The document discusses measurement scales and types of data in research. There are four main types of measurement scales: nominal, ordinal, interval, and ratio scales. Nominal scales classify objects into categories without order or ranking, while ordinal scales rank objects along a dimension but without precise distances. Interval scales provide meaningful distances between rankings but no true zero point, and ratio scales are the most precise with ordered and meaningful distances between points and a true zero. The document provides examples of applying different scales to measure store customers, voter attitudes, and stock preferences. It also discusses characteristics of good measurements, including validity, reliability, and practicality.
2. Measurement
While people measure things casually in daily
life, research measurement is more precise and
controlled.
Variables being studied in research may be
classified as objects or as properties.
– Objects include tangible items such as furniture,
laundry detergent, people or automobiles.
– Properties are the characteristics of the object. A
person's physical properties include weight, height
etc., and his psychological properties are attitudes
and intelligence.
cont...
4. An event is measured in terms of its
duration;
For duration, one measures the number of
hours and minutes recorded.
Measurement
5. Measurement
For what happened, one uses some system
to classify types of activities that occurred.
Measurement typically uses some sort of
scales to classify or quantify the data
collected.
There are four types of scales. In increasing
order of power, they are nominal, ordinal,
interval, and ratio.
cont...
6. Nominal – Classify into categories – no order, distance,
or natural origin
Example: personality type, religion, gender
Ordinal – Order objects along a dimension (ranking) but
no distance or natural origin
Example: Top 10 movies
Interval – Meaningful distances between rankings:
ordered, distance, but no natural origin
Example: thermometer
Ratio – Interval with true zero point (most precise):
ordered, distance, natural origin
Example: height, weight, age, length
Measurement
cont...
7. Measurement
A. Store Customers:
Nominal – Group them by race, ethnic
background, married or single status, etc.
Ordinal – Rank them as very frequent
buyers, frequent buyers, infrequent
buyers.
cont...
8. Measurement
Interval – Customer Satisfaction on
different points interval i.e.
Ratio – Average size of monthly
purchases
cont...
9. Measurement
B. Voter Attitudes
Nominal – grouped as PML(N), PPP, PTI, and
others;
Ordinal – Rank of candidates in order of
preference;
Interval – Likert – type scale. Most likely to win,
likely to win, neutral, less likely to win, cannot
win
Ratio – Count of votes for various candidates
in each district.
cont...
10. Measurement
C. Common Stock Preference
Nominal – Industry classification of
stocks;
Ordinal – Rank order of preference
stocks as your preference for them;
cont...
11. Measurement
Interval – Rating of preference for the
stock by converting the results of a paired
comparison rating into presumed interval
scale;
Ratio – Six-month changes in price of
various preferred stocks.
cont...
12. Characteristics of Good
Measurement
Three major criteria for evaluating a
measurement tool are: validity, reliability,
and practicality.
– Validity is the extent to which a test measures
what we actually wish to measure.
– Reliability has to do with the accuracy and
precision of a measurement procedure.
– Practicality is concerned with a wide range of
factors of economy, convenience, and
interpretability
13. Types of Data
Quantitative – things you measure
Examples: (age, time, scores, etc.)
How much does a book weigh?
Qualitative – things you categorize
Examples: (gender, race, class standing, etc.)
What color is the book?