click below
click below
Normal Size Small Size show me how
mgmt212-final
marketing research final notes BIG FILE
Question | Answer |
---|---|
the iceberg principle | the dangerous part of many marketing problems is neither visible to nor understood by marketing managers |
managerial goals | should be expressed in measurable terms |
situation analysis | informal gathering of background information to familiarise researchers or managers with the decision area, |
Symptom: declining market share. Identify the problems. | outdated product, new competition, shifting demographics (i.e. aging population and making retirement neighborhoods as an opportunity), inappropriate pricing |
symptom: decline in profits. Problems: | ineffective promotions, escalating distribution costs, improper channel structure |
symptom: inability to gain channel participation. Problems: | lack of product differentiation, misdirected promotions, inferior product image |
symptom: decline in company sales. Problems: | decline in industry sales (i.e. airline trend has been declining in recent years), increased competition |
unit of analysis | individuals, households, organisations, hotels etc. (in many studies, the family rather than the individual, is the appropriate measure) |
variable | anything that varies in value (for example, attitude towards airlines may be a variable ranging from positive to negative) |
categorical/classificatory | limited number of distinct values (i.e. gender, socio-economic status (SES), colour, size, etc) |
continuous | infinite number of values (i.e. sales, length, weight, age, etc.) |
dependent variable | Y - variable that is to be predicted or explained |
independent variable | X - variable that is expected to influence Y. can be manipulated by researcher, or be naturally occurring groups |
key variables to measure: Demographics | age, gender, race, income, religion, occupation, family size, geographic location |
key variables to measure: Psychographics | consumer activities, interests, opinions, attitude towards a particular issue (i.e. being 'green') |
key variables to measure: product usage | occasion (special use, gift), situation (climate, time of day, place), usage level (heavy, medium, or light) |
key variables to measure: brand preferences | level of brand loyalty, salient product attributes, product/brand awareness |
key variables to measure: decision process | size and frequency of purchase, propensity to purchase, risk of purchase (high, medium, low); product involvement (sponsorship) |
A hypothesis | unproven proposition or a possible solution to a problem |
research objective | the researcher's version of the marketing problem - explains the purpose of the research in MEASURABLE TERMS; and DEFINES STANDARDS for what the research should accomplish; and INFLUENCES DECISIONS about the research design |
research proposal | written statement of the research design that includes a statement explaining the purpose of the study and detailed outline of procedures associated with a particular methodology |
research proposal stages (one through five) | Problem definition, selection of basic research design, selection of sample, data gathering, data analysis and evaluation |
stage one of research proposal | problem definition: what is the purpose of the study, how much is already known, what is to be measured, can a hypothesis be formulated, etc? |
stage two of research proposal | selection of basic research design: what types of questions need to be answered, are descriptive or causal findings required, how quickly is the information needed, etc? |
stage three of research proposal | selection of sample: who or what is the source of data, is a probability sample necessary, how large a sample is necessary, how will the sample be selected, etc? |
stage four of research proposal | data gathering: who will gather the data, how long will data gathering take, how much supervision is needed, what operational procedures need to be followed, etc? |
stage five of research proposal | data analysis and evaluation: how will the data be categorised, what is the nature of the data, what questions need to be answered, etc? |
dummy tables | helps managers gain a better understanding of the actual outcome from a research proposal; representations of the actual tables that will be in the findings section of the final report |
secondary data | collected by persons or agencies for purposes other than solving the problem at hand |
secondary data benefits | low cost, less effort, less time, at times the only way to obtain data |
secondary data limitations | collected for some other purpose/objective, no control over data collection, may not be accurate (i.e. bias), may be oudated (not useful, may need to make assumptions (assuming a normal curve, etc) |
data sources | secondary because they offer solutions to problems which are secondary to (in addition to) their primary purpose for existing. (i.e. yellow pages and google maps) |
internal sources | internal records (e.g. accounting data, sales reports, and customer databases) |
external sources | published data sources (e.g. census data, publications from trade associations or governments, etc.); computer retrievable databases (e.g. online databases) |
Appraising secondary sources | why, how and when was the data collected? Who has collected the data? What data was collected? |
syndicated | managed by a group of individuals or organisations that are combined to promote some common interest |
syndicated sources | i.e. ACNielsen ScanTrack - because information users have common information needs and the cost of satisfying individual user's needs are sometimes prohibitive |
exploratory research laymen's terms | not quite sure what the problem is so you need to get some background information to determine the right research problem |
