is

limited.

The order in which the objects arepresented may introduce bias in results.

I t does not ref lect a true market

situation, which involves selection frommultiple alternatives.

137

i i . Rank Order Scaling:


138/396

is commonly used to measure preferences for

brands as well as attr ibutes.

respondents are presented wi th several objects

simultaneously and asked to rank them

according to some cr iter ion.

138


139/396

iii. Q-Sort and Scaling :


140/396

Q-Sort scaling discriminate among a

relatively large number of objects quickly.

This technique uses a rank-order procedure

in which objects are sorted into piles basedon similarity with respect to some criter ion.

140


141/396


142/396

142


143/396

143

2. Non-comparative scales each object is scaled independently of the others


144/396

each object is scaled independently of the others

and the resulting data generally assumed to be

interval or ratio scaled.

include continuous rating and itemized rating

scales.

The rating scale gives a quali tative description

of a number of character istics of an individual.

An object is judged in absolute terms against

some specif ied cr iter ia

i.e. properties of objects judged without

reference to other simi lar objects.144

The ratings may be in the forms as:

like.Dislike,


145/396

aboveaverage, average, below average,or

other classif ications with more categories such as

excellent- good- average- below average- poor,

and so on.

There is no specif ic rule whether to use a two-points scale, three-points scale or scale with sti l l

more points.

Since more points on a scale provide anopportunity for greater sensitivity of

measurement so in practice, three to seven

points scales are general ly used.145


146/396


147/396

147

ii. Itemized Rating Scales


148/396

also known as numerical scale,

presents a ser ies of statements from which a

respondent selects one as best reflecting his

evaluation.

These statements are ordered progressively in

terms of more or less of some property.

The respondents are required to select the

specified statement that best describes the

object being rated.

148


149/396


150/396


151/396

Itemized rating scales are widely used in

marketing research and

form the basic components of more complexscales, such as multi-item rating scales.

The commonly used itemized rating scales are

the Likert and Semantic differential scales. ForExample;

151


152/396

152

Attitude Rating Scales Construction Techniques

Si l Attit d S li


153/396

1. Simple Attitude Scaling: I n its most basic form, attitude scaling requires that

an individual agree with a statement or respond to a

single question.

This type of self -rating scale merely classif iesrespondents into one of two categories;

For Example: THE GUTTMAN SCALE

Simplified Scaling Example

THE PRESIDENT SHOULD RUN FOR RE-ELECTION

_______ AGREE ______ DISAGREE

153

2 Category Scales:


154/396

2. Category Scales:

A category scale is a more sensiti ve measure

than a scale having only two response

categories

i t provides more information.

Questions working is an extremely important

factor in the usefulness of these scales.

154

How important were the following in your decision to visit San

Diego (check one for each item)


155/396

g ( )

VERY SOMEWHAT NOT TOO

IMPORTANT IMPORTANT IMPORTANT

CLIMATE ___________ ___________ ___________

COST OF TRAVEL ___________ ___________ ___________

FAMILY ORIENTED ___________ ___________ ___________

EDUCATIONAL/

HISTORICAL ASPECTS _________ ___________ ___________

FAMILIARITY WITH

AREA ___________ ___________ ___________

155


156/396

L ikert Scale for Measur ing Atti tudes Toward

Tennis:


157/396

I t is more fun to play a tough, competitive

tennis match than to play an easy one.

___Strongly Agree

___Agree

___Not Sure

___Disagree

___Strongly Disagree

157


158/396


159/396


160/396

The semantic differential consists of identification of

a company, product, brand, job, or other concept

followed by a series of seven-point bipolar rating

scales.

The subject makes repeated judgments of the concept

under investigation on each of the scales related to

measuring attitudes.160

The scoring of the semantic differential can be

illustrated by using the scale bounded by the

h " d " d " ld f hi d "


161/396

anchors "modern" and "old-fashioned."

extremely modern,

very modern,

slightly modern,

both modern and old fashioned,

slightly old-fashioned,

very old-fashioned, andextremely old-fashioned.

A weight is assigned to each position on the

rating scale161


162/396

CH APTER EIGHT

DATA COLLECTION TECHNIQUES

162

Information expressed in appropriate quantitative

form are known as data


163/396

form are known as data.

I n short, neither a business decision nor a

governmental decision can be made in a casual

manner

I t is through appropr iate data and their analysis that

the decision maker becomes equipped with proper tools

of decision making.

