Study Guide Exam 2
Study Guide Exam 2 MKT 319
Popular in Marketing Research
verified elite notetaker
Popular in Marketing
This 10 page Study Guide was uploaded by Danielle Lynch on Wednesday November 4, 2015. The Study Guide belongs to MKT 319 at Michigan State University taught by R. Spreng in Summer 2015. Since its upload, it has received 220 views. For similar materials see Marketing Research in Marketing at Michigan State University.
Reviews for Study Guide Exam 2
Can you just teach this course please? lol :)
-Margie Swaniawski I
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 11/04/15
MKT 319 Exam 2 Study Guide Textbook Chapter 8 Causality: When the occurrence of X increases the probability of the occurrence of Y Conditions for causality 1. Concomitant variation: A condition for inferring causality that requires that a cause, X, and an effect, Y occur together or vary together as predicted by the h ypothesis under consideration 2. Time Order of Occurrence of Variables: For one variable to cause another, it must precede or occur simultaneously with the effect; it cannot occur afterwards 3. Absence of Other Possible Causal Factors: The presence of additional or extraneous variables that impact the effect variable must be controlled in order to draw causal inferences Independent variables: The researcher manipulates variables and the effects are measured and compared (advertising) Dependent variables : The variables that measure the effect of the independent variables on the test units (sales of products) Extraneous variables • History: Specific events that are external to the experiment but that occur at the same time as the experiment – longer time between observations, the greater the possibility • Maturation: Attributable to changes in the test units themselves that occurs with the passage of time – people aging example • Testing Effects: Post treatment attitudes might be influenced more by pre treatment attitudes than by the treatment itself • Instrumentation: Involving changes in the measuring instrument or in the observers or scores themselves • Statistical Regression: Occurs when test units with extreme scores move closer to the average score during the course of the experiment • Selection bias: The improper assignment of test units to treatment conditions • Mortality: Attributable to the loss of test units while the experiment is in progress. Internal validity: A measure of accuracy of an experiment. It measures if the manipulation of the independent variables, or treatments, actually caused the effects on the dependent variables – control extraneous variables External validity: A determination of whether the cause -effect relationships found in the experiment can be generalized – control extraneous variables, lab settings not externally valid Experimental designs • Pre-experimental designs: Do not control for extraneous factors by randomization o One-shot case study: A single group of test units is exposed to a treatmen t X, and then a single measurement on the dependent variable is taken ▯ X O1 ▯ Self-selected ▯ Nonrandom sampling ▯ Exploratory o One-group pretest posttest: Test units measured twice, once before and once after the treatment ▯ O1 X O2 ▯ Lack control group/randomization • True experimental designs: Researcher can randomly assign test units to experimental and control groups and also randomly assign treatments to experimental groups o Pretest posttest control group: Experimental group exposed to the treatment but the control group is not. Pretest and posttest measures are taken on both groups. Test units are randomly assigned ▯ EG: R O1 X O2 ▯ CG: R O3 O4 ▯ TE = (O2-O1) - (O4-O3) ▯ Interactive testing effects: Prior measurement affects the test unit’s response to the independent variable o Posttest only control group: Experimental group is exposed to the treatment but the control group is not and no pretest measure is taken. Posttest measures are taken on both groups. Test units are randomly assigned ▯ EG: R X O1 ▯ CG: R O2 ▯ TE = O1-O2 ▯ Most popular experimental design ▯ Mortality, selection bias • Quasi-experimental designs: Apply part of the procedures of true experimentation, while lacking full experimental control Where they are unable to randomize or control the scheduling of experimental treatments but can control when and whom o Time Series: Periodic measurements on the dependent variable for a group of test units. Then, the treatment is administered by the researcher or occurs naturally. After the treatment, periodic measurements are continue d in order to determine the treatment effect ▯ O1…O5 X O6…O10 ▯ Testing effect ▯ History not controlled ▯ Good for natural settings Demand artifacts: Responses given because the respondents attempt to guess the purpose of the experiment and respond accordingly • Test market: An application of a controlled experiment done in limited but carefully selected, tests markets. It involves replicating the planned national marketing program for a product