Quiz 2

Likert Scale

- A scale that asks respondents to indicate the extent to which they agree or disagree with a series of mental belief or behavioral belief statements about a given object. - The most widely used approach to scaling responses in survey research - Likert scales typically range from 2 to 10 - with 5 or 7 being the most common.

Forced Vs. Unforced Choice Scales

A scale consideration.

Measurement

An integrative process of determining the intensity (or amount) of information about constructs, concepts, or objects

Reliability

Another term for consistency. If one person takes the same test in different conditions, and always receives the same results, the test is reliable.

Scales that measure attitudes and behaviors

Likert Scale Semantic Differential Scale Behavioral Intention Scale

Scale reliability

Refers to the extent to which a scale can reproduce the same or similar measurement results in repeated trials

Construct development

The process of identifying characteristics that define the concept being studied. -You need to determine exactly what is to be measured. Example: Consider an object such as the Loyalty. - You can measure the number of times a certain brand is purchased, which is concrete - You can measure their attitudes towards the brand, which is abstract in nature

Discriminatory Power

The scale's ability to differentiate between these scale responses. - The more the scale points the greater the discriminatory power. Example: Going from a five point to a 7-point scale: - 1=Completely Disagree, 2=Disagree, 3=Neither Agree/Disagree, 4=Agree, 5=Completely Agree - 1=Completely Disagree, 2=Disagree, 3=Somewhat Disagree, 4=Neither Agree/Disagree, 5= Somewhat Agree, 6=Agree, 7=Completely Agree - So you can discriminate better between participants when you increase scale points and capture more variance in the population.

Rank-order scales

These allow respondents to compare their own responses by indicating their first,second, third, and fourth preferences, and so forth.

Types of Construct Validity

convergent and discriminant

Cronbach's alpha

- Split the scale questions into two halves - Calculate the correlation between responses of each pair - A coefficient alpha calculates the average of all possible split-half correlation measures. - The coefficient value can range from 0 to 1. A value of 0.7 or greater shows high internal consistency

Issues with Test-Retest

- You might not get the same respondents in your second trial - People might become sensitive to the scale and not respond accurately second time round - People's attitudes and behaviors might change between the two trials

Construct

-An abstract idea or concept formed in a person's mind -A hypothetical variable made up of a set of component responses or behaviors that are thought to be related -A combination of a number of variables that can be measured -These variables are related to each other and are intended to measure the same construct examples: brand loyalty, customer satisfaction, service quality, advertising recall

The two parts of measurement

-Construct selection/development -Scale measurement

Types of scale validity

-Face validity -Content validity

Nominal Scale

-For categorical variables with no inherent order or ranking -Objects are categorized into mutually exclusive, labeled subsets -No necessary relationships among categories -No ordering or spacing are implied -Responses do not contain a level of intensity -A nominal level of measurement is simply a matter of distinguishing by name e.g., 1 = male, 2 = female. -Even though we are using the numbers 1 and 2, they do not denote quantity. -Only possible arithmetic operation is a count of each category Examples: Meal Preference: Breakfast, Lunch, Dinner Political Orientation: Republican, Democratic, Libertarian, Green -Which one of the following soft drinks did you consume the most during the previous week? Coke 1 7-up 2 Pepsi 3 Dr. Pepper 4 -Are you? Male 1 Female 2 LGBTQ 3

Ratio Scale

-In addition to possessing the qualities of nominal, ordinal, and interval scales, a ratio scale has an absolute zero (a point where none of the quality being measured exists) -When the variable equals 0.0, there is none of that variable -Possible to say how many times greater or smaller one object is than another Examples: -Length: inches or centimeters -Years of work experience -Income: money earned last year -Number of children What is your height? __________ How many times did you go to Home Depot in the last week? _________

Interval Scale

-Interval scales provide information about order, and also possess equal intervals. -A scale that demonstrates absolute differences between each scale point -Distances represent equal values. -From the previous example, if we knew that the distance between 1 and 2 was the same as that between 7 and 8 on our 10-point rating scale, then we would have an interval scale. -The zero point is arbitrary; zero does not mean the variable does not exist. -Equal-interval scales of measurement can be devised for opinions and attitudes. Examples: -Temperature -IQ -Time of the Day on a 12-hour Clock -GPA