exploratory research in a nutshell | defining research problems, developing and/or pretesting questionnaires, generating and/or evaluating new product concepts |
orientation qualitative research methods | learning more about consumers (e.g. culture, needs, etc.) |
Clinical Research | gaining insight into topics that would be difficult to pursue using structured research methods (e.g. the real underlying causes of behaviour) |
Research goals/objectives: qualitative methods | discover/identification of new ideas, thoughts, feelings; initial insights on and understanding of ideas and objects |
research goals/objectives: quantitative methods | validation of facts, estimates, relationships, predictions |
type of research: qualitative methods | normally exploratory designs |
type of research: quantitative methods | descriptive and causal designs (running experiments - manipulating something) |
types of questions: qualitative methods | open-ended, semi-structured, unstructured, deep probing |
types of questions: quantitative methods | mostly structured |
time of execution: qualitative methods | relatively short time frames |
time of execution: quantitative methods | usually significantly longer time frames |
representativeness: qualitative methods | small samples, limited to the sampled respondents |
representativeness: quantitative methods | large samples, normally good representation of target populations |
type of analyses: qualitative methods | debriefing, subjective, content, interpretive, semiotic analyses |
type of analyses: quantitative methods | statistical, descriptive, causal predictions and relationships |
researcher skills: qualitative methods | interpersonal communications, observations, interpretive skills |
researcher skills: quantitative methods | scientific, statistical procedure, and translation skills; and some subjective interpretive skills |
generalisability of results: qualitative methods | very limited; only preliminary insights and understanding (wouldn't base big decisions on this alone) |
generalisability of results: quantitative methods | usually very good; inferences about facts, estimates of relationships |
exploratory research is conducted for three purposes: | diagnosing a situation, screening alternatives, discovering new ideas |
exploratory research is useful when: | the researcher has limited amount of experience or knowledge about a research issue |
exploratory research provides which type of data? | qualitative. Focusing on words and observations |
exploratory research - purpose one: | diagnosing a situation: helps set priorities for research, gather information on an unfamiliar topic, clarify the market research problem |
exploratory research - purpose two: | screening alternatives: used to determine the best alternatives when there are budget constraints; concept testing |
concept testing | purpose is to test a new, revised, or repositioned product or service |
exploratory research - purpose three: | discovering new ideas: used to generate ideas for new products, advertising copy, etc.; uncovering consumer needs (e.g. determine what problems consumers have with a product category) |
observational techniques - information about people can be observed through their: | physical actions, expressive behaviours, temporal behaviour patterns, spacial relationships and locations, physical objects |
observational techniques: physical actions | shopping trip patterns. i.e. if you see 3 furniture shops sitting next to each other and think well that's a bad idea think again - much better than being isolated |
observational techniques: expressive behaviours | facial expressions |
observational techniques: temporal behaviour patterns | time spent at a website |
observational techniques: spatial relationships and locations | crowding studies |
observational techniques: physical objects | products bought at a supermarket; i.e. beer and nappies sold together |
observational techniques: appropriate conditions for use | information condition, type-of-data condition, time-frame condition, setting condition |
observational techniques: information condition | if current behaviour patterns are important to the study |
observational techniques: type-of-data condition | when motivations, attitudes, feelings, etc. are unimportant |
observational techniques: time-frame condition | behaviours need to occur within a short time span |
observational techniques: setting condition | limited to settings where behaviour can be observed |
observational techniques: unique characteristics | directness of observation, subjects' awareness of being observed, structure of observation, type of observing mechanism |
observational techniques: directness of observation | can use either direct or indirect observation |
observational techniques: subjects' awareness of being observed | can use disguised or undisguised observation |
observational techniques: structure of observation | can use structured or unstructured techniques |
observational techniques: type of observing mechanism | can use human observers or mechanical devices |
Benefits of observational techniques | accuracy of actual behaviour, reduction of confounding factors, in-depth detailed behavioural data |
Limitations of observational techniques | difficulty of generalising results, inability to explain behaviours or events, complexity of setting and recording oh behaviours or events |
Focus Groups | Obtaining possible ideas or solutions to a marketing problem from a group of respondents via discussion |
Focus Group Composition | typically involve 6-12 participants; relatively homogeneous; three or four groups usually sufficient |
Focus Group Environmental Conditions | mood as relaxed and natural as possible; cameras/one-way mirrors used to allow observation by others who aren't in the room |
