8 The Concept of Measurement Measurement Process Measurement

8 The Concept of Measurement

Measurement Process • Measurement: process of assigning numbers/labels to persons, objects, or events in accordance with specific rules for presenting quantities/qualities of attributes. • Rule: guide, method, or command that tells a researcher what to do.

Measurement Process • Note: not the person, object, or event that is being measured, but rather, its attributes. • Example: A researcher does not measure a consumer per se but instead measures that consumer’s attitudes, income, brand loyalty, age, and other relevant factors.

Measurement Process • The concept of rules is key to measurement. (Rule: guide, method, or command that tells a researcher what to do. ) • Example: rule of measurement might state, “assign the numbers 1 through 5 to people according to their disposition to do household chores. If they are extremely willing to do any household chores, assign them a 1. If they are not willing to do any household chores, assign them a 5. ”

Measurement Process If the evaluation is satisfactory, the researcher Evaluate Identify the concept of interest the reliability and validity of the scale Utilizes the scale Which leads to Use the concept to That requires the researcher to A measure ment scale Develop a construct Which is used to create Which enables a researcher to create A constitutive definition An operational definition Which enables a researcher to develop Research findings

Step 1: Identify the concept of interest • A concept is an abstract idea generalized from particular facts. It is a category of thought used to group sense data together “as if they were all the same. ”

Step 2: Develop a construct • Constructs: specific types of concepts that exist at higher levels of abstraction than do everyday concepts. • Constructs are invented for theoretical use and thus are likely to cut across various preexisting categories of thought.

Step 2: Develop a construct • Generally, constructs are not directly observable. Instead, they are inferred by some indirect method from results such as findings on questionnaire. • Example of marketing constructs: brand loyalty, high-involvement purchasing, socialclass, personality, and channel power.

Step 3: Define the concept constitutively • Constitutive (or theoretical, or conceptual ) definition: statement of the meaning of central idea/concept under study, establishing its boundaries. • All constructs, to be capable of being used in theories, must possess constitutive meaning. Like a dictionary definition, a constitutive definition should fully distinguish the concept under investigation from all other concepts. A vague constitutive definition cause an incorrect research question to be addressed.

Step 3: Define the concept constitutively • For instance, to say that researchers are interested in studying marital roles would be so general as to be meaningless. To say that they want to examine the marital roles of newlyweds (married less than 12 months) from 24 to 28 years of age with 4 years of college may not even suffice. While one researcher may be interested in communication patterns as partners assume certain roles, a second researcher may be interested in parenting roles.

Step 4: Define the concept operationally • Operational definition: statement of precisely which observable characteristics will be measured and the process for assigning a value to the concept. • In other words, it assigns meaning to a construct in terms of the operations necessary to measure it in any concrete situation.

Step 4: Define the concept operationally • An operational definition serves as a bridge between a theoretical concept and real-world events/factors. • Constructs such as “attitude” and “highinvolvement purchasing” are abstractions that cannot be observed. Operational definitions transform such constructs into observable events. In other words, they define/give meaning to a construct by spelling out what the researcher must do to measure it.

Example The operational definition of role ambiguity was developed by 2 marketing professors for use with salespeople and customer service personnel. The theoretical notion is that role ambiguity leads to job stress and impedes a worker’s ability to improve performance and obtain job-based rewards, leading to job dissatisfaction. Constitutive and Operational Definitions of Role Ambiguity Constitutive Definition Role ambiguity is a direct function of discrepancy between the info. available to the person and that which is required for adequate performance of a role. It is the difference between a person’s actual state of knowledge that provides adequate satisfaction of that person’s personal needs and values. Operational Definition Role ambiguity is the amount of uncertainty (ranging from very uncertain to very certain on a 5 -point scale) an individual feels regarding job-role responsibilities and expectations from other employees and customers.