163


164/396

The collection of data refers to purposive

gather ing of information relevant to the subject


165/396

matter of study and as per requirement of

research.

The method to be selected for data collection

depends upon the :

nature,

purpose and

scope of enquiry on the one hand and the availability of resources and time on the

other hand.

165


166/396


167/396


168/396

Sources of secondary data:

company records or archives,

government publications, industry analyses offered by the media,

web sites,

the internet, and so on.

168

8.2 Data Co ect on Tec n ques

Primary Data


169/396

We collect primary data dur ing the course of doing

exper iment in an exper imental research.

But in case of non-exper imental research a researcher

conducts survey to obtain primary data either through: Observation

Direct communication with respondent in one form

or another

Personal interview

169

There are several method of collecting primary

data particularly in survey and descriptive


170/396

research.

Commonly used methods of collecting primary

data are discussed below: Observation method

Interview Self administered Questionnaires

Schedule (Interview Questionnaires)

Focus Group Discussion (FDG)

In-depth interview Other methods / Etc.

170

1 INTERVIEW METHOD:


171/396

1. INTERVIEW METHOD:

the researcher meets people and discusseshis/their social, economic or some other problem

with them.

During the courses of discussion, he gathers facts.

An interview is different from Schedules

(interview questionnaires).

A schedule includes some predetermined

questions asked by the researcher in a def ini teorder with out change.

171


172/396

A. Personal Interview:


173/396

requi res interviewer-asking question in face-to-

face contact to respondent.

The interviewer has to be on the spot and has tomeet people from whom the data are collected.

is suitable for intensive investigation.

But in certain cases it may not be possible orworthwhile to contact direct the person

concerned

173

can be of two type

structured and

t t d


174/396

unstructured

STRUCTURED INTERVIEW:

involves the use of a set of predetermined

questions and has highly standardized technique

of recording.

I t is not possible for interviewer to change even

the sequences of the questions.

The recording formats also are standardized.

174

UNSTRUCTURED INTERVIEW:

is characterized by a flexibility of questions to


175/396

y y q

questioning. I t does not follow a system of pre-determined

question and standardize techniques of recording

information.

The researcher is allowed much greater freedom

to, if it is needed, supplementary questions or at

times he may omit certain questions.

I nterviewer can change the sequences of question

and he has also freedom in recording the response

to include some aspects and exclude the other.175


176/396


177/396


178/396


179/396

Weakness of the personal interview:

I t is very expensive method specially when large and

wide spread geographical sample is taken

There is sti l l the possibil i ty of the bias of interviewer as

well as that of the respondent. Because the supervision

and control of interview is sti l l problem

Certain group of respondent (such as importantofficial) may not be easily approachable under this

method.

179


180/396


181/396


182/396

Replies can be recorded without causing

embarrassment to respondent

Easy access to those respondent who are highly

off icials and can not be contacted personal ly

No field staff is required

Wider distr ibution of sample is possible.

182

Weakness of this method: Little time is given to respondent for considering


183/396

possible answer. Mostly the interview wil l not exceed

five minutes at most

Surveys are restricted to respondents having

telephone

Cost consideration may restrict extensivegeographical coverage

There is high possibil i ty of biasedness from the side

of the interviewer

Since questions have to be sort and to the

point, probes are dif f icult to handle.

183

Prerequisites of interview: For successful implementation of the


184/396

interview method;

interviewer should be:

carefully selected,

trained and

briefed.

184


185/396

I nterviewer should be:

honest,

sincere,

hardworking,

impartial and

must posses the technical competence and necessary

practical exper ience.185

I nterviewer has to try to create fr iendly

atmosphere of trust and conf idence


186/396

atmosphere of trust and conf idence

I nterviewer must ask question proper ly and

completely.

interviewer must answer legitimate questions if

any asked by the respondent.

The interviewer should not show surprise or

disapproval of a respondentsanswer, instead he

must keep the direction of interview in his ownhand.

186


187/396


188/396


189/396

Types of Questionnaires:

Questionnaires can be of the following

type: I nterview Questionnaires (Schedules)

Mail Questionnaires (Self administered

questionnaires) Questionnaires through Internet(Through electronics media).

189

A. MAIL QUESTIONNAIRES:


190/396

is very popular especially for large study.

The questionnaires are sent by post to the

person concerned with a request to answer thequestion and return them back.

