Term
| Threats to Internal Validity |
|
Definition
| 1. History, 2. Maturation, 3. Testing, 4. Instrument, 5. Selection, 6. Mortality, 7. Regression to the mean |
|
|
Term
|
Definition
| Nominal scales, Ordinal scales, Internal scales, Ratio scales |
|
|
Term
|
Definition
| partitions data into one category or another. ie: male-10, female-7. Gives us frequency counts, percentages, mode |
|
|
Term
|
Definition
| Balanced ranking or scale, ordering answers. Gives you all above + a rank and a media |
|
|
Term
|
Definition
| contains all features of ordinal scales with added dimension that the intervals between the data points on the scale are equal. Gives you all above + means, variances. -- Distances are the same, '0' has no meaning |
|
|
Term
|
Definition
| All powers of those mentioned as well as a meaningful absolute zero or origin. Gives you all above + magnitutes and ratios, and zero has meaning. |
|
|
Term
|
Definition
| consistent results over time and measures are free from error. Random error (as goes down, sample size goes up), Systematic (goes up with sample size) |
|
|
Term
|
Definition
| Obtained by repeating the measurement using the same instrument under as nearly the same conditions as possible. |
|
|
Term
| Equivalent Form Reliability |
|
Definition
| Avoids the test-retest by creating equivalent forms of measurement instrument. Two different instruments, maybe the same people. |
|
|
Term
| Internal Consistency Reliability |
|
Definition
| Assess the ability to produce similar results using different samples to measure a phenomenon. Same instrument, but admin.to two or more groups. May or may not contain same people. |
|
|
Term
| You must have _______ before you can have _______. |
|
Definition
|
|
Term
|
Definition
| A variation between the information being sought and the info. obtained. |
|
|
Term
|
Definition
| Using an incomplete or inaccurate sampling frame. |
|
|
Term
|
Definition
| mistakes in the transfer of info. from survey documents to the computer |
|
|
Term
|
Definition
| = Is there a difference in people who did vs. those who didn't? |
|
|
Term
| Measurement Instrument Bias |
|
Definition
| problems with the measurement instrument or questionare |
|
|
Term
|
Definition
| A variation between the information being sought and the info. obtained |
|
|
Term
|
Definition
| Use of incomplete or improper sampling procedures or when appropriate selection procedures are not properly followed |
|
|
Term
|
Definition
| mistakes or problems in the research design |
|
|
Term
|
Definition
| Door-to-door Interviews, Mall Intercept, Executive Interviewing, Telephone Interviewing, Central Location Telephone Interviewing, Computer-Assisted Telephone Interviewing, Self-Administered Interviewing, Mail Surveys, Internet Surveys |
|
|
Term
|
Definition
| Graphic, Itemized, Rank Order, Paired Comparison, Constant Sum, Semantic Differential, Stapel, Likert, Purchase Intent |
|
|
Term
|
Definition
| Measurement of agreement, 5 point |
|
|
Term
|
Definition
| What will they do in the future. Assess Demand, Projective Analysis |
|
|
Term
|
Definition
| Measurement scales that include a graphic continuum, anchored by two extremes |
|
|
Term
|
Definition
| Measurement scales in which the respondent selects an answer from a limited number of ordered categories. |
|
|
Term
|
Definition
| Measurement scales in which the respondent compares two or more items and ranks them. |
|
|
Term
|
Definition
| Measurement scales that ask the respondent to pick one of two objects in a set |
|
|
Term
|
Definition
| Measurement scales that ask the respondent to divide a given number of points, typically 100, among two or more attributes, based on their importance to them. |
|
|
Term
| Semantic Differential Scales |
|
Definition
| Measurement scales that examine the strengths and weaknesses of a concept by having the respondent rank it between parts of words that could be used to describe it |
|
|
Term
|
Definition
| Measurement scales that require the respondent to rate, on a scale ranging from +5 to -5, how closely and in what direction a descriptor fits a concept. |
|
|
Term
|
Definition
| Measurement scales in which the respondent spcifies a level of agreement with statements expresses an favorable or unfavorable attitude towards a concept. |
|
|
Term
|
Definition
| Questionnaires sent to selected names and addresses without prior contact by the researcher |
