Market Research-Measurement Techniques

For this session we focused on measurement and the importance of being able to develop scales in order to caputre data regarding a respondents attitudes, behaviour or opinions. 

A scale is set of symbols so constructed that the symbols or numbers can be assigned by a rule to the individual (or their behaviour or attitudes) to whom the scale is applied.

There are four levels of measurement which are:

1. Nominal
2. Ordinal
3. Internval
4. Ratio

Nominal Scales

These partition date into mutually exclusive and collectively exhaustive categories. Can use labels like user/non user, occupations etc.


Ordinal Scales

Ordinal scales are nominal scales that can order data.  They

are used to measure preferences for brands, social class

etc.

Internval Scales

These are ordinal scales with equal intervals between points

to show relative amounts.  This allows the researcher to use

more powerful statistical tests and to compare the size of

difference between members.  For example, the grade point

average on a 0 to 4.0

 

Ratio Scales

These are interval scales with a meaningful zero so that

magnitudes can be compared.  For example units sold,

number of purchasers, probability of purchase.

 

When we are focusing on measurement we also have to take

into account two important factors which are reliability and

validity

 

Reliablity is where a measurement provides consistent

results over time

 

Validity -This focuses on whether we have measured what

we set out to measure

 

Attitude Scales

Scaling refers to a procedure for the assignment of numbers

or other symbols to a property of objects, in order to impart

some of the characteristics of numbers to the properties in

question.

There are two different types of attitude scales:

• Unidimensional Scales
• Multidimensional Scales