Types of Scale Measurement

-Nominal Scales -Ordinal Scales -Interval Scales -Ratio Scales

Ordinal Scale

-Ordinal refers to order in measurement. -An ordinal scale indicates direction, in addition to providing nominal information. -Ranks objects or arranges them in order by some common variable -Spacing between is uneven; does not provide information on how much difference there is between objects -Allows a respondent to express relative magnitude between the answers to a question -Low/Medium/High; or Faster/Slower are examples of ordinal levels of measurement. -Ranking an experience as a "nine" on a scale of 1 to 10 tells us that it was higher than an experience ranked as a "six." -Mathematical operations are limited to statistics such as median or mode Examples: -Socioeconomic status: Poor, Middle Class, Rich -Time of Day: Dawn, Morning, Noon, Afternoon, Evening, Night Rank the following stores based on your preference. Walmart ______ Target ______ Aldi ______ What is your age? <25 1 25-50 2 >50 3

Scale Considerations

-Scale Descriptors -Balanced versus unbalanced scales -Forced or non-forced choice scales

Techniques that help scale reliability

-Test-retest -Equivalent form -Internal Consistency

Balanced scale

A scale consideration A balanced scale has an equal number of positive (favorable) and negative (unfavorable) response alternatives. Example: How satisfied are you with the picture quality of your TV? 1=Completely dissatisfied, 2=Somewhat dissatisfied, 3=Slightly dissatisfied, or 4=Slightly Satisfied, 5=Somewhat satisfied, 6=Completely Satisfied

Scale Descriptors

A scale consideration Scale descriptors are the descriptions used for the scale points, description besides the number Example: On a 5-point scale: 1=Completely Disagree, 2=Disagree, 3=Neither Agree/Disagree, 4=Agree, 5=Completely Agree

unbalanced scale

A scale consideration an unbalanced scale has a large number of either positive or negative responses. Example: How satisfied are you with the picture quality of your TV? 1=Dissatisfied, vs. 2=Slightly Satisfied, 3=Generally satisfied, 4=Completely Satisfied

Graphic rating scales

A scale measure that uses a scale point format that presents the respondent with some type of graphic continuum as the set of possible raw responses to a given question

Semantic Differential Scale

A scale to measure attitudes and behaviors and a unique bipolar scale format that captures a person's attitudes or feelings about a given object. Examples: Bipolar scales: like/dislike, high quality/ low quality etc. Please rate below the extent to which you feel our product is reliable: 1=Unreliable, 7=Reliable

Likert scale

A scale to measure attitudes and behaviors and a scale that asks respondents to indicate the extent to which they agree or disagree with a series of mental belief or behavioral belief statements about a given object Example: "I do not think that advertisements influence my purchase behavior." - 1=Completely Disagree, 2=Disagree, 3=Somewhat Disagree, 4=Neither Agree/Disagree, 5= Somewhat Agree, 6=Agree, 7=Completely Agree

Behavioral Intention Scale

A special type of rating scale designed to capture the likelihood that people will demonstrate some type of predictable behavior intent toward purchasing an object or service in a future time frame. Example: If you were in the market for a tablet, how likely are you to buy each of the following brands? -Microsoft (Would definitely buy, Probably, Probably Not, or Would definitely not)

Test-Retest

A technique that helps scale reliability Step 1: Administer the scale to a set of respondents Step 2: Administer scale to either the same respondents at a significantly later time, or to a completely new set of respondents from the same population Example: Administer our scale of technical adaptability to students today, and again after a month to see if there is consistent measurement. -If there are very few variations between the two sets of responses, then the scale will be thought of as stable and reliable.