Focus Groups: the Moderator | helps people relax; develops rapport; promotes interaction among its members; listens to what people have to say; everyone gets a chance to speak |
Discussion Guide | A document prepared by the focus group moderator that contains remarks about the nature of the group and outlines the topics or questions to be addressed |
Advantages of Focus Groups | fast, inexpensive, and easy to execute, numerous topics can be discussed and many insights can be gained; synergy; snowballing; serendipity; security; spontaneity |
synergy | combined effort of the group will produce a wider range of information, insights, and ideas (especially beneficial when trying to think of new product ideas) |
snowballing | bandwagon effect where a comment from one individual triggers a chain of responses from others. Includes brainstorming |
serendipity | more often that some idea drops out of the blue. also greater opportunity to develop an idea to its full potential |
security | individual can find some comfort when others share similar feelings |
spontaneity | individual responses can be more spontaneous if they are not required to answer any given question (as opposed to yes/no question and answers) |
Shortcomings of Focus Groups | require sensitive and effective moderators that encourage group without being intrusive; since participants are screened to have similar backgrounds and experiences, they may not be representative of the entire market |
Projective Techniques | an indirect means of questioning that enables a respondent to project beliefs and feelings onto a third party, an inanimate object or a task situation |
Word Association tests (projective technique) | the subject is presented with a list of words, one at a time, and asked to respond with the first word that comes to his or her mind |
Sentence completion method (projective technique) | respondents are required to complete a number of partial sentences with the first word or phrase that comes to mind (i.e. people who drink beer are... ) This method is more open-ended rather than asking someone directly |
third-person technique and role playing (projective technique) | respondent is asked why a third person behaves in a certain way or what they think about a product. |
thematic apperception test TAT (projective technique) | the respondent is presented a series of pictures; then is asked to provide a description of or a story about the pictures |
cartoon tests (projective technique) | version of the TAT (thematic apperception test) where the respondent suggests dialogue for characters in a picture |
In-depth Interviews: nondirective | maximum freedom to respond (so long as discussion is related to area(s) of research interest); ask someone to open up and talk about whatever they want - can be problematic as they could easily go off tangent |
In-depth Interviews: semi-structured or focused individual | covers a specific list of topics or sub-areas (e.g. timing, exact wording, and time allocated to each question usually usually predetermined) |
In-depth Interviews: experience surveys | gathering opinions from knowledgeable people |
In-depth Interviews: Protocol Interviews | verbally expressing the decision-making process |
Advantages of Qualitative Methods | economically and timely data collection; richness of the data; accuracy of recording marketplace behaviours; preliminary insights into building models and scale measurements for more extensive research |
Disadvantages of Qualitative Methods | lack of generalisability; inability to distinguish small differences; lack of reliability of validity; difficulty finding well-trained investigators, interviews and observers |
Research Design | a framework or blueprint for conducting the marketing research project |
exploratory research | typically used to provide structure and insight into the research problem |
exploratory research example | using focus groups to determine key factors related to the use of a product |
conclusive research | tests specific hypotheses, examines specific relationships, makes predictions |
conclusive research: descriptive | used to describe something, usually market characteristics or functions |
descriptive research example | determining the average age of purchasers of your product |
conclusive research: causal | used to obtain evidence regarding cause-and-effect relationships; attempts to infer causal relationships between variables as opposed to describing variables |
causal research example | determining if increased advertising spending has led to an increase in sales |
situations where descriptive research should be used | describe the market size, buying power of consumers, availability of distributors; determine the proportion of total sales received by a company and its competitors; image studies which determine consumer perceptions of the firm and its products |
situations where descriptive research should be used | product usage studies, distribution studies, pricing studies, advertising studies |
major data collection methods | secondary research; survey research; experimental research |
survey research | systematic collection of information directly from respondents |
survey research objectives | attempts to identify characteristics of target markets; measure consumer attitudes and describe consumer purchasing patterns |
survey research advantages | easy to administer and record, accommodates large sample size so it's more generalisable, allows the use of advanced statistical analyses |
survey research disadvantages | can take a long time, problem with low-response rates, difficult to know whether respondents are being truthful |
Person-Administered surveys | in-home interviews, executive interviews, mall-intercept interviews, purchase-intercept interviews |