in the test markets. o Representativeness is the most important o Risk revealing strategies Chapter 9 Measurement Scaling: The generation of the continuum upon which measured ob jects are located Scale characteristics • Description: The unique labels or descriptors that are used to designate each value of the scale. All scales possess description. • Order: The relative sizes or positions of the descriptors; denoted by descriptors such as greater than, less than, and equal to • Distance: The absolute differences between the scale descriptors are known and can be expressed in units • Origin: A unique or fixed beginning or true zero point of a scale Primary scales of measurement • Nominal: Uses numbers as labels or tags for identifying and classifying objects o One-to-one correspondence between the numbers and the objects o Mutually exclusiv e: No overlap between classes; every object being measured falls into only one class o The objects in each class are viewed as equivalent in terms of the characteristics o Collectively exhaustive: All the objects fall into one of the classes o Percentages, mode • Ordinal: A ranking scale in which numbers are assigned to objects to indicate the relative extent to which some characteristic is possessed. Thus, it is possible to determine whether an object has more or less of a characteristic than some other object o Order differences, not magnitude o Percentile, median o Quality, tournament team ranks, education levels • Interval: A scale in which the numbers are used to rank objects such that numerically equal distances on the scale represent equal distances in the characteri stic being measured o Mean, standard deviation o Temperature • Ratio: This is the highest level of measurement. It allows the researcher to identify or classify objects, rank-order the objects, and compare intervals or differences. It also is meaningful to compu te ratios or scale values. o Geometric mean, all o Height, weight, income Comparative scales • Paired comparison: A respondent is presented with two objects at a time and asked to select one object in the pair according to some criterion o Sensory o <5 brands o Order might bias results o Little resemblance to market • Rank order: Respondents are presented with several objects simultaneously and asked to order or rank them according to some criterion o Rank brands, attributes o Closer to resembling shopping environment o Forces respondent to discriminate o Less time than paired o Easily understood, results easy to communicate • Constant Sum: Respondents are required to allocate a constant sum of units, such as points, dollars, chits, stickers, or chips among a set of stimulus object s with respect to some criterion o Has an absolute zero – sometimes considered metric ▯ Not Generalizable so ordinal o Fine discrimination o Doesn’t require too much time o Respondents can allocate more or fewer units than those specified Chapter 10 Non-comparative scales: Monadic scale because only one object is evaluated at a time. An object is not compared to another • Continuous rating scale : Allows the respondent to place a mark at any point along a line running between two points rather than selecting from among a set of predetermined response categories o Easy to construct o Scoring difficult and unreliable unless on a computer screen • Likert scale: “A measurement scale with five response categories ranging from “strongly disagree” to “strongly agree,” which req uires the respondents to indicate a degree of agreement or disagreement with each of a series of statements related to the stimulus object o Advantages ▯ Easy to construct/administer ▯ Easy for respondent to understand ▯ Mail, telephone, personal, electronic o Disadvantages ▯ Takes longer to complete than other itemized rating scales ▯ Difficult to interpret statements • Semantic differential : A 7-point rating scale with end points associated with bipolar labels that have semantic meaning o -3 to +3 or 1 to 7 o Analyzed using profile analysis: Means or median values for each item are calculated, plotted, and statistically analyzed – differences and similarities o Overall comparison, summed like Likert o Advantages ▯ Versatile – compare brand, product, and company images, develop advertising and promotion, and develop products o Disadvantages ▯ Difficulty determining the appropriate bipolar adjectives Non-comparative itemized rating scale decisions • Number of scale categories : o Sensitivity: The ability to detect subtle differences in the attitude or the characteristic being measured o Sensitivity increases with the number of categories o Constraints ▯ Respondents can only process so much information ▯ Space o No fewer than 5, no greater than 9 • Balanced vs. unbalanced scales o Balanced scale: An equal number of favorable and unfavorable categories o Should be balanced unless skewed predictable • Odd vs. even number of categories o If a neutral or indifferent scale response is possible for at least some of the