measurement in survey research mktg 3342 fall 2008 professor edward fox

23
Measurement in Survey Measurement in Survey Research Research MKTG 3342 MKTG 3342 Fall 2008 Fall 2008 Professor Edward Fox Professor Edward Fox

Upload: anna-briggs

Post on 24-Dec-2015

216 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Measurement in Survey Measurement in Survey ResearchResearch

MKTG 3342MKTG 3342

Fall 2008Fall 2008

Professor Edward FoxProfessor Edward Fox

Page 2: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Measurement in Survey Measurement in Survey ResearchResearch

Measurement is the process of assigning numbers numbers or labels labels to the attributes of

objects, persons, states, or events in accordance with specific rulesrules

Page 3: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Identify the concept of

interest

Identify the concept of

interest

Develop a constructDevelop

a construct

A constitutivedefinition

A constitutivedefinition

An operationaldefinition

An operationaldefinition

A measurementscale

A measurementscale

Evaluate the reliability andvalidity of the

scale

Evaluate the reliability andvalidity of the

scale

Utilize thescale

Utilize thescale

Research findings

Research findings

The Measurement ProcessThe Measurement Process

…which is used to create…

…which enables a researcher to

develop …

…which enables a researcher to create…

…that requires the researcher to…

If the evaluation is satisfactory, the

researcher…

…which leads to…

…which is used to…

Page 4: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Steps 1&2: Identify Concept / Steps 1&2: Identify Concept / Develop ConstructDevelop Construct

Identify the concept of

interest

Identify the concept of

interest

Develop a constructDevelop

a construct

A constitutivedefinition

A constitutivedefinition

An operationaldefinition

An operationaldefinition

A measurementscale

A measurementscale

Evaluate the reliability andvalidity of the

scale

Evaluate the reliability andvalidity of the

scale

Utilize thescale

Utilize thescale

Research findings

Research findings

Page 5: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Steps 1&2: Identify Concept / Steps 1&2: Identify Concept / Develop ConstructDevelop Construct

Measurement begins by identifying a concept of interest and the construct to be studied. Both are abstractions of reality.

A concept is expressed in every-day terminology. This requires the researcher to generalize/categorize.

A construct is a theoretical abstraction that can’t really be observed (e.g., love, trust, social class, personality, power).

Page 6: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Steps 1&2: Identify Concept / Steps 1&2: Identify Concept / Develop Construct – ExampleDevelop Construct – Example

Question – Why do some customers buy Air Jordan athletic shoes over and over again?

Concept – Repeat purchase

Construct – Brand loyalty

Page 7: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Steps 3&4: Define the Concept Steps 3&4: Define the Concept Conceptually and OperationallyConceptually and Operationally

Identify the concept of

interest

Identify the concept of

interest

Develop a constructDevelop

a construct

A constitutivedefinition

A constitutivedefinition

An operationaldefinition

An operationaldefinition

A measurementscale

A measurementscale

Evaluate the reliability andvalidity of the

scale

Evaluate the reliability andvalidity of the

scale

Utilize thescale

Utilize thescale

Research findings

Research findings

Page 8: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Steps 3&4: Define the Concept Steps 3&4: Define the Concept Conceptually and OperationallyConceptually and Operationally

Constitutive DefinitionA theoretical or conceptual definition

that defines the concept in terms of other concepts and constructs; like a dictionary definition

Operational DefinitionDefines which observable characteristics

will be measured and the process for assigning a value to the concept

Page 9: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Steps 3&4: Define the Concept Steps 3&4: Define the Concept Conceptually and Operationally – Conceptually and Operationally –

ExampleExample

Constitutive Definition – Increased propensity to purchase a brand due to previous experience with that brand

Operational Definition – Rating of purchase probability, depending upon prior purchase

Page 10: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Step 5: Develop a Step 5: Develop a Measurement ScaleMeasurement Scale

Identify the concept of

interest

Identify the concept of

interest

Develop a constructDevelop

a construct

A constitutivedefinition

A constitutivedefinition

An operationaldefinition

An operationaldefinition

A measurementScale

A measurementScale

Evaluate the reliability andvalidity of the

scale

Evaluate the reliability andvalidity of the

scale

Utilize thescale

Utilize thescale

Research findings

Research findings

Page 11: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Step 5: Develop a Measurement Step 5: Develop a Measurement ScaleScale

