id DATA MEASUREMEN T.

.
. .
f numerical data are gathered in businesses eve ---:-----_ d
.
Millions o I b ry
. n'lyriad items. For examp e, num ers represent costs 0 f. ay' repre-
sent1ng ,.. raphical locations
. o f re t ai·1 ou ti ets, weights
. of sh' 1terns
· Pro-
duce d, ge Og I · ipments
k' gs of subordinates at year Y reviews. All such data sh Id , and
ran in d the same way statistically because the entities rep ou not be
ahna 1yz~bers are different. For this reason, the business resea:eshented by
t e nu c er need
know the level of data measurement represented by the numb en bemg . s·
analyzed. ·
The disparate use of numbers can be illustrated by the numbers 40 d 8
which could represent the weights of t~o objects being shipped, the ;:tin:~
received on a consumer te~t by two different products, or football J.
.d . Al h ersey
numbers of a fullback an d a wi e receiver. t ough 80 pounds is twice
much as 40 pounds, the wide r,eceiver is pr_o bably not twice as big as t~:
fullback! Averaging the two weights seems reasonable, but averaging the
football jersey numbers makes no sens~. The appropriateness of the data
analysis · depends on the level of measure-
ment of the data gathered. The phenomenon Highest Level of Data Measurement
represented by the numbers determines the
level of data measurement. Four common \ Ratio
levels of:data measurement follow.
Toterval
1. Nominal
2. Ordinal Ordinal

3. Interval
Nomiri.;1.I
4. Ratio
Nominal is the lowest level ~f data measure- Lowest Level of Data Measurement
ment followed by ordinal, interval, and ratio.
Figure 1.3: Hierarchy of
Ratio is the highest level of data measure-
ment, as shown in Figure 1.3. Levels of Data