respondents, an odd number of categories should b e used • Forced vs. unforced rating scales o Forced rating scale: A rating scale that forces the respondents to express an opinion because a “no opinion” option is not provided o In situations where the respondents are expected to have no opinion the accuracy of data may be improved by a nonforced scale • Verbal descriptions : o An argument can be made for labeling all or many scale categories. The category descriptions should be located as close to the response categories as possible Validity: The extent to which i n observed scale scores reflect true differences in what is being measured, rather than systematic or random error Reliability: The extent to which a scale produces consistent results if repeated measurements are made on the characteristic *** If perfectly valid, perfectly reliable Reliability is necessary but not sufficient for validity Perfectly reliable, might or might not be valid because systematic error might still be present Chapter 11 Questionnaire: A formalized set of questions for o btaining information from respondents • Translate the researcher’s information needs into a set of specific questions that respondents are willing and able to answer • Minimize demands on respondents • Minimize response error Double-barreled question: Two or more questions are combined into one Confusing to respondents and result in ambiguous responses Inability to answer • Respondent informed? o Filter questions: Initial questions in a questionnaire that screen potential respondents to ensure they meet the require ments of the sample o Don’t know should be added if it’s a predicted response • Respondent remember? o Consumers dramatically overestimate usage o People remember what’s personally relevant, unusual, frequent o Aided or unaided – aided may bias results • Respondent able to articulate? o Visual aids, and verbal descriptions help Unwillingness to answer • Effort/Context • Legitimate purpose • Getting sensitive information (methods to increase willingness to answer) o Ask at the end because rapport is built Unstructured questions: Open-ended questions that respondents answer in their own words Structured questions: Prespecify the set of response alternatives and the response format. Could be multiple choice, dichotomous, or scale • Multiple choice o Number of alternatives o Order position bias: The respondents’ tendency to check an alternative merely because it preoccupies a certain position in a list – beginning and somewhat end paid attention to o Easier to analyze and interview bias reduced o Difficult to develop effective questions, when other is checked a lot that alternative list might be flawed. The list of options introduces bias o Should be mutually exclusive and collectively exhaustive • Dichotomous: Only two response alternatives: yes, no, agree or disagree etc • Scales: o Ch 9 and 10 o Should evaluate for reliability, validity, generalizability Branching questions : Used to guide respondents or interviewers through a survey by directing them to different spots on the questionnaire depending on the answers given Pretesting: Testing of the questionnaire on a small sample of respondents for the purpose of improving the questionnaire by identifying and eliminating potential problems before using it in the actual survey o Personal interviews so reactions and attitudes observed o Similar environment as actual o Final step: Coding and analyzed o Small: 15-30 respondents Chapter 12 Element: Objects that possess the information the researcher seeks and about which the researcher will make inferences Population: The total of all the elements that share some common set of characteristics Census: A complete enumeration of the elements of a population or study objects • Budget: Large • Time available: Long • Population Size: Small • Variance in characteristic: Large • Cost of sampling error: High • Cost of nonsampling errors: Low • Nature of measurement: Nondestructive • Attention to individual cases: No Sample: A subgroup of the population • Budget: Small • Time available: Short • Population Size: Large • Variance in characteristic: Small • Cost of sampling error: Low • Cost of nonsampling errors: High • Nature of measurement: Destructive • Attention to individual cases: Yes Target population: The collection of elements or objects that possess the information the researcher seeks and about which the researcher will make infe rences Sampling unit: The basic unit containing the elements of the population to be sampled Sampling frame: A representation of the elements of the target population. It consists of a list or set of directions for identifying the target population Non-probability sampling: Relies on the personal judgment of the researcher, rather than chance, in selecting sample elements 1. Exploratory 2. Nonsampling errors larger 3. Homogeneous variability (low) 4. Unfavorable statistical considerations 5. Favorable time and cost • Convenience: Obtain a sample of convenient