Telephone Administered surveys | can be conducted from a central location or from home |
self-administered surveys | direct-mail, mail panel (sent to those people who have agreed to participate), drop-off |
online surveys | fax, email, internet |
surveys: types of questions | structured, unstructured, undisguised, disguised |
surveys: timing | cross-sectional, longitudinal |
cross-sectional study | various segments of a population are sampled and data are collected at a single moment in time |
longitudinal study | respondents are surveyed at different times, thus allowing analysis of continuity and changes over time |
surveys: situational characteristics | budget, time frame, quality requirement (completeness, generalisability and precision) |
Surveys: task characteristics | difficulty of the task, stimuli needed to elicit response, amount of info needed from respondent, research topic sensitivity |
surveys: respondent characteristics | diversity, incidence rate, degree of participation (ability, willingness, knowledge) |
experimental research | the research manipulates one or more variables in such a way that its effect on one or more other variables can be measured |
functional relationship | an observable and measurable systematic change in one variable as another variable changes |
conditions for valid causal inferences | concomitant variation, time order of occurrence, absence of competing causal explanations |
independent variable | X; also called a predictor or treatment variable; its value is manipulated by the researcher; it is assumed to have a functional relationship with the dependent variable |
dependent variable | Y; also called a criterion variable; the measured outcome is derived from manipulating the independent variable(s) |
control variables | the variables a researcher controls so they do not effect the functional relationship between both the independent and dependent variables |
extraneous variables | variables that cannot be controlled; with randomisation, the effects of these variables will tend to average out |
validity | extent to which the conclusions drawn from an experiment are true |
internal validity | extent to which the research design accurately identifies causal relationships (i.e. rival explanations are ruled out) |
external validity | extent to which a causal relationship found in a study can be expected to be true for the entire population |
X | the EXPOSURE of an independent variable (treatment manipulation) to a group of test subjects |
O | the OBSERVATION (or measurement) of the dependent variable on the test subjects |
[R] | the RANDOM assignment of test subjects to separate treatment groups |
EG | the EXPERIMENTAL GROUP of test subjects |
CG | the CONTROL GROUP of test subjects (who are not exposed to the treatment manipulation) |
-> | a movement through time (normally left-to-right) |
(EG): X -> O1 | One-group Post-test: apply the experimental treatment to a subject/group and measure the results |
one-group post-test example | junk mail promotion - measure response from consumers |
(EG): O1 -> X1 -> O2 | One-group, Pretest-Post-test: improves control by adding a before measure |
One-group, Pretest-Post-test example | attitudes to smoking measured before, then advertising campaign administered, then attitudes measured again |
(EG): X -> O (CG): O1 | Static Group Comparison: improves control by adding a control group |
static group comparison example | junk mail promotion - measure response from consumers and compare with consumers who don't get promotion |
Pre-experimental designs | one-group post-test; one-group pretest-post-test; static group comparison |
true experimental designs | post-test-only control group; pretest-post-test control group |
post-test-only, control group | a popular and well practiced experimental design |
(EG): [R] X -> O1 (CG): [R] O1 | Post-test-only, control group: randomisation can "match" experimental and control groups, given a sufficient sample size |
(EG): [R] O1 X -> O2 (CG): [R] O1 O2 | pretest-post-test, control group |
laboratory experiments: validity? | high in internal validity, but low in external validity |
laboratory experiments | experiments where the treatment manipulation is introduced in an artificial or laboratory setting; respondents may not respond naturally |
Field experiments: validity? | high in external validity, but low in internal validity |
field experiments | experiment where the treatment manipulation is introduced in a completely natural setting (e.g. test market) |
test marketing | essentially a controlled field experiment that is conducted within a limited market area which aims to examine sales potential & evaluate variables within a products' marketing mix |
surrogate information error | variation between the information required to solve the problem and information sought by the researcher |
measurement error | variation between the information sought by the researcher and the information produced by the measurement process |
experimental error | variation between the actual impact of the independent variables and the impact that is found to be attributed to the independent variables |
population specification error | variation between the population required to provide the needed information and the population selected by the researcher |
frame error | variation between the population as defined by the researcher and the list of population members used by the researcher |
sampling error | variation between a representative sample and the sample obtained by using a probability sampling method |
selection error | variation between a representative sample and the sample obtained by using a non-probability sampling method |
non-response error | variation between the selected sample and the sample that actually participates in the study |
