marketing research - concept of measurement

8/3/2019 Marketing Research - Concept of Measurement

1/22

The Concept of Measurement

and Attitude Scales

Prof. Rushen Chahal

Prof. Rushen Chahal


2/22

Measurement Process

Measurement:

Rule:

The Process of assigning numbers or labels to persons,

objects, or events in accordance with specific rules forrepresenting quantities or qualities or attributes.

The guide, method, or command that tells a

researcher what to do.

Prof. Rushen Chahal


3/22

Data Levels

Nominal Yes No No Nouses labels

categorizes

Ordinal Yes Yes No Noranks responses

determines order

not distance

Interval Yes Yes Yes Nodistance between

descriptors is known

Ratio Yes Yes Yes Yeshas zero as reference point

numeric

Scale Description Order Distance Origin

Least

Sophisticated

Most

Sophisticated

Prof. Rushen Chahal


4/22

Nominal Data

Classification Type Data. Examples:

Yes or no questions;

Nouns in general

Gender;

Race / Ethnicity;

Occupation;

Text open-ended questions.

Analysis Approach:

Cross tabulations / Percentages;

Sums and frequency counts;

Cant tell the relative value of responses.

Scales that partition data into mutually exclusive

and collectively exhaustive categories.

Scales that partition data into mutually exclusive

and collectively exhaustive categories.

Prof. Rushen Chahal


5/22

Ordinal Data

Ranking Type Data Examples:

Best liked, worst liked; Win, place, or show;

First, second, third;

Small, medium, and large;

Comparisons rankings -

rank these movies from best to worst

Analysis Approach:

Cross tabulations, sums and frequency counts;

Percentages, mode, mean for some types;

Can tell the relative order of responses

but not the distance between responses

Scales that maintain the labeling characteristics of

nominal scales and have the ability to order data.

Scales that maintain the labeling characteristics of

nominal scales and have the ability to order data.

Prof. Rushen Chahal


6/22

Interval Data

Comparison Type Data Examples:

One a 1 to 10 scale; Age, income, etc. as ranges

Red, blue, green

- if each rated from 1 to X for example.

Analysis Approach:

Standard deviation, variance, kurtosis; Descriptive statistics - mean, median, mode;

Sums and ranged frequency counts;

Correlation;

Can tell the relative value of responses and

can tell the distance between responses.

Scales that have the characteristics of ordinal

scales, plus equal intervals between points.

Scales that have the characteristics of ordinal

scales, plus equal intervals between points.

Prof. Rushen Chahal


7/22

Ratio Data

Flat Numeric Type Data Examples:

Age = 50 (not an age range) Income = $25,000 (not an income range)

Number of children: ________

Analysis Approach:

Standard deviation, variance, kurtosis

Descriptive statistics - mean, median, mode Sums and ranged frequency counts

Pearson correlation, regression

Can tell the relative value of responses and

can tell the distance between responses and

how they relate to zero.

Scales that have the characteristics of interval, plus

a meaningful zero point.

Scales that have the characteristics of interval, plus

a meaningful zero point.

Prof. Rushen Chahal


8/22

Reliability:

Degree to which measures are free from random error

and, therefore, provide consistent data. The extent to

which the survey responses are internally consistent.

Validity:

Degree to which what the researcher was

trying to measure was actually measured.

Reliability and Validity

Prof. Rushen Chahal


9/22

Test and Retest:

The ability of the same instrument to produce consistent

results when used a second time under conditions as similar

as possible to the original conditions.

Stability:

Lack of change in results from test to test.

Equivalent Form:

When two very similar forms of an instrument produce

closely correlated results.

Testing Reliability

Prof. Rushen Chahal


10/22

Internal Consistency:

The ability of an instrument to produce similar results

when used on different samples during the same time

period to measure a phenomenon.

Spilt Half: A method of assessing the reliability of a scale by

dividing the total set of measurement items in half and

correlating the results.

Testing Reliability

Prof. Rushen Chahal


11/22

Face:

The degree to which a measurement seems to

measure what it is supposed to measure.

Content: The representativeness, or sampling adequacy, of

the content of the measurement instrument.

Testing Validity

Prof. Rushen Chahal


12/22

Criterion Related:

The degree to which a measurement instrument can

predict a variable that is designated a criterion.

Construct:

The degree to which a measurement instrumentrepresents and logically connects, via the underlying

theory, the observed phenomenon to the construct.

Testing Validity

Prof. Rushen Chahal


13/22

Convergent:

The degree of correlation among different measures

that purport to measure the same construct.

Discriminate:

The measure of the lack of association amongconstructs that are supposed to be different.

Testing Validity

Prof. Rushen Chahal


14/22

Predictive:

The degree to which a future level of a

criterion can be forecast by a current

measurement scale.

Concurrent:

The degree to which another variable,measured at the same point in time as the

variable of interest, can be predicted by the

measurement instrument.

Testing Validity

Prof. Rushen Chahal


15/22

Reliability and Validity

Prof. Rushen Chahal


16/22

Unidimensional:

Measures only one dimension of

a concept, respondent, or object.

Multidimensional:

Measures several dimensions of

a concept, respondent, or object.

Measurement Scales

Procedures for assigning numbers or

symbols to properties of an object in order

to impart some numerical characteristics

to the properties in question.

Prof. Rushen Chahal


17/22

Attitude Measurement Scales

Enduring organization of motivational,

emotional, perceptual, and cognitive

processes with respect to some aspect of a

persons environment.

Prof. Rushen Chahal


18/22

Important Not Important

1 2 3 4 5

Important Not Important

1 2 3 4 5 6

Odd Scale

Even Scale

Non-comparative Scale:

Scales in which judgement is made without reference to

another object, concept, or person.

Comparative Scale:

Scales in which one object, concepts, or person is compared

with another on a scale.


Prof. Rushen Chahal


19/22

Uses Comparative Scaling:

Put these fast food chains in order of preference:

McDonalds

Burger King

Taco Bell

Measurement scale employing a sophisticated form of rank ordering usingcard sorts. Respondents each rank X number of items in order from best to

worst by putting the cards representing the idea at hand into ranked piles.

Then the piles with the most become the top choices. The procedure can

be done many times to winnow down the choice to a top two or three.


Prof. Rushen Chahal


20/22

Which drink do

you prefer:

___Coke

___Pepsi

___Coke

___Sprite

___Pepsi

___Sprite

What features do you want in a car?

Sun roof ______

Leather ______ABS Breaks ______

CD Player ______

Total 100 points


Prof. Rushen Chahal


21/22

How do you like your pizza?

Hot Cold

Bland SpicyExpensive Inexpensive

Fresh Frozen

Natural Artificial

Soggy Crisp

Moist Dry

Is soggy prejudicial?

- - - - - - - - - - - - - - - - - -- - - - - - - - - - - - - - - - - -

- - - - - - - - - - - - - - - - - -- - - - - - - - - - - - - - - - - -

- - - - - - - - - - - - - - - - - -

- - - - - - - - - - - - - - - - - -

- - - - - - - - - - - - - - - - - -

-5

-4

-3

-2

-1High Value

+1

+2

+3

+4

+5


Prof. Rushen Chahal


22/22

Honda is a good car brand:

1 Agree

2 Somewhat Agree

3 Somewhat Disagree

4.Disagree

1 Agree

2 Somewhat Agree

3 Somewhat Disagree

4.Disagree

Multiple response

Single response

Controlled response

Check all that apply

Check only oneCheck the top three






Prof. Rushen Chahal

marketing research - concept of measurement

Documents