Description
It explains the fundamentals of measurement and scaling.
MEASUREMENT AND SCALING: FUNDAMENTALS AND COMPARATIVE SCALING
1. Nominal scale. This is used only as a labeling scheme where numbers serve only as labels or tags for identifying and classifying objects. The numbers in a nominal scale do not reflect the amount of a characteristic possessed by the objects, rather they are used only for identification. For example, numbers on baseball players uniforms, street names, or social security numbers. 2. Ordinal scale. This is a ranking scale in which numbers are assigned to objects to indicate the relative extent to which some characteristic is possessed. It is then possible to determine whether an object has more or less of a characteristic than some other object. For example, rankings of teams for the NCAA Basketball tournament, socioeconomic status, and quality rankings. 3. Interval scale. Numbers are used to rank objects such that numerically equal distances on the scale represent equal distances in the characteristic being measured. Examples include time and temperature. 4. Ratio scale. This is used to identify or classify objects, rank order the objects, and compare intervals and differences. For example, height, age, and income. Types of Scales o Comparative scales—a direct comparison of stimulus objects is elicited. Thus, two brands may be compared along a dimension such as quality. o Noncomparative scales—the respondent provides whatever standard seems appropriate to him/her, thus, only one object is evaluated at a time. In this case, one brand is rated on a scale independent of other brands. All comparative scaling techniques involve a direct comparison of stimulus objects with one another. 1. Paired comparison scaling. Here a respondent is presented with two objects at a time and asked to select one object in the pair according to some criterion. The data obtained is ordinal in nature. This is frequently used in marketing when comparisons of products or brands are being made. See Figure 8.3 for an example of paired comparison scaling.
2.
Rank order scaling. Respondents are presented with several objects simultaneously and asked to order or rank them according to some criterion. This is commonly used to measure preferences for brands as well as the importance of attributes. See Figure 8.4 for an example of rank order scaling.
3.
Constant sum scaling. Respondents are required to allocate a constant sum of units such as points, dollars, chits, stickers, or chips among a set of stimulus objects with respect to some criterion. Specific instructions are provided that if an attribute is not at all important, it is possible to assign zero points. If an attribute is twice as important as some other attribute it should receive twice as many points. See Figure 8.5 for an example.
4.
Q-sort scaling. This technique uses a rank order procedure in which objects are sorted into piles based on similarity with respect to some criterion.
5.
Magnitude estimation. Here numbers are assigned to objects such that ratios between the assigned numbers reflect ratios among the objects on the specified criterion.
6.
Guttman scaling or scalogram analysis. This is a procedure for determining whether a set of objects can be ordered into an internally consistent, unidimensional scale.
From the viewpoint of the respondents, nominal scales are the simplest to use, whereas ratio scales are the most complex. Respondents in many developed countries, due to higher education and consumer sophistication levels, are quite used to providing responses on interval and ratio scales. However, such is not the case in less developed countries. Preferences can, therefore, be best measured by using ordinal scales in less developed countries. In particular, the use of binary scales (e.g., preferred/not preferred) is recommended. EXAMPLE: While measuring preferences for jeans in the United States, Levi Strauss & Co. could ask consumers to rate their preferences for wearing jeans on specified occasions using a seven-point interval scale. However, consumers in Papua, New Guinea, could be shown a pair of jeans and simply asked whether or not they would prefer to wear it for a specific occasion (e.g., when shopping, working, relaxing on a holiday, etc.).
1.
Measurement is the assignment of numbers or other symbols to characteristics of objects according to certain prespecified rules.
2. 3.
The primary scales of measurement are nominal, ordinal, interval, and ratio. The differences between a nominal and an ordinal scale are that in nominal scales, the numbers serve only as labels or tags for identifying and classifying objects while in an ordinal scale the numbers are used as a ranking device. Although both nominal and ordinal scale data can be used for counting operations, ordinal scales permit the use of statistics based on centiles.
4.
The implications of having an arbitrary zero point in an interval scale means that any positive linear transformation of the form y = a + bx will preserve the properties of the scale. Hence, it is not meaningful to take ratios of scale values.
5.
The advantage of a ratio scale over an interval scale is that the origin is fixed. Hence, it is meaningful to take ratios of scale values. Statistics such as the geometric mean, harmonic mean, and coefficient of variation can be applied to analyze ratio scale data. However, this advantage is not significant because the commonly used statistics in marketing research can be calculated on interval data.
6.
A comparative rating scale involves the direct comparison of stimulus objects with one another.
7.
In paired comparison scaling, a respondent is presented with two objects at a time and asked to select one object in the pair according to some criterion.
8.
Paired comparison scaling is useful when the number of brands is limited because it requires direct comparison of brands. Thus, the disadvantages of paired comparison scaling are with a large number of brands the number of comparisons become unwieldy, violations of the assumption of transitivity may occur, the order in which the objects are presented may bias the results, and they bear little resemblance to the marketplace situation involving multiple alternatives. 9. In a constant sum scale, the respondents are required to allocate a constant sum of units such as points, dollars, chits, stickers, or chips among a set of stimulus objects with respect to
some criterion. The constant sum is a more refined ranking scale in that it allows fine discrimination among stimulus objects without requiring too much time. 10. Q-sort scaling was developed to discriminate among a relatively large number of objects while taking less time than other comparative scaling techniques. This technique uses a rank order procedure in which objects are sorted into piles based on similarity with respect to some criterion. The number of objects to be sorted should not be less than 60 nor more than 140—with 60 to 90 objects constituting a reasonable range. The number of objects to be placed in each pile is prespecified, often to result in a roughly normal distribution of objects over the whole set. In analyzing the data, successive integers are assigned to denote the subjective values of the piles.
doc_161330239.docx
It explains the fundamentals of measurement and scaling.
