Scaling and Measurement

You might also like

Download as ppt, pdf, or txt
Download as ppt, pdf, or txt
You are on page 1of 17

Scaling and Measurement

Measurement
Selecting observable empirical events
Using numbers or symbols to represent aspects of the events Applying a mapping rule to connect the observation to the symbol

What is Measured?

Objects-things of ordinary experience and that are not that concrete Properties-characteristics of objects

Sad-to-Happy Faces that Work with Children (and Adults!)

Sources of Measurement Differences

Respondent Situational factors Measurer or researcher Instrument

Scaling
Assigning numbers to indicants of the properties of objects Dimensions of a Scale: Unidimensional Multidimensional

Validity
Content Validity Criterion-Related Validity Concurrent Predictive

Construct Validity

Reliability
Stability Test-retest Alternative forms reliability Parallel forms Internal Comparision reliability - Co-efficient alpha

Practicality
Economy
Convenience Interpretability

Scales of Measurement
Scale
Nominal

Basic Comparisons
Identity

Typical Examples
Male-female User-nonuser Occupations Uniform numbers Preference for brands Social class Hardness of minerals Graded quality of lumber Temperature scale Grade point average Attitude toward brands Awareness of advertising Units sold Number of purchasers Probability of purchase Weight

Measures of Average
Mode

Ordinal

Order

Median

Interval

Comparison of intervals

Mean

Ratio

Comparison of absolute magnitudes

Geometric mean Harmonic mean

Assessing a Respondents Liking of Soft Drinks With Nominal, Ordinal, Interval, and Ratio Scales
Nominal
Which of the soft drinks in the following list do you like? (Check ALL that apply): ___Thums Up ___Limca ___Mountain Dew ___Pepsi ___Seven Up ___Sprite

Ordinal
Rank the soft drinks according to how much you like each (most preferred drink = 1, and least preferred drink = 6): ___Thums Up ___Limca ___Mountain Dew ___Pepsi ___Seven Up ___Sprite

Interval
Please indicate how much you like each soft drink by checking the appropriate position on the scale: dislike like a lot dislike like a lot Thums Up ____ ____ ____ ___ Limca ____ ____ ____ ___ Mountain Dew ____ ____ ____ ___ Pepsi ____ ____ ____ ___ Seven Up ____ ____ ____ ___ Sprite ____ ____ ____ ___

Ratio
Please divide 100 points among these soft drinks To represent how much you like each:

___Thums Up ___Limca ___Mountain Dew ___Pepsi ___Seven Up ___Sprite 100

Types of Response Scales

Rating Scales
o Likert o Multiple choice o Semantic Differential

Ranking Scales
o o Forced Ranking Comparision

Likert Scales
Used to measure attitudes and opinions Should be used for multiple item scales Sufficient variability in answers

1 2 3 4 5

Strongly Agree Somewhat Agree Neutral Somewhat Disagree Strongly Disagree

Multiple Choice Multiple Response


Check any type of item you usually have for breakfast Eggs Toast Idli Chapattis Cake

Single Item Response


Check the category of fast Food that you ate most frequently last month o Egg rolls o Pizza o Burgers o Chowmin

Semantic Differential Scale


Measuring images, profiles, people, things Adjectives should define a single dimension Must clearly state what respondent it to rate No more than about twenty items should be used Good Foolish Pleasant Beneficial Bad Wise Unpleasant Harmful

Forced Ranking Scale


Number of items ranked should be small (<10) Cannot determine the distance (intervals) between the rankings Single judgment criterion must be stated Rank the following four brands from 1(favorite) to 4 (least favorite) Pepsi Coke Sprite Mirinda

Comparison Scales Paired Comparative Compare one standard entity. to one or more others The standard should be very familiar to all respondents Rating scale should have an equal number of alternatives

Fewer than 10 items Used when the choice is actually dichotomous No ability to measure distance Lack of transitivity
Coke vs. Pepsi Pepsi vs. Mirinda Mirinda vs. Coke

Compared to A, B is o Very superior o About the same o Inferior

You might also like