Textbook Notes (373,326)
CA (164,596)
York (13,204)
ADMS (1,669)
ADMS 4260 (5)


8 Pages

Administrative Studies
Course Code
ADMS 4260
Manfred Maute

This preview shows pages 1-2 and half of page 3. Sign up to view the full 8 pages of the document.
MEASUREMENT & QUESTIONNAIRE DESIGN Commentary Despite the obvious time, energy and cost associated with responding to a mail questionnaire or participating in a personal/telephone interview, researchers hardly ever pay people to provide primary data. The basic premise behind gathering primary data is that people are more likely to provide complete, accurate, high quality data if the research the rewards of participating in the study are maximized and the costs are minimized. In this section, we identify the four major sources of error that arise when gathering primary data by communication, contrast the challenges posed by measuring objective properties and subjective constructs, and examine four different scales of measurement. and how question form, wording, sequence and other design features influence perceptions of the rewards and costs associated with research participation and contribute to the collection of accurate, complete, high quality primary data. Our learning objectives include: 1. define measurement and contrast the challenges posed by measuring objective properties and subjective constructs; 2. define four sources of error that arise when collecting primary data by communication; 3. review nominal, ordinal, interval and ratio scales of measurement and examine how these approaches to measurement influence the design survey questions; 4. examine different types of commonly used rating scales and assess their usefulness for capturing state-of-mind and state of intention data. MEASUREMENT (defined) … Objective Properties Subjective Properties physically verifiable characteristics unobservable mental constructs (i.e., Age, Income, $ Spent) measured indirectly by indicators (i.e., Satisfaction, Purchase Intention) Construct Development Identifying and defining what is being measured Scaling Assigning a set of descriptors to represent the range of responses to a question about a characteristic of interest MEASURING AIRLINE SAFETY Scale of Operations Maintenance Personal Injuries AIRLINE Pilot Experience/Training SAFETY Aircraft Damage Aircraft Age/Condition Magnitude of Accident Operational Definition of Airline Safety serious personal injuries and substantial damage to aircraft per 100,000 departures Accident Rating Departures U.S. Air (5 fatal crashes, > 300 fatalities) 0.242 5,782,745 Tower Air (0 crashes, 2 mishaps) 8.680 23,041 MEASURING BRAND LOYALTY Commentary Consider how a complex Marketing Construct like Brand Loyalty should be measured. What do marketers mean by ‘Brand Loyalty’? How can we assign a value to a customer that accurately and objectively reflects the intensity of his/her loyalty to a particular brand? How Should Brand Loyalty be Operationalized? 1. C 2. C 3. C Majority of 4. C Purchases 5. C Four Consecutive (Coke) 6. P Purchases 7. P (Pepsi) 8. P 9. P 10. C Last Purchase (Coke) Measures for Brand Loyalty Based on Different Construct Development and Scaling Majority of Purchases Coke Pepsi Last Purchase Coke Pepsi Four Consecutive Purchases Coke Pepsi MEASUREMENT PROPERTIES Commentary Establishing a measurement rule for assigning numbers to people, ideas, events or objects involves consideration of the underlying properties of the construct being measured. The fundamental premise is that a measure should reflect the underlying properties of the construct being measured. FOUR PROPERTIES TO CONSIDER 1. Assignment (identify) 2. Order (less than/greater than) 3. Distance (different by this much) 4. Origin (half as often, twice as much) NOMINAL SCALE > the most basic of the four levels of measurement, only the assignment property is activated > it is permissible only to categorize observations into mutually exclusive categories > there is no implication of differences in relative magnitudes Example? Which of the soft drinks on the following list do you like? Check all that apply. □ Coke □ Dr. Pepper □ Fanta □ Mountain Dew □ Pepsi □ 7 UP Note how ‘liked’ brands are identified, but no inferences about the degree of liking are supported. ORDINAL SCALE > assignment and order scaling properties are activated > it is permissible to rank-order observations and to draw inferences about ‘greaterthan/less than’, ‘more often/less often’ etc. > it is not permissible to draw inferences about absolute differences Example? Please rank the following soft drinks according to your degree of liking for each, assigning a rank of ‘1’ to your
More Less
Unlock Document
Subscribers Only

Only pages 1-2 and half of page 3 are available for preview. Some parts have been intentionally blurred.

Unlock Document
Subscribers Only
You're Reading a Preview

Unlock to view full version

Unlock Document
Subscribers Only

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.