Chapter 10: Measurement annd Attitude Scaling

scale

A device providing a range of values that correspond to different characteristics or amounts of a characteristic exhibited in observing a concept

unbalanced rating scale

A fixed-alternative rating scale that has more response cate- gories at one end than the other resulting in an unequal number of positive and negative categories. Notice that there are three "satisfied" responses and only two "dissatisfied" responses above. The choice of a balanced or unbalanced scale generally depends on the nature of the concept or the researcher's knowledge about attitudes toward the stimulus to be measured. When respondents are expected to be predisposed toward one end of a concept or the other, unbalanced scales are appropriate. Otherwise, researchers are better off with balanced scales.

non-forced-choice scale

A fixed-alternative rating scale that provides a "no opinion" cate- gory or that allows respondents to indicate that they cannot say which alternative is their choice.

forced-choice rating scale

A fixed-alternative rating scale that requires respondents to choose one of the fixed alternatives.

balanced rating scale

A fixed-alternative rating scale with an equal number of positive and negative categories; a neutral point or point of indifference is at the center of the scale.

concept

A generalized idea that represents something of meaning Concepts such as age, sex, education, and number of children are relatively concrete having relatively unambiguous meanings. Concepts such as loyalty, personality, channel power, trust, corporate culture, customer satisfaction, value, and so on are more difficult to both define and measure.

graphic rating scale

A measure of attitude that allows respondents to rate an object by choosing any point along a graphic continuum.

Likert scale

A measure of attitudes designed to allow respondents to rate how strongly they agree or disagree with carefully constructed state- ments, ranging from very positive to very negative attitudes toward some object. • is a measure of attitudes designed to allow respondents to rate how strongly they agree or disagree with carefully constructed statements, ranging from very positive to very negative attitudes • Generally choose from five choices: • "Strongly Agree," "Agree," "Neutral", "Disagree," and "Strongly Disagree"

constant-sum scale

A measure of attitudes in which respondents are asked to divide a constant sum to indicate the relative importance of attributes; respondents often sort cards, but the task may also be a rating task.

semantic differential

A measure of attitudes that con- sists of a series of seven-point rating scales that use bipolar adjectives to anchor the begin- ning and end of each scale. is a scale type that has respondents describe their attitude using a series of bipolar rating scales • Bipolar adjectives—such as "good" and "bad," "modern" and "old-fashioned," or "clean" and "dirty"—anchor both ends (or poles) of the scale • The validity of the semantic differential depends on finding scale anchors that are semantic opposites

Attitudinal Rating Scales: Choice

A measurement task that identi- fies preferences by requiring respondents to choose between two or more alternatives

Attitudinal Rating Scales: Sorting

A measurement task that pre- sents a respondent with several objects or product concepts and requires the respondent to arrange the objects into piles or classify the product concepts.

Attitudinal Rating Scales: Rating

A measurement task that requires respondents to estimate the magnitude of a characteristicor quality that a brand, store, or object possesses.

Attitudinal Rating Scales: Ranking

A measurement task that requires respondents to rank order asmall number of stores, brands, or objects on the basis of overall preference or some characteristic of the stimulus.

paired comparison

A measurement technique that involves presenting the respon- dent with two objects and ask- ing the respondent to pick the preferred object; more than two objects may be presented, but comparisons are made in pairs.

split-half method

A method for assessing internal consistency by checking the results of one-half of a set of scaled items against the results from the other half.

multi-attribute model

A model that constructs an attitude score based on the multiplicative sum of beliefs about an option times the evaluation of those belief characteristics

Implement a multi-attribute model.

A multiattribute model represents a respondent's attitude about some activity, object, event, or idea by taking belief scores assessed with some type of rating scale and multiplying each belief score by an evaluation of the matching characteristic, also sup- plied using some type of rating scale, and then summing those products together. These attitude scores are expected to predict behavioral intentions with some degree of confidence. Multi- attribute models provide highly diagnostic information to competitive businesses and thus, they are widely applied.

category scale

A rating scale that consists of several response categories, often providing respondents with alter- natives to indicate positions on a continuum.

summated scale

A scale created by simply sum- ming (adding together) the response to each item making up the composite measure. The scores can be but do not have to be averaged by the number of items making up the composite scale.

face (content) validity

A scale's content logically appears to reflect what was intended to be measured. • refers to the subjective agreement among professionals that a scale logically reflects the concept being measured • Ex: Researcher judgment; weakest form of validity, but often used

attribute

A single characteristic or fun- damental feature of an object, person, situation, or issue.

Even the apparently simple concept of student performance is measured in many different ways.

