Monday, February 7, 2011

Chapter 5 – Rating Scales


 

Attitude Measurement


-          Respondents need help to express attitudes / describe images

 

Itemised Rating Scales


-          Researcher first develops a number of dimensions

-          Rating scale usually interval scale  à evenly spaced points

-          Neutral / middle point normally in middle of scale, but there are exceptions

o   Example – influence of advertising

-          Balanced scales

o   Unbalanced scales might be used when it is known that responses will be overwhelmingly in one direction, and need better discrimination in that direction

§  Example à customer service

-          Number of points on scale

o   7 is considered optimal by many researchers

o   Some researchers suggest 10 (as opposed to 5)

o   Issues

§  Distinction possible

§  Ability of respondents to discriminate

§  Degree of discrimination sought

§  Interview medium : telephone (fewer) vs self completion (more)

-          Don't Knows

o   Distinguishing between genuine mid point response ( neither agree nor disagree) and "Don't Know" can become serious issue

-          Odd or even number of points

o   Even – eliminate neutral mid point

o   Studies: including neutral scale position significantly increases number of neutral responses compared to accepting them spontaneously

o   Study: mid point used by respondents trying to reduce effort à exagerate true mid point score

 

Attitudinal Rating Scales

 

-          Likert scale

o   Agree – disagree scale

o   5 point scale

o   Full application: sum scores to provide overall attitudinal score for each individual

o   Means / std dev can be calc.

o   Issues

§  Order effect – order in which response codes are presented

·         Bias to left on self-completion scale

§  Acquiescence

·         Tendancy for respondents to say yes / agree

§  Central tendancy

·         Reluctance of respondents to use exteme positions

§  Pattern answering

·         Conflicting answers will identify

-          Semantic differential scale

o   Bipolar rating scale

o   Opposite statements of dimension are placed at two ends of scale and respondents are asked how much they agree.

o   Difficult to always determine opposites: modern vs old fashioned / traditional

o   Dimensions of similiar meaning should be given with reversed polarity to minimise pattern answering and check internal consistency of responses

-          Stapel Scale

o   Dimension or descriptor is placed at centre of scale that ranges from -5 to +5.

o   Similar to semantic differentials, but not necessary to find accuarte opposite to each dimension

-          Numeric scales

o   Simple form of scale

o   Eg 1 to 10

o   End point of scale should be verbally anchored.

-          Graphic scales

o   Continous bi-polar scale

o   Line between two end anchor points

o   Visual analoge scale

-          Pictorial Scales

o   Image of thermometer

-          Anchor strength

o   Wording of anchor statement is critical

§  Extremely vs very (satisfied)

 

Comparative Scaling Techniques


-          Paired comparisons

o   Choose between 2 objects

o   Repeat : every object compared with every other object

o   Easier than ranking

o   Limited to small number of objects

-          Constant Sum

o   Respondents asked to allocate fixed number of points between set of options to ind relative importance etc

o   Reuires some mental agility on part of respondent.

-          Card sorting

o   Sort cards into groups,

o   Then rank each group

-          Q  sort

 

 

 

 

 

 

 

No comments: