MEASUREMENT AND SCALING

Measurement and Scaling

 Measurement means assigning numbers or some other

symbols to the characteristics of certain objects.

 When numbers are used, the researcher must have a rule for assigning a
number to an observation in a way that provides an accurate
description.

 Scaling is an extension of measurement.

 Scaling involves creating a continuum on which measurements on

objects are located.
 Types of Measurement Scale

 Nominal scale is the lowest level of measurement.

 Numbers are assigned for the purpose of identification of the objects.

 Any object which is assigned a higher number is in no way superior to
the one which is assigned a lower number.
• Are you married? (a) Yes (b) No

 Properties:
 Assigned values cannot be added, subtracted, multiplied or divided.
 Only count operation of each category is possible.
 A frequency distribution can be prepared
 Mode of distribution can be worked out.

 Limitations:
 Cannot say whether the assigned number to an object is higher or lower
than the one assigned to other object.
 Types of Measurement Scale
 Ordinal scale is next level of measurement and tells whether an
object has more or less of characteristics than other objects.

 It tells us the relative positions of the objects and the difference between
the magnitudes of the objects
 Assigned ranks cannot be added, multiplied, subtracted or divided.
 Compute median, percentiles and quartiles of the distribution.
 Rank order correlation coefficient.
 Ordinal scale is higher than nominal scale measurement
 Techniques applicable to nominal scale can be used for ordinal scale

Rank the following attributes while

choosing a restaurant for dinner.
Most important attribute may be
ranked no. 1, next important may be
assigned a rank no. 2 and so on.
 Types of Measurement Scale

 Interval scale is the next higher level of measurement.

 Difference of the score on interval scale has meaningful interpretation.

 Here the respondent is able to answer the questions on a continuum scale.
• Numbers on this scale can be added, subtracted, multiplied or divided.
• Compute mean, median, mode, standard deviation, correlation regression,
factor analysis and conduct a t-test, z-test, F-test.
 Types of Measurement Scale

 Ratio scale is the highest level of measurement and takes care

of all the limitations of all other scales.
 The ratio of measurements on the scale does have a meaningful
interpretation.

 Mathematical form of the ratio scale data is given by Y = b X.

 In ratio scale, there is a natural zero (origin).
 All mathematical and statistical operations can be carried out using the
ratio scale data.
 Classification of Scales

 Single item scale: Only one item to measure a given subject.

• How satisfied are you with your current job:

• Highly dissatisfied
• Dissatisfied
• Neutral
• Satisfied
• Highly satisfied.
 Classification of Scales
 Multiple item scale: Many items that play a role in forming the
underlying subject that the researcher is trying to measure.

 How satisfied are you with the pay you are getting on your
current job:
• Highly dissatisfied
• Dissatisfied
• Neutral
• Satisfied
• Highly satisfied.

 How satisfied are you with rules and regulations of your

organization:
• Highly dissatisfied
• Dissatisfied
• Neutral
• Satisfied
• Highly satisfied.
Classification of Scales
Comparative scales
 Comparison of Scales

 Paired comparison scales:

• From four items i.e. chocolate, burger, ice cream, pizza, chose one pair

• (chocolate or burger)
• (chocolate or ice cream)
• (chocolate or pizza)
• (burger or ice cream)
• (burger or pizza)
• (ice cream or pizza).
 Comparison of Scales

 Rank order scale

 Rank the following soft drinks in order of your preference:

 Coke
 Pepsi
 Limka
 Sprite
 Mirinda
 Seven up
 Comparison of Scales

 Constant sum rating scale:

 Allocate 100 points among the various school in which you like to admit
your child.
 DPS
 APEEJAY
 DAV
 Tagore Int
 Mother Int
 Laxman public
 Comparison of Scales

 Q-sort technique

 Sort the objects into different piles based on their similarity.

 100 statements pile them into five group and assigned strongly agree to strongly
disagree
 Non-Comparative Scales
 Graphic Rating Scale
 It is continuous scale and respondent is asked to tick his preference on a
graph.

 Please put a tick mark (√) on the following line to indicate your preference for
fast food.

• How do you like fast food by pointing to the face that best shows your
attitude and taste.
 Itemized rating scale

 Provided with a scale that has a number of brief descriptions associated

with each of the response categories such as
 very important, relatively important, neither important nor unimportant,
relatively unimportant, very unimportant.
 Balanced versus unbalanced scales:
 An equal number of favorable and unfavorable categories
 Odd or even number of categories:
 Forced to choose positive or negative side but not neutral category.

 Likert scale
 Provided a certain number of statements on which they are asked to
express their degree of agreement or disagreement.

 Semantic Scale
 This scale bounded each end by bipolar adjectives or phrases.
Likert Scale
Semantic Scale
 Classification of Scales

Stapel Scale: It measure the direction and intensity of an attitude

 Attitude
 It can not measure directly but derived from perceptions.
 A company is able to sell its products or services when its customers
have a favorable attitude towards its products or services.

 Cognitive component
 Individual’s knowledge, awareness and belief on attributes of an object.
• If a respondent is asked to name any company manufacturing plastics products,
respondent say Tupperware.

 Affective component
 Person’s overall feeling or emotions towards the objects.
• Choice from several alternative, Pepsi, Coke, Limca and Sprite

 Intention or action component

 Reflects a predisposition to an action by reflecting the consumer’s buying or
purchase intention.
• How likely a person is to buy a designer carpet may range from most likely to not
at all likely reflecting the purchase intention