Measurement & Scaling Techniques

E. E. Okon MRCS
 Measurement in Research

Measurement is a relatively complex and
demanding task, specially so when it concerns
qualitative or abstract phenomena.

Assigning numbers to objects or observations
 Measurement scales

Based on mathematical properties

Classified into
 Nominal
 Ordinal
 Interval
 Ratio
 Nominal Scale

Assigning number symbols to events in order
to label them

E.g Numbers to Football players, basketball
players

Not considered to be associated with an
ordered scale

No quantitative value

No generally used measure of dispersion for
nominal scales.

Chi-square test is the most common test of
statistical significance that can be utilized
 Nominal Scale

Nominal scale is the least powerful level of
measurement

No order or distance relationship and has no
arithmetic origin
 Ordinal Scale

Ordinal scale places events in order.
 From Highest to lowest
 No absolute values
 Less than, more than or equal to

Rank orders e.g Allsaints Student ranking
according to USMLE scores

One has to be very careful in making statement
about scores based on ordinal scales.

For instance, if Ram’s position in his class is 10
and Mohan’s position is 40, it cannot be said
that Ram’s position is four times as good as that
of Mohan
 Interval scale

Intervals are adjusted in terms of some rule
that has been established as a basis for making
the units equal.

Arbitrary zero but lack a true zero

Lacks ability to measure the complete absence
of a trait of characteristics

Example: farenheit.

Equality of interval – More powerful
measurement than ordinal scale

Mean – Central tendency

S.D – Dispersion

Research in behavioural science
 Ratio Scale

An absolute or true zero of measurement.

E. g – Length

Comparisons can be made

Ratio scale represents the actual amounts of
variables

Most precise

Researchers in physical sciences.