A student can be assigned a letter corresponding to his/her performance as is typical of U.S.- based grading systems. A — Represents excellent performance B — Represents good performance C — Represents average performance D — Represents poor performance F — Represents failing performance A student can be assigned a number from 1 to 20, which is the system more typically used in France a. 20 — Represents outstanding performance b. 11-20 — Represent differing degrees of passing performance c. Below 11 — Represent failing performance A student can be assigned one of two letters corresponding to performance. a. P — Represents a passing mark b. F — Represents a failing mark

construct

A term used to refer to concepts measured with multiple variables.

test-retest method

Administering the same scale or measure to the same respon- dents at two separate points in time to test for stability.

attitude

An enduring disposition to consistently respond in a given manner to various aspects of the world; composed of affective, cognitive, and behavioral components. is an enduring disposition to respond consistently in a given manner to various aspects of the world, including persons, events, and objects • There are three components of attitude: • Affective component - how much affinity someone has toward the relevant matter • Cognitive component - represents an individual's awareness of the relevant matter • Behavioral component - the action that corresponds to a certain type of attitude

index measure

An index assigns a value based on how much of the concept being measured is associated with an observation. Indexes often are formed by putting several variables together.

reliability

An indicator of a measure's internal consistency. A measure is reliable when different attempts at measuring something converge on the same result When the measuring process provides reproducible results, the measuring instrument is reliable The test-retest method of determining reliability involves administering the same scale or measure to the same respondents at two separate times to test for stability If the measure is stable over time, the test, administered under the same conditions each time, should obtain similar results

convergent validity

Another way of expressing internal consistency; highly reliable scales contain convergent validity.

monadic rating scale

Any measure of attitudes that asks respondents about a single concept in isolation.

comparative rating scale

Any measure of attitudes that asks respondents to rate a con- cept in comparison with a bench- mark explicitly used as a frame of reference.

composite measures

Assign a value to an observation based on a mathematical derivation of multiple variables.

Define attitude and understand why it is so important in business research

Attitudes are a relatively enduring predisposition to respond consistently to various things including people, activities, events and objects. Attitudes are predispositions toward behavior and as such represent rules that inform a person as to the appropriate reaction in a given situation. Attitudes consist of three components: the affective, or the emotions or feelings involved; the cognitive, or aware- ness or knowledge; and the behavioral, or the predisposition to action. Attitudes are so important because when an attitude is known, behavior can be predicted with some degree of confidence.

Ordinal Example

Can see order of importance, but not degree of importance between the rankings. For example, if I love UCLA football and that is far and away my favorite team, using an Ordinal Scale, you can't tell how much more I like UCLA than the other teams. Note: a Likert scale, which is very common, and which we will talk about in a bit, is considered an Ordinal Scale.

How do you measure an Attitude?

Different techniques depending on your goals: • Direct, Indirect, Physiological Examples of types of questions: • Likert Scale • Semantic Differential • Paired Comparison • Constant Sum Scale

construct validity

Exists when a measure reliably measures and truthfully represents a unique concept; consists of several components including face validity, convergent validity, criterion validity, and discriminant validity. exists when a measure reliably measures and truthfully represents a unique concept • A Construct is a theoretical concept. It is usually not easy to measure directly • Ex: Self-Esteem, Academic Motivation, Social Anxiety • So, you need to define your construct and be clear about what you are trying to measure; and test several indicators to see if your hypothesis is correct

Distinguish levels of scale measurement.

Fourlevelsofscalemeasurementcanbeidentified.Each level is associated with increasingly more complex properties. Nominal scales assign numbers or letters to objects for identification or classification. Ordinal scales arrange objects based on relative magnitude of a concept. Thus, ordinal scales represent rankings. Interval scales also represent an ordering based on relative amounts of a concept, but they also capture the differences between scale values. Thus, interval scales allow stimuli to be compared to each other based on the difference in their scale scores. Ratio scales are absolute scales, starting with absolute zeros at which there is a total absence of the attri- bute. Nominal and ordinal scales are discrete. The mode is the best way to represent central tendency for discrete measures. Ratio measures are continuous and interval scales are generally treated as con- tinuous. For continuous measures, the mean represents a valid representation of central tendency.

Know how to form an index or composite measure.

Indexes and composite measures are formed by combining scores from multiple items. For instance, a composite score can be formed by adding the scores to multiple scale items, each intended to represent the same concept. Index scores and composite measures scores are often obtained in much the same way. However, they differ theoretically in that index scores do not have to be theoretically or statistically related to one another. Thus, reliability, validity, and sensitivity are characteristics of good measurement. Reli- ability represents the consistency and repeatability of a measure. Validity refers to the degree to which the instrument measures the concept the researcher wants to measure.

correspondence rules

Indicate the way that a certain value on a scale corresponds to some true value of a concept.

Behavioral Intention

Intentions represent the behavioral expectations of an individual toward an attitudinal object

reverse coding

Means that the value assigned for a response is treated oppositely from the other items. Thus, on a 5-point scale, the values are reversed as follows: 5 becomes 1 4 becomes 2 3 stays 3 2 becomes 4

continuous measures

Measures that reflect the intensity of a concept by assigning values that can take on any value along some scale range.

discrete measures

Measures that take on only one of a finite number of values.

interval Example

No zero point. Most common example is temperature.

Nominal, Ordinal, Interval, and Ratio Scales

Nominal - identifies the horse with a number Ordinal - Win, Place, Show identifies the order of the finish Interval - captures the interval of time between the horses Ratio - captures the odds of winning your bet

ordinal scales

Ranking scales allowing things to be arranged based on how much of some concept they possess • Have nominal properties • Include ranking scales (order) • Are somewhat arbitrary • Example: "win," "place," and "show" in a horse race tells which horse was first, second, and third, but does not tell by how much a horse won

Perform a basic assessment of scale reliability and validity.

