Non Comparative Scale 2003 (2)

28
Noncomparative scaling techniques

Transcript of Non Comparative Scale 2003 (2)

Page 1: Non Comparative Scale 2003 (2)

Noncomparative scaling

techniques

Page 2: Non Comparative Scale 2003 (2)

Definition of noncomparative scales: Noncomparative techniques:

Continuous:Itemized:

Likert:Semantic:Stapel:

What else to think about: Multi-item: Scale evaluation:

Reliability:Validity:Generalizable:

Page 3: Non Comparative Scale 2003 (2)

Ø Are often called monadic scales because only one object is evaluated at a time.

Ø There is no comparison to another object

FAIROUZ

Page 4: Non Comparative Scale 2003 (2)

Continuous rating scale: Continuous rating scale: Allows the respondent to place a mark at any point along a line running between two extreme points rather than selecting from a set of predetermined response categories.Sometimes referred to as graphic rating scales.Easy to construct.Scoring them can be difficult and unreliable.Provides little new information

FAIROUZ

Page 5: Non Comparative Scale 2003 (2)

 How would you rate Sears as a department store?Version 1Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Probably the best Version 2Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -- - Probably the best0 10 20 30 40 50 60 70 80 90 100 Version 3

Very bad Neither good Very good nor bad

Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - -- - - - - - - - - - - - - - - - -Probably the best0 10 20 30 40 50 60 70 80 90 100

FAIROUZ

Page 6: Non Comparative Scale 2003 (2)

Has a number or brief description associated with each response category, the categories are ordered in terms of scale position

The commonly used itemized rating scales are the Likert, semantic differential, and Stapel scales.

FAIROUZ

Page 7: Non Comparative Scale 2003 (2)

A measurement scale with five response categories ranging from “strongly disagree” to “strongly agree”

It requires the respondents to indicate a degree of agreement or disagreement with each of a series of statements about the stimulus objects.

FAIROUZ

Page 8: Non Comparative Scale 2003 (2)

 Strongly Disagree Neither Agree

Strongly disagree agree nor

agreedisagree

 1. Sears sells high quality merchandise. 1 2X 3 4 5 2. Sears has poor in-store service. 1 2X 3 4 5 3. I like to shop at Sears. 1 2 3X 4 5 4. Sears doesn’t offer a good mix of 1 2 3 4X 5  different brand within a product category

5. The credit policy at sears are terrible 1 2 3 4X 5

The analysis can be conducted on an item-by-item basis (profile analysis), or a total (summated) score can be calculated.

FAIROUZ

Page 9: Non Comparative Scale 2003 (2)

Easy for the researcher to construct and administer this scale

Easy for the respondent to understand Suitable for mail, telephone, personal, and

electronic interviews

Disadvantage of LIKERT scale

• Takes longer to complete than other itemized rating scales

FAIROUZ

Page 10: Non Comparative Scale 2003 (2)

Is a seven point rating scale on which the end points are adjectives representing opposites.

Negative adjective or phrase sometimes appears on the left side of the scale and sometimes on the right.

houda

Page 11: Non Comparative Scale 2003 (2)

 SEARS IS:

Powerful --:--:--:--:-X-:--:--: WeakUnreliable --:--:--:--:--:-X-:--: ReliableModern --:--:--:--:--:--:-X-: Old-fashionedCold --:--:--:--:--:--:-X-: WarmCareful --:--:--:--:--:--:-X-: Careless

houda

Page 12: Non Comparative Scale 2003 (2)
Page 13: Non Comparative Scale 2003 (2)

• By plotting the results, the researcher can see overall differences and similarities among the objects measured 

DisadvantageDisadvantage

• The difficulty determining the appropriate bipolar adjectives required to construct the scale.

houda

Page 14: Non Comparative Scale 2003 (2)

Typically presented vertically, with one adjective appearing at the midpoint of a scale ranging from plus five to minus five.

SEARS 

+5 +5+4 +4+3 +3+2 +2X+1 +1

HIGH QUALITY POOR SERVICE-1 -1-2 -2-3 -3-4X -4-5 -5

HOUDA

Page 15: Non Comparative Scale 2003 (2)

DisadvantageDisadvantage

• Does not require a pretest of the adjectives or phrases

• It can be administrated over the telephone

• Confusing and difficult to apply• It is the last used of the three

itemized rating scalesHOUDA

Page 16: Non Comparative Scale 2003 (2)

Number of scale categories: Traditional guidelines suggest that no fewer than five and no more than nine categories of information should be used.

Balanced vs unbalanced: ~in balanced scale: the number of

favorable and unfavorable categories or scale points is equal.

~ in an unbalanced scale they are unequal.

HOUDA

Page 17: Non Comparative Scale 2003 (2)

Balanced scale Unbalanced scale

Jovan Musk for Men is Jovan Musk for Men is Extremely good Extremely good Very good Very good Good Good Bad Somewhat goodVery bad Bad Extremely bad Very bad HOUDA

Page 18: Non Comparative Scale 2003 (2)

Odd or Even number of categories: ~ When an odd number of categories

are used in a scale, the mid-point typically represents a neutral category.

~ The scale should have an odd number of categories if the researcher has reason to believe that a portion of the respondent population is actually neutral on a particular subject. HOUDA

Page 19: Non Comparative Scale 2003 (2)

Forced vs Nonforced Scales: ~ In a forced rating scale, the

respondents are forced or required to express an opinion, because a “no opinion” option is not provided.

~ a nonforced scale that includes a “no opinion” category may improve the accuracy of data.

HOUDA

Page 20: Non Comparative Scale 2003 (2)

Circle the appropriate answer:Students visiting campus like the housing that is available:

Strongly StronglyDisagree Agree 1 2 3 4 5

Circle the appropriate answer:Students visiting campus like the food service that is available:

Strongly StronglyDisagree Agree 1 2 3 4 5 No Opinion

HOUDA

Page 21: Non Comparative Scale 2003 (2)

A multi-item scale needs to measure only one attribute or behavior.

The process of ranking or measuring results from a series of questions or examinations testing the same attribute in a variety of ways. (For example, a questionnaire that asks you numerous questions that seem quite similar is likely using this form of analysis to get a better over all picture of your attitudes.)

HOUDA

Page 22: Non Comparative Scale 2003 (2)

Discriminant NomologicalConvergent

Test/ Retest

Alternative Forms

Internal Consistency Content Criterion Construct

GeneralizabilityReliability Validity

Scale Evaluation

FAIROUZ

Page 23: Non Comparative Scale 2003 (2)

Reliability: measures how consistent or stable the ratings generated by the scale are likely to be.

FAIROUZ

Page 24: Non Comparative Scale 2003 (2)

Validity : The scale needs to demonstrate that it actually measures what it is meant to measure: if it predicts that customers will recommend your brand, successive research should demonstrate that those customers do in fact recommend your brand.

HOUDA

Page 25: Non Comparative Scale 2003 (2)

HOUDA

Page 26: Non Comparative Scale 2003 (2)

Generalizable - The scale should work in multiple collect modes (web, paper, telephone, face-to-face) and across the target population.

Page 27: Non Comparative Scale 2003 (2)

The true score model provides a framework for understanding the accuracy of measurement.

XO = XT + XS + XR

where

XO = the observed score or measurement

XT = the true score of the characteristic

XS = systematic error

XR = random error

Page 28: Non Comparative Scale 2003 (2)

Systematic error – affects the measurement in a constant way, that is, the same way each time the measurement is made

Random error – arises from random changes and has a different effect each time the measurement is made