MEASUREMENT AND SCALING: FUNDAMENTALS AND COMPARATIVE SCALING
1. Nominal scale. This is used only as a labeling scheme where numbers serve only as labels or tags for identifying and classifying objects. The numbers in a nominal scale do not reflect the amount of a characteristic possessed by the objects, rather they are used only for identification. For example, numbers on baseball players uniforms, street names, or social security numbers. 2. Ordinal scale. This is a ranking scale in which numbers are assigned to objects to indicate the relative extent to which some characteristic is possessed. It is then possible to determine whether an object has more or less of a characteristic than some other object. For example, rankings of teams for the NCAA Basketball tournament, socioeconomic status, and quality rankings. 3. Interval scale. Numbers are used to rank objects such that numerically equal distances on the scale represent equal distances in the characteristic being measured. Examples include time and temperature. 4. Ratio scale. This is used to identify or classify objects, rank order the objects, and compare intervals and differences. For example, height, age, and income. Types of Scales o Comparative scales—a direct comparison of stimulus objects is elicited. Thus, two brands may be compared along a dimension such as quality. o Noncomparative scales—the respondent provides whatever standard seems appropriate to him/her, thus, only one object is evaluated at a time. In this case, one brand is rated on a scale independent of other brands. All comparative scaling techniques involve a direct comparison of stimulus objects with one another. 1. Paired comparison scaling. Here a respondent is presented with two objects at a time and asked to select one object in the pair according to some criterion. The data obtained is ordinal in nature. This is frequently used in marketing when comparisons of products or brands are being made. See Figure 8.3 for an example of paired comparison scaling.
2.
Rank order scaling. Respondents are presented with several objects simultaneously and asked to order or rank them according to some criterion. This is commonly used to measure preferences for brands as well as the importance of attributes. See Figure 8.4 for an example of rank order scaling.
3.
Constant sum scaling. Respondents are required to allocate a constant sum of units such as points, dollars, chits, stickers, or chips among a set of stimulus objects with respect to some criterion. Specific instructions are provided that if an attribute is not at all important, it is possible to assign zero points. If an attribute is twice as important as some other attribute it should receive twice as many points. See Figure 8.5 for an example.
4.
Q-sort scaling. This technique uses a rank order procedure in which objects are sorted into piles based on similarity with respect to some criterion.
5.
Magnitude estimation. Here numbers are assigned to objects such that ratios between the assigned numbers reflect ratios among the objects on the specified criterion.
6.
Guttman scaling or scalogram analysis. This is a procedure for determining whether a set of objects can be ordered into an internally consistent, unidimensional scale.
From the viewpoint of the respondents, nominal scales are the simplest to use, whereas ratio scales are the most complex. Respondents in many developed countries, due to higher education and consumer sophistication levels, are quite used to providing responses on interval and ratio scales. However, such is not the case in less developed countries. Preferences can, therefore, be best measured by using ordinal scales in less developed countries. In particular, the use of binary scales (e.g., preferred/not preferred) is recommended. EXAMPLE: While measuring preferences for jeans in the United States, Levi Strauss & Co. could ask consumers to rate their preferences for wearing jeans on specified occasions using a seven-point interval scale. However, consumers in Papua, New Guinea, could be shown a pair of jeans and simply asked whether or not they would prefer to wear it for a specific occasion (e.g., when shopping, working, relaxing on a holiday, etc.).
1.
Measurement is the assignment of numbers or other symbols to characteristics of objects according to certain prespecified rules.
2. 3.
The primary scales of measurement are nominal, ordinal, interval, and ratio. The differences between a nominal and an ordinal scale are that in nominal scales, the numbers serve only as labels or tags for identifying and classifying objects while in an ordinal scale the numbers are used as a ranking device. Although both nominal and ordinal scale data can be used for counting operations, ordinal scales permit the use of statistics based on centiles.
4.
The implications of having an arbitrary zero point in an interval scale means that any positive linear transformation of the form y = a + bx will preserve the properties of the scale. Hence, it is not meaningful to take ratios of scale values.
5.
The advantage of a ratio scale over an interval scale is that the origin is fixed. Hence, it is meaningful to take ratios of scale values. Statistics such as the geometric mean, harmonic mean, and coefficient of variation can be applied to analyze ratio scale data. However, this advantage is not significant because the commonly used statistics in marketing research can be calculated on interval data.
6.
A comparative rating scale involves the direct comparison of stimulus objects with one another.
7.
In paired comparison scaling, a respondent is presented with two objects at a time and asked to select one object in the pair according to some criterion.
8.
Paired comparison scaling is useful when the number of brands is limited because it requires direct comparison of brands. Thus, the disadvantages of paired comparison scaling are with a large number of brands the number of comparisons become unwieldy, violations of the assumption of transitivity may occur, the order in which the objects are presented may bias the results, and they bear little resemblance to the marketplace situation involving multiple alternatives. 9. In a constant sum scale, the respondents are required to allocate a constant sum of units such as points, dollars, chits, stickers, or chips among a set of stimulus objects with respect to
some criterion. The constant sum is a more refined ranking scale in that it allows fine discrimination among stimulus objects without requiring too much time. 10. Q-sort scaling was developed to discriminate among a relatively large number of objects while taking less time than other comparative scaling techniques. This technique uses a rank order procedure in which objects are sorted into piles based on similarity with respect to some criterion. The number of objects to be sorted should not be less than 60 nor more than 140—with 60 to 90 objects constituting a reasonable range. The number of objects to be placed in each pile is prespecified, often to result in a roughly normal distribution of objects over the whole set. In analyzing the data, successive integers are assigned to denote the subjective values of the piles.
doc_161330239.docx