|
|
Term
| Natural vs Contrived Observations |
|
Definition
| Natural Obs. occurs when those being observed have no idea they are under observation. Contrived Obs. is lower cost and recruites a group to participant in a specific behavior and results might therefore be different. |
|
|
Term
| Open vs. Disguised Observation |
|
Definition
| Open Obs. occurs when participants know they are being observed and can see the Observer where as a Disguised Obs. may occur with the Observer behind a one-way glass. |
|
|
Term
| Structured vs. Unstructured Observation |
|
Definition
| Structured Obs. usually included the observer filling out a form on each person observed, usually counting number of occurances of a certain behavior where Unstructured may only make notes. |
|
|
Term
| Human vs. Machine Observers |
|
Definition
| Machines can sometimes offer the advantages of being less expensive, more accurate, and readily. ie: Traffic-counting, AC Nieslon. |
|
|
Term
| Direct vs. Indirect Observation |
|
Definition
| Direct Obs. is any research done on current behavior where as Indirect Obs. looks at past behavior, ie: Garbologists |
|
|
Term
|
Definition
| Researchers who sort through people's garbage to analyze consumption |
|
|
Term
|
Definition
| People who pose as consumers and shop at a company's store or competitors to collect data about customer-employee interactons and gather observation data. |
|
|
Term
|
Definition
| Level 1, conducts a mystery phone call and measures level of service. Level 2, shopper visits and makes quick purchase with little-no interaction. Level 3, shopper uses a script and initiates a conversation with an employee. Level 4, shopper visits with excellent communication skill and product knowledge and measures services quality with an high-level interaction. |
|
|
Term
|
Definition
| the degree to which an experiement actually measures what it was set out to. Depends on the level the measure is free from both systematic and random error. |
|
|
Term
|
Definition
| The extent to which competing explanations for the results observed can be ruled out. |
|
|
Term
|
Definition
| The extent to which causal relationships measured in an experiment can be generalized to outside persons, settings, and times. |
|
|
Term
| Solomon four-group design |
|
Definition
| Research in which two experimental groups and two control groups are used to control for all extraneous variable threats. |
|
|
Term
|
Definition
| Testing of a new product or some element of the marketing mix using an experimental or quasi-experimental design. |
|
|
Term
|
Definition
| Use of survey data and math models to simulate test market results at a much lower cost |
|
|
Term
|
Definition
| A predictable statistical relationship between two variables. Must show they have some correlation to each other. |
|
|
Term
| Order of Questions on a Questionnaire |
|
Definition
| 1. Screeners, qualifying questions. 2. Warm-ups. 3. Transitions. 4. Difficult and complicated questions. 5. Classifing and demographic questions |
|
|
Term
|
Definition
| A written outline of topics to be covered during a focus group discussion |
|
|
Term
| Advantages of Depth interviews in place of Focus groups |
|
Definition
| they are much more expensive but can provide accurate information when scheduling or number of participants are problematic. |
|
|
Term
|
Definition
| Typically descriptive research that monitors respondents' actions wihtout direct interaction |
|
|
Term
|
Definition
| Research in which an interviewer interacts with respondents to obtain facts, opinions, and attitudes |
|
|
Term
|
Definition
| measure causality, in which the researcher changes one or more variables and observes the effect of the changes on another variable. |
|
|
Term
| Causal Research (Causation) |
|
Definition
| Research deisnged to determine whether a change in one variable likely caused an observed change in another. |
|
|
Term
| 3 things one must show to prove Causation |
|
Definition
| 1. Concomitant variation (correlation), 2. Appropriate time order of occurrence, 3. Elimination of other possible causal factors. |
|
|
Term
|
Definition
| Designs that offer little or no control over extraneous factors |
|
|
Term
|
Definition
| Research using an experimental group and a control group, to which test units are randomly assigned |
|
|