Questionnaires are mailed to respondents who

are expected to read and understand the question

and wr ite down the answer.

190

Advantage (strength)

Low cost even for larger sample size and widely

spread geographical ly


191/396

spread geographical ly

I t is free from bias of the interviewer. Answers are

in respondentsword.

Respondents have adequate time to give well

though answers

Respondents, who are not approachable, can be

reached conveniently (especially, in mail and e-

mail).191


192/396


193/396

Open-end questions: The respondent is asked to provide his own

answer to the question.


194/396

answer to the question.

H is answer is not in any ways limited.

E.g., the respondent might be asked, What

do feel the most important issue facing your

community?

The problem associated with such form of

questioning is that, it is not possible to get

uniform answers and hence is difficult toprocess.

194

Closed ended questions:


195/396

The respondent is asked to select his answer

from among a list provided by the researcher

(yes, no, I dontknow, etc).

Are very popular in survey research since they

provide a great uniformity response and

because they are easy to process.

195


196/396

major shortcoming is checkl ist or the provided

list of answers may not include all possible

answers.

For example: In asking about The most

important issues facing your country? the

researcher may provide a checkl ist of issues, but

in doing so he might over look certain issues that

respondent would have said were important.

196

To limit this shortcoming the followingguidelines are helpful.

The response categor ies provided should be


197/396

exhaustive they should include all the possible response

that might be expected.

Often the researchers support this effort byadding a category leveled like others

(please specify)

The answer categories must be mutuallyexclusive; the respondent should not feel

compelled/ obliged to select more than one.197

B) Make items cleari. Make questionnaires item clear:


198/396

Questionnaire items should be clear andunambiguous.

opinion and perspective are clear to the

researchers but may not be clear to his

respondent.

So question items should be precise sothat the respondent knows exactly what

the researcher want to an answer to be.198

ii. Avoid double questions: Researcher often asks respondent for a single


199/396

answer to combination of question.

E.g., Whatdo you think about the services l ike food

and transportation provided by CBE off ice dur ing

the second phase of your CBTP program?"

Some respondent may want to answer as good to

the transportation service and bad to the food

service.

199

iii. Respondent must be competent to answer

The researcher should ask himself whether


200/396

the respondents are able to answer the

desired questions.

Question should be relevant to most of

respondents.

Short i tems are commonly considered as thebest (long and complicated item should be

avoided). 200


201/396

C) General questionnaire format


202/396

The format of a questionnaire is as importantas the nature and wording or the question

asked.

If the lay out of the questionnaire is not

appropriate it can confuse respondents and in

the extreme, can lead respondents throwingthe questionnaire away.

202


203/396

Therefore, as a general rule, the questionnaire

should be spread out and organized.

The researcher should maximize the white spacein his instrument.

Putting more than one question in one line,

leads to the probabil i ty of skipping the secondquestion in case of some respondents.

203


204/396


205/396


206/396

ii. Ordering questions in questionnaires

The order in which questions are asked can

affect response as well as the overall data


207/396

p

collection activi ty.

The appearance of one question can affect

the answers given to the subsequent ones.

Some researchers attempt to overcome thiseffect by randomizing the order of the

questions.

The researcher should be in a position toestimate what effect it wi ll have on the next

question.207

iii. Opening question:


208/396

Opening question is also very important.

The researcher should avoid the following

type of question as opening question in a

questionnaire. Question that put too great strain on the

memory or intel lect of the respondent

Question of personal character

Question related to personal wealth etc.

208

iv. Questionnaire format Different research can have dif ferent Questionnaires

formats


209/396

formats.

Commonly used formats of questionnaires contains

the following parts:

Instruction:

Every questionnaire, whether it is self administeredor schedules should contain clear instruction and

introductory comment.

I f a questionnaire has dif ferent parts it needs to have general instruction for the whole questionnaire and

specif ic instruction for each parts of a questionnaire.

209

Introduction: I f the questionnaire is arranged into content

subsections then it is useful to introduce each


210/396

section with short statement concerning its

content and purpose.

Here the researcher will instruct (tell) the

respondent to indicate their answer by

putting a check mark in the box or his

appropriate answer if needed.

210

V. Mail distribution and return


211/396

The basic method for data collection through the mail

has been a transmission of a questionnaires

accompanied by a letter of explanation and a returnenvelope.

The respondents then complete the questionnaire and

return i t to the research off ice through the mail , using

the envelope provided for that purpose.