Internal consistency

A technique that helps scale reliability -Determining a scale's Internal consistency is a popular approach by researchers to quickly determine a scale's reliability. -Internal consistency: The degree to which the individual questions of a construct are correlated. (i.e. are they actually related to each other?) The most popular technique for internal consistency is using Cronbach's alpha. - Split the scale questions into two halves - Calculate the correlation between responses of each pair - A coefficient alpha calculates the average of all possible split-half correlation measures. - The coefficient value can range from 0 to 1. A value of 0.7 or greater shows high internal consistency Example -Respondents are asked to rate the statements in an attitude survey about computer anxiety. -One statement is: "I feel very negative about computers in general." -Another statement is: "I enjoy using computers." -People who strongly agree with the first statement should be strongly disagree with the second statement, and vice versa. -If the rating of both statements is high or low among several respondents, the responses are said to be inconsistent

Equivalent Form Technique

A technique that helps scale reliability - Create two similar versions of the same scale (change the wording). - Administer both versions to either the same sample or a two different samples from the same population. -Measure whether there is high correlation between the two. -However, different versions may not always be identical. -Might not be worth the time and cost to administer two versions of the same scale. -Thus both test-retest and equivalent form techniques are not time efficient and cost efficient techniques of determining reliability

Variability

A test is valid if it measures what it is supposed to measure. If the results of the personality test claimed that a very shy person was in fact outgoing, the test would be invalid. A valid test is always reliable but a reliable test could be invalid.

Scale validity

Assesses whether a scale measures what it is supposed to measure

Scale points

Designated degrees of intensity assigned to the responses in a given questioning or observation method. Example: Variable: Gender -Question: What is your gender? -Scale points: (1) male (2) female

Forced choice scales

Scales where you do not have neutral descriptors such as "Neither Disagree or Agree" is a forced choice scale

Scale Development Example

Suppose you develop a scale for the construct 'technical adaptability'. You define technical adaptability as a consumer's ability to solve issues with a product on their own, without contacting customer service. Example: - "How often do you explore solutions to a problem with a product on your own?" - "How often do you consult the product manual to figure out how a particular function works? Issues to consider: - Is the scale reliable? Will it always measure the same construct? - Is it a valid scale? Am I measuring what I had intended to?

Content validity

The extent to which a construct represents all relevant dimensions. ■ Content validity is assessed in the process of developing the scale by gathering data. ■ "Have I accounted for all dimensions of technical adaptability or am I leaving something out?" Example: - Construct: sleep quality, - Content validity: 19-item questionnaire that consists of 7 components: (1) subjective sleep quality, (2) sleep latency, (3) sleep duration, (4) habitual sleep efficiency, (5) sleep disturbances, (6) use of sleeping medication, and (7) daytime dysfunction (the Pittsburgh Sleep Quality Index (PSQI)). - Each of these 7 components aims to measure a different dimension of the construct, sleep quality. - More components you measure in your survey, more content validity has your measurement.

Scale Measurement

The process of assigning descriptors to represent the range of possible responses to a question about a particular object or construct.

Divergent (Discriminant) Validity

Type of construct validity Measures of (theoretically) unrelated constructs should not be correlated. - Example ■ Self-esteem and intelligence are theoretically different. ■ If you are measuring self-esteem, you should test that you are not actually measuring intelligence

Convergent validity

Type of construct validity Measures of (theoretically) related constructs should be correlated. - Example: ■ Self-esteem, self-worth, self-appraisal, and confidence are different constructs which in theory are related to each other. ■ Assume that you measure these constructs for a sample. ■ If the average self-esteem of the sample is low, self-appraisal, self-worth and confidence of the sample also should be low.

Unforced choice scales

When you have neutral descriptors, it is an unforced choice scale because you aren't forcing the respondent to pick either agree or disagree. Example: focus on 3 E.g. 1=Completely Disagree, 2=Disagree, 3=Neither Agree/Disagree, 4=Agree, 5=Completely Agree

Face Validity

is based on the researchers' intuitive and subjective evaluation. -Transparency; Whether it looks like you are measuring the right construct. -A subjective, superficial assessment is made after the scale is developed. Example: - Construct to be measured: Anxiety - Measures with face validity ■ "My stomach gets upset when I think about taking tests" ■ "My heart starts pounding fast whenever I think about all of the things I need to get done" - Measures without face validity ■ "I get headache when I drink too much" ■ "I like eating chips"