elements. The selection of sample units is left primarily to the interviewer. o Inexpensive, fast o Selection bias – not Generalizable o Exploratory o Focus groups, pretesting questionnaires, pilot studies • Judgmental: The population elements are purposively selected based on the judgment of the researcher o Low cost, convenient, quick o Population not defined explicitly, subjective o When broad generalizations are not required • Quota o A two-stage restricted judgmental sampling. T he first stage consists of developing control categories or quotas of population elements. In the second stage sample elements are selected based on convenience or judgment ▯ Relevant characteristics may be overlooked ▯ Doesn’t permit assessment of sampling er ror ▯ Selection bias • Snowball: An initial group of respondents is selected randomly. Subsequent respondents are selected based on the referrals or information provided by the initial respondents. This process may be carried out in waves by obtaining referrals from referrals. o Begins with a probability sample, results in a nonprobability sample o Increases the likelihood of locating the desired characteristic in the population Probability sampling : A sampling procedure in which each element of the popula tion has fixed probabilistic change of being selected for the sample 1. Conclusive 2. Sampling errors larger 3. Heterogeneous variability (high) 4. Favorable statistical considerations 5. Unfavorable time and cost • Simple random sampling : Each element in the population h as a known and equal probability of selection. Every element is selected independently of every other element, and the sample is drawn by a random procedure from a sampling frame • Systematic sampling : Sample is chosen by selecting a random starting point an d then picking every ith element in succession from the sampling frame o Sampling interval o Sampling frames in a cyclical pattern tend to be less representative when systematic sampling is used o Less costly and easier than SRS because random selection is done only once o Consumer mail, telephone, mall -intercept and Internet • Stratified sampling : Two-step sampling process, producing a probability rather than a convenience or judgment sample o Strata: Every population element should be assigned to one and only one stratum, no population elements should be omitted o Elements are randomly selected from each stratum ▯ All of the subpopulations (strata) are selected for sampling. ▯ Within a stratum, elements should be homogeneous with clear differences (heterogeneity) between the strata. ▯ A complete sampling frame for the entire stratified subpopulations should be drawn. ▯ Objective is to Increase precision without increasing cost ▯ The number of strata usually varies between two and six. Beyond six strata, any gain in precision is more than offset by the increased cost • Sampling variation reduced, sampling costs reduced • Demographic, type of customer, size of firm, or type of industry • Cluster sampling: A two-step probability sampling technique. First, the target population is divided into mutually exclusive and collectively exhaustive subpopulations called clusters. Then, a random sample of clusters is selected based on probability sampling technique, such as simple random sampling. For each selected cluster, either all the elements are included in the sample or a sample of elements is drawn probabilitistically o Area sampling: A common form of cluster sampling in which the clusters consist of geographic areas, such as counties, housing tracts, blocks, and so forth ▯ Only a sample of the s ubpopulations (clusters) is selected for sampling ▯ Within a cluster, elements should be different (heterogeneous) whereas homogeneity or similarity is maintained between clusters ▯ A sampling frame is needed only for the clusters selected for the sample. ▯ Increases sample efficiency by decreasing cost ▯ Easy to implement ▯ Difficult to compute and interpret results Chapter 13 Parameter: A summary description of a fixed characteristic or measure of the target population Statistic: A summary description of a characteristic or measure of the sample that is used as an estimate of the population parameter Confidence interval approach : The range into which the true population parameter will fall, assuming a given level of confidence Sample size determination: Me ans (given the formula, be able to calculate the sample size) Sample size determination: Proportions (given the formula, be able to calculate the sample size) Response rate calculation : Number of completed interviews/Number of eligible respondents in the sample Weighting Lecture Chapter 8 Cross tabs Correlation vs. causality Chapter 11 Randomized response method Honesty detectors Gamification Chapter 12 and 13 Sample size determination: Means Sample size determination: Proportions SPSS Introduction SPSS basics covered in c lass Qualtrics Introduction to Qualtrics
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'