population | complete set of observations about which an investigator wishes to draw conclusions - is defined by the interest of the investigator, is defined in terms of observations rather than people |
sample | part of the population; study it in the hope that it will lead to meaningful conclusions about the target population; is defined in terms of observations rather than people |
statistic | a descriptive index (mean, proportion, percentage, etc.) of a sample |
parameter | a descriptive index (i.e. mean, proportion, percentage, etc.) of a population |
census | measurement of all members of the population |
central limit theorem | the sampling distribution of the mean derived from a simple random sample will be approximately normally distributed, provided the sample size is sufficiently large (n >= 30) |
sampling process (5 steps) | define population, determine sampling frame, select sampling method, determine sample size, select sample |
sampling process - step 1 | define population: isolate the characteristics of the observations in the population which are required to answer the research question |
sampling process - step 2 | determine sample frame: the list of all eligible sample units from which the sample will be drawn (e.g. telephone directories, electoral registers, company lists, club membership lists, etc) |
sampling process - step 3 | selection of sampling method: probability/non-probability, single unit/cluster, unstratified/stratified, equal/unequal probability, single stage/multistage |
sampling method: probability sample | one in which the sampling units are selected by chance and for which there is a known chance of each unit being selected (i.e. simple random, systematic, stratified) |
sampling method: non-probability sample | one in which chance selection procedures are not used (i.e. convenience, judgment, referral, quota, purposive) |
probability sample: simple random | each unit has an identical chance of selection, using blind draw or a table of random numbers |
probability sample: systematic | the sample is drawn by selecting a random starting point and selecting every xth element in succession (x is skip interval) |
probability sample: stratified | the target population is divided into mutually exclusive and collectively exhaustive sub-populations or strata - a random sample is taken from each strata |
mutually exclusive | every element in the population must be assigned to only one stratum |
collectively exhausted | no population element can be excluded |
non-probability sample: convenience | only criterion for selecting the sampling units is the convenience of the sampler |
non-probability sample: judgment | an attempt is made to draw a sample of the population using an educated guess - useful if broad population inferences are not required |
non-probability sample: referral | snowball - participants provide names of other potential sample units - characteristics will be similar to the person referring |
non-probability sample: quota | define the sample in such a way that the demographic characteristics of interest are in the same proportion as they are in the population - the sample elements are selected based on convenience or judgment |
non-probability sample: purposive | sample is chosen to achieve some objective, such as heavy users, frequent viewers, small population sub-samples |
selection of sampling method: single unit sample | each unit is selected separately (i.e. individuals) |
selection of sampling method: cluster sample | units are selected in groups (i.e. households) |
selection of sampling method: unequal unit probability sampling | if variation in expenditure is less for one group, reduce sample size of that group and reallocate share to other groups with higher expenditure variation |
sampling process - step 4 | sample size determination: arbitrary, conventional, cost basis, statistical analysis, confidence interval |
arbitrary sample size determination | rule of thumb (e.g. 5% of the population) |
conventional sample size determination | based on a standard (e.g. 8 in a focus group) |
cost basis sample size determination | determined by budget |
statistical analysis sample size determination | some techniques require a minimum sample size |
confidence interval sample size determination | statistically determined and most accurate method |
confidence interval - variability | the more variability (standard deviation), the larger the sample size required |
confidence interval - confidence | the higher the confidence required, the larger the sample size required |
confidence interval - precision (standard error) | the more precise the results required, the larger the sample size required |
sampling process - step 5 | selecting the sample: need to uphold the sampling method throughout the sampling process |
selecting the sample | if we start using a random sampling method, but we have a low response rate, we shouldn't then change to snowball sampling, we should re-sample the population using random sampling. |
sampling errors | difference between the observed values of a variable (i.e. sample mean) and long-run average of the observed values in repetitions of the measurement (i.e. population mean) |
sampling distribution | reflects the fact that the different possible samples that could be drawn under the sampling plan will produce different estimates of the population parameter |
non-sampling errors | reflect bias that occurs regardless of whether a sample or census was used; can't be estimated |
random errors | produce estimates that vary from the true value; sometimes estimates are above and sometimes below the true value |
non-random errors | most troublesome, tend to produce mistakes only in one direction, bias the sample value away from the population parameter |
week 6 measurement | s |