SCALEA scale is a set of symbols or numbers

so constructed that the symbols or numbers can be assigned by a rule for the individuals (or their behaviors or attitudes) to whom the scale is applied

Page 12: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Types of ScalesTypes of Scales

NominalDescription

Uses numerals to identify objects, individuals, events, or groups. Used for Classification (male/female; buyer/nonbuyer)

Typical Descriptive StatisticsFrequency counts, percentages/modes

Examples of Nominal ScalesGender (1) Male (2) Female Geographic Area (1) Urban (2) Rural

(3) Suburban

Page 13: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Types of ScalesTypes of ScalesOrdinal Scale

DescriptionIn addition to identification, the numerals

provide information about the relative amount of some characteristic; determines greater or less than

Typical Descriptive StatisticsMedian

Example of Ordinal Scale: Please rank the following fax machines from 1 to 5 with

1 being the most preferred and 5 the least preferred. _____ Panasonic _____ Toshiba _____ Sharp _____ Savin _____ Ricoh

Page 14: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Types of ScalesTypes of Scales Interval

DescriptionHas all the properties of nominal and

ordinal scales + equal intervals between consecutive points; preferred measure for complex concepts or constructs

Typical Descriptive StatisticsMean/variance

Example of an Interval ScaleScaled response (on a scale from 1 to 10…)

Page 15: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Types of ScalesTypes of Scales

RatioDescription

Incorporates all the properties of nominal, ordinal, and interval scales plus it includes an absolute zero point

Typical Descriptive StatisticsMean/variance + a few higher order

statisticsExample of a Ratio Scale

Age, weight, height, population of the U.S., etc.

Page 16: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Step 5: Develop a Step 5: Develop a Measurement Scale – Measurement Scale –

Example Example Probability of purchasing the shoe

brand again in the next month, next year, or at any point in the future

Type of scale?

Page 17: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Step 6: Scale Reliability and Step 6: Scale Reliability and ValidityValidity

Identify the concept of

interest

Identify the concept of

interest

Develop a constructDevelop

a construct

A constitutivedefinition

A constitutivedefinition

An operationaldefinition

An operationaldefinition

A measurementscale

A measurementscale

Evaluate the reliability andvalidity of the

scale

Evaluate the reliability andvalidity of the

scale

Utilize thescale

Utilize thescale

Research findings

Research findings

Page 18: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Step 6: Scale Reliability and Step 6: Scale Reliability and ValidityValidity

Any measurement can be expressed as a Any measurement can be expressed as a function of three components:function of three components:

XXOO = X = XTT + X + XSS + X + XRR

Observed Score = True Score + Systematic Error + Random ErrorObserved Score = True Score + Systematic Error + Random Error

Ideally,Ideally, XXOO = X = XTT

In Practice,In Practice, XXOO X XT T … …

that is, Xthat is, XSS + X + XRR 0 0

Total Error = XTotal Error = XSS + X + XRR, where , where

XXSS = Systematic error (validity) = Systematic error (validity)

XXRR = Random error (reliability) = Random error (reliability)

Page 19: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Step 6: Scale Reliability and Step 6: Scale Reliability and Validity – IllustrationValidity – Illustration

..........

..

. .

.

..

.

.

.

..

.

Not Reliable Reliable and ValidNot Valid

..

... ..

...

Page 20: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Scale ReliabilityScale Reliability

The degree to which measures are free from random “noise” and, therefore, provide consistent data

IssuesTest-Retest ReliabilityInternal Reliability (split-half

technique)

Page 21: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

Scale ValidityScale Validity

Addresses the issue of whether what we attempted to measure was actually measured

IssuesFace ValidityContent ValidityPredictive ValidityConvergent ValidityDiscriminant Validity

Page 22: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

SummarySummary

Measurement means using rules to assign numbers to objects in such a way as to represent quantities of attributes

The measurement process is as follows: identify the concept of interest, develop a construct, define the concept constitutively and operationally, develop a measurement scale, evaluate the reliability and validity of the scale, and then use the scale

There are four basic types of measurement scales: nominal, ordinal, interval, and ratio

Page 23: Measurement in Survey Research MKTG 3342 Fall 2008 Professor Edward Fox

SummarySummary(Cont.)(Cont.)

Measurement data consists of information (“signal”) and error (“noise”).

Validity requires that you actually measure what you intended to measure

Reliability is the degree to which measures are free from random error