Reliability is most often assessed using coefficient . Coefficient should be at least above 0.6 for a scale to be considered as accept- ably reliable.Validity is assessed in components.A measure that has adequate construct validity is one that is likely to be well measured. Construct validity consists of face or content validity, convergent validity (internal consistency), discriminant validity, and criterion validity. Statistical procedures like factor analysis can be helpful in providing evidence of construct validity.

Ratio Scales

Represent the highest form of measurement in that they have all the properties of interval scales with the additional attribute of representing absolute quantities; characterized by a meaningful absolute zero Represent absolute meaning Zero, therefore, has meaning in that it represents an absence of some concept • An absolute zero is a defining characteristic in determining between ratio and interval scales • For example, money is a way to measure economic value

nominal scales

Represent the most elementary level of measurement in which values are assigned to an object for identification or classification purposes only. * HORSE # • The value can be but does not have to be a number since no quantities are being represented • A qualitative scale • Marketing researchers use nominal scales quite often Examples: •Uniform numbers •Airport terminals •School bus numbers

internal consistency

Represents a measure's homogeneity or the extent to which each indicator of a concept converges on some common meaning

discriminant validity

Represents how unique or distinct is a measure; a scale should not correlate too highly with a measure of a different construct.

Determine what needs to be measured based on a research question or hypothesis.

Research- ers can determine what concepts must be measured by examining research questions and hypotheses. A hypothesis often states that one concept is related to another or that differences in some outcome concept will be observed across different groups. Therefore, the concepts listed in the hypotheses must have operational measures if the research testing them is to be performed.

interval scales

Scales that have both nominal and ordinal properties, but that also capture information about differences in quantities of a concept from one observation to the next. Classic example: Fahrenheit temperature scale: • 80 degrees is hotter than 40 degrees • One cannot conclude that the 40° is twice as cold as 80° • Illustration: convert the temperatures to the Celsius scale 80° F = 26.7° C and 40° F = 4.4° C. Not 2x as cold anymore.

criterion validity

The ability of a measure to correlate with other standard measures of similar constructs or established criteria. addresses the question: "Does my measure correlate with measures of similar concepts or known quantities?" • May be classified as either concurrent validity or predictive validity

validity

The accuracy of a measure or the extent to which a score truthfully represents a concept. Good measures should be both precise (i.e. reliable) and accurate (i.e. valid). Validity is the accuracy of a measure or the extent to which a score truthfully represents a concept • Achieving validity is not a simple matter • Addresses the problem of whether a measure indeed measures what it is supposed to measure • Note: A precondition for validity is that the measuring instrument is reliable. However, being reliable doesn't necessarily mean the instrument is valid.

Reliability vs. Validity

The differences between the two are illustrated below... A: The shots from the older gun are scattered ► low reliability B: The shots from the newer gun are closely clustered and on target ► high reliability and validity C: The shots from a newer gun are closely clustered but off target ► high reliability but low validity

coefficient alpha ()

The most commonly applied estimate of a multiple item scale's reliability. It represents the aver- age of all possible split-half reli- abilities for a construct.

Measurement

The process of describing some property of a phenomenon of interest, usually by assigning numbers in a reliable and valid way. • When numbers are used, the researcher must have a rule for assigning a number to an observation in a way that provides an accurate description • All measurement systems present the potential for error The decision statement, corresponding research questions, and research hypotheses can be used to decide what concepts need to be measured

operationalization

The process of identifying scale devices that correspond to properties of a concept involved in a research process.

Establishing Validity

The three approaches to establishing validity: 1. Face (content) validity 2. Criterion validity 3. Construct validity

Produce a scale that measures an attitudinal concept.

With a Likert scale, respondents indi- cate their attitudes by checking how strongly they agree or disagree with carefully constructed statements. An attitude can be represented with a series of Likert scale items. Typically, Likert scales contain between five and seven response points. A five-item Likert scale states a phrase with which a respondent expresses agreement. The response points would be "strongly disagree," "dis- agree," "neutral," "agree," "strongly agree." A semantic differential uses a series of attitude scales anchored by bipolar adjectives. The respondent indicates where his or her attitude falls between the polar attitudes. Constant-sum scales require the respondent to divide a constant sum into parts, indicating the weights to be given to various attributes of the item being studied.

Concurrent validity

is the degree in which the scores on a measurement are related to other scores on other measurements that have already been established as valid. Ex: You develop a replacement to the SAT that's shorter and easier to administer. You'd want to compare the results of that new test to the existing SAT to see if it accurately measures the same things as the SAT.

Predictive validity

which requires you to compare test scores to performance on some other measure in the future. Ex: voter polls prior to an election or purchase intent questions trying to predict the likelihood of purchasing a brand

Levels of Scale Measurement

• Marketing researchers use many scales • Important because it determines the mathematical comparisons that are allowed

The four levels of scale measurement (N-O-I-R):

•Nominal •Ordinal •Interval •Ratio