211


212/396

Alternative method is that in some cases it is

possible to further faci l i tate this process through

the use of a self-mai l ing questionnaire.

The questionnaires are constructed in such a way

that the research officesreturn address and

postage are printed on the questionnaire itself .

Up on completion, then it can be dropped in the

mail without requir ing an envelope.

212

However, the post office has special requirement

regarding the form of mater ials that can be mailed; thus,

researcher should plan thi s approach proper ly and count


213/396

researcher should plan this approach proper ly and count

with i t.

These methods simpl i fy the assembly of mai ling pieces

since it is unnecessary to include a return envelope and

the respondent cannot lose the return envelope.

I t has a certain TOYVALUE.

To some extent the respondent may want to complete the

questionnaire so that he can then play with a cover.

213


214/396


215/396

I t is usually best to complete two graphs. One

should show the number returned each day

raising then dropping.

Another should report cumulative number or

percentage. This wil l show the picture of his

successful data collection.

215

vii. Follow-up-mailing Following up mailings is strongly

recommended, as it is an effective approach for


216/396

increasing return rate in mail survey. Follow up wil l be done by sending another mail

to the respondents.

I n practice, three mail ing (one or iginal andtwo follow-ups) seems the most eff icient.

The timing of follow-up mail ings is also

important- two or three weeks are a reasonablegap between mai l ings.

216

Follow-up mailings may be administered

in a number of ways


217/396

Respondents are simple sent a letter of

additional encouragement to participant

Better method is to send a new copy of the

survey questionnaire with the follow-up letter

to al l respondents

217

viii. Acceptance response rate


218/396

The percentage return rate that should be

achieved in a mail survey is:

A response rate 50% is adequate for analysis

and reporting

A return rate at least 60% is good and a

response rate of 70% or more is very good.218


219/396

Enumerator along with schedule


220/396

(questionnaires), goes to the respondent, put to

them the questions from the Performa in the

order of the questions are listed and record.

Here we consider both schedule and interview

questionnaires are simi lar and the same.

220


221/396

The questionnaires are either delivered by hand

to be answered by respondents or the trained

interviewer wil l read the question to respondent

and record the answer given.

But mostly the interviewer read the question andrecords the answers given by respondent.

221

Differences between questionnaires and schedulesMail Questionnaires Schedules

Generally sent through They are filled out by a research


222/396

mail to respondents worker or enumerators

Data collection is

relatively cheap

It is more expensive, since money

has to be spent in appointing, train

the enumerators

Non response is usually

high

Non-response is generally low

222


223/396

Wider and more

representative sample

It is difficult to sent

enumerator to wider area


224/396

distribution is possible

The success of this method

depend up on the quality of

the questionnaires

Success of this method

depends on the honesty and

competence of enumerator

No observation Observation method can also

be used

224

Example of a Questionnaire: A questionnaire with an objective to collect

information concerning the loanees who have taken


225/396

loan from a bank during the last five years under theSelf Employment to Educated Unemployed Youth

Scheme is presented below.

Note that the first few questions make the interviewerfamiliar with the subject.

The substantive information commences from

question 9 but the two embarrassing questions 11 and

12 is followed by a Sympathetic question 13. Although the questionnaire is structured an

unstructured part has been included in the answer of

question 14 to record the diversity of replies. 225

BANK OF XYZSelf Employment to Educated UnemployedYouth Scheme


226/396

226


227/396

227


228/396

228


229/396

229

14. Your suggestions to overcome these difficulties

.


230/396

230

.

Signature of the

Investigator..

Name of the

Investigator

Date of

Interview

3. Focus Group Discussions: is an unstructured, free f lowing interview with


231/396

a small group of people.

I t is f lexible format

allow people to discuss their : true feelings,

anxieties, and frustrations,

and to express the depth of their convictions in

their own words.

231

advantages relatively brief,

easy to execute,


232/396

quickly analyzed, and inexpensive.

I t must be remembered, however, that a

small discussion group will rarely be arepresentative sample, no matter how

careful ly it is recruited.

The group consists of an interviewer ormoderator and six to tenparticipants who

discuss a single topic.

232


233/396


234/396

AdvantagesSYNERGISM:


235/396

The combined effort of the group wi l l produce a widerrange of information, insights, and ideas than will the

accumulation of sep

Marketing Research ch-5, 6, 7 ,8, 10, & 12.ppt

Documents