Example Measurement Scale of Role Ambiguity Measurement Scale The measurement scale consists of 45 items, with each item assessed by a 5 -point scale with category labels 1 = very certain, 2 certain, 3 = neutral, 4 = uncertain, 5 = very uncertain. Samples of the 45 items follow: • How much freedom of action I am expected to have • How I am expected to handle nonroutine activities on the job • To what extent my boss is open to hearing my point of view • How satisfied my boss is with me • How managers in other departments expect me to interact with them • How I am expected to interact with my customers • How my co-workers expect me to behave while on the job • How much info. my co-workers expect me to convey to my boss • About how much time my family feels I should spend on the job

Step 5: Develop a measurement scale • Scale: set of symbols/numbers so constructed that the symbols/numbers can be assigned by a rule to the individuals (or their behaviors/attitudes) to whom the scale is applied. The four basic levels of measurement: 1. Nominal level of measurement 2. Ordinal level of measurement 3. Interval level of measurement 4. Ratio level of measurement

Step 5: Develop a measurement scale • Nominal level of measurement Nominal scales: scales that partition data into mutually exclusive and collectively exhaustive categories. Example: Gender: (1) Male Geographic area: (1) Urban (2) Female (2) Rural (3) Suburban

Step 5: Develop a measurement scale • Ordinal level of measurement Ordinal scales: scales that maintain the labeling characteristics of nominal scales and have the ability to order data. Example: Please rank the following online dating services from 1 to 5, with 1 being the most preferred and 5 the least preferred. www. spark. com ______ www. eharmony. com ______ www. match. com ______ www. zoosk. com ______ www. friendfinder. com ______

Step 5: Develop a measurement scale • Interval level of measurement Interval scales: scales that have the characteristics of ordinal scales, plus equal intervals between points to show relative amounts; they may include an arbitrary zero point. This scale enables a researcher to discuss differences separating 2 objects. Example: Fahrenheit and Celsius scales; the freezing point of water is zero on one scale and 32 degrees on the others.

Step 5: Develop a measurement scale • Ratio level of measurement Ratio scales: scales that have the characteristics of interval scales, plus meaningful zero point so that magnitudes can be compared arithmetically. The ratio scale reflects the actual amount of a variable. Physical characteristics of a respondent such as age, weight, and height are examples of ratio-scaled variables.

Step 5: Develop a measurement scale Level Basic Empirical Description Operations Typical Descriptive Typical Usage Statistics Nominal Uses numerals to identify objects, individuals, events, or groups Determination of equality/inequality Classification (male/female; buyer/nonbuyer) Frequency counts, percentages/ modes Ordinal In addition to identification, provides info. about the relative amount of some characteristic possessed by an event, object, etc. Determination of greater/lesser Rankings/ratings (preferences for hotels, banks, etc. ; social class; rating of foods based on fat content, cholesterol) Median (mean and variance metric) Interval Possesses all the properties of nominal and ordinal scales plus equal intervals between constructive points Determination of equality of intervals Preferred measure of complex concepts/ constructs (temperature scale, air pressure scale, level of knowledge about brands) Mean/variance Ratio Incorporates all the properties of nominal, ordinal, and interval scales plus an absolute zero point Determination of equality of ratios Preferred measure when precision instruments are available (sales, number of on-time arrivals, age) Geometric mean/ harmonic mean

Step 6: Evaluate the reliability and validity of measurement • Reliability Degree to which measures are free from random error and, therefore, provide consistent data. Three ways to assess reliability: 1) test-retest 2) Internal consistency 3) Use of equivalent forms

Three ways to assess reliability 1) Test-retest: ability of the same instrument to produce consistent results when used a second time under conditions as similar as possible to the original conditions. 2) Internal consistency: ability of an instrument to produce similar results when used on different samples during the same time period to measure a phenomenon. 3) Use of equivalent forms: ability of 2 very similar forms of an instrument to produce closely correlated results.

Step 6: Evaluate the reliability and validity of measurement • Validity Degree to which what the researcher was trying to measure was actually measured. Types of validity include: 1) Face validity 2) Content validity 3) Criterion-related validity 4) Construct validity

Types of validity 1) Face validity: degree to which a measurement seems to measure what it is supposed to measure. It can refer to the subjective agreement of researchers, experts, people familiar with product, market, or industry. 2) Content validity: representativeness, or sampling adequacy, of the content of the measurement instrument. In other words, does the scale provide adequate coverage of the topic under study? 3) Criterion-related validity: degree to which a measurement instrument can predict a variable that is designated a criterion. 4) Construct validity: degree to which a measurement instrument represents and logically connects, via underlying theory, the observed phenomenon to the construct.

Group Project (20%) • Suppose you are the marketing research supplier. Develop the “marketing research proposal” for your selected client*. v. Your client must be a real business organization. v. You also need to attach the questionnaire (if you propose to do a survey) or discussion guide (if you propose to do the focus group) separately from this proposal when submitted. v. All details in the proposal should be based on the current situation of your selected client. • Due: 24 November 2015 (in class)