Short Answer - 150 Words - 4 Questions (150 word limit) Extended Response - 1 Question (500 words) - Research Design - Research Validity and Ethics Research Design Template MKTG 1002 → Week 1 & 2 Overview of the research process Question Notes What is marketing research? designing an approach to collect valid information to improve the understanding of a situation to make a decision or inform the understanding of a concept What is basic academic research? Expands the limit of knowledge and to learn more about a certain concept Not aimed at solving a particular problem Verify the acceptability of again theory Conducted when a decision must be made about a specific real-life problem Aimed to understand and answer questions about specific problems Undertaken to make decisions about particular courses of action or policies What is applied research? Academics cannot usually solve a specific problem without also doing targeted applied research. But applied research methodology is often similar to basic research methodology What is the value of marketing research? Fulfills the marketing manager’s need for knowledge of the market Effective marketing management requires research Eg. Club Med somehow figuring out to reposition itself as an attractive destination for Japanese tourists Marketing research reduces the uncertainty of marketing strategies and tactics When is marketing research needed? What are the stages in the research process? Time constraints Availability of data Nature of the decision value of research VS the cost Defining the problem Planing a research design Planning a sample Collecting the data Processing and analysing the data Drawing conclusions and preparing a report Research design is needed to specify method used to analyse needed information After problem is found apply three broad types of research for separate problems Exploratory research (Ambiguous problem) “Our sales are declining and we don't know why?” descriptive research (Partially defined problem) “What features do buyers prefer in our product?” causal research (Clearly defined problem) “Which of two advertising campaigns are more effective” What are the intended outcomes and methods for different research designs? How to form research design? Exploratory research What is descriptive research? Initial research conducted to clarify and define a problem, gain insights and discover new ideas Purpose is to: Progressively narrow the scope of the research topic Transform ambiguous problems into well-defined research objectives Expectation that subsequent research will be required to provide conclusive evidence Narrowing of the research scope happens: By investigating any existing studies on the subject By talking with knowledgeable individuals and experts By informally investigating the situation Exploratory research techniques Secondary Data Pilot studies Qualitative methods Focus groups Projective techniques Practical data collection In depth interviews Pilot studies Collection of data from actual research subjects to serve as a guide for a larger study Data collection methods are informal and findings may lack precision Focus group interview to obtain qualitative information Sharing of ideas and preferences of six to ten people in a grouP For example, the National Drugs campaign used focus groups to identify attitudes and motivations of youth towards the use of illicit drugs Purpose is to describe characteristics of a population Example: determining who purchases a product, portraying the size of the market, identifying competitors’ actions etc. Seeks to determine the answers to who, what, when, where and how questions Segmentation and target marketing Revealing the nature of consumer behavior Descriptive studies are based on some previous understanding of the nature of the research problem Note that this is distinct from exploratory research Accuracy is of paramount importance Surveys Most common method of descriptive research In this technique information is gathered from a sample of people using a questionnaire Research investigators may choose to contact respondents by telephone or mail, on the internet or in person Each survey method has advantages and disadvantages, and researchers need to decide on the appropriate method for the data collection Secondary data An example of descriptive research using secondary data includes a mathematical model to predict sales on the basis of past sales Generally, the quantitative analysis of secondary data is more sophisticated than that of exploratory studies Pros and cons of Secondary research Pros: Inexpensive and easily accessible Cons: Unknown accuracy + might not be relevant to problem Types of secondary data Fact finding Identification of consumer behaviour for a category Trend analysis Environmental scanning Model Building Specification of relationships between variables Data Mining Market based analysis Social media and sentiment analysis Customer discovery Observation methods Observation methods involve recording behavior without relying on reports from respondents Example: number of automobiles that pass by a proposed site for a petrol station How do you plan a sample? A sample is a subset of a larger population Sampling procedure uses a small number of items or a portion of the population to make a conclusion regarding the whole population Results of a good sample should have the same characteristics as the population as a whole Researcher determines who is to be sampled, how large a sample is needed and how sampling units will be selected Sampling Issues: Target population Sample size Sampling method Sampling techniques Probability Sampling Non Probability sampling How is data gathered for market research? Data may be collected by humans or recorded by machines Many research techniques involve various methods of data collection What are the two phases of data gathering? Two phases of data gathering: Pretesting: small scale study on a small sub sample to determine the appropriateness of the research design and minimize errors Main Study How is market research data processed and analysed? Editing Checking the data collection forms for omissions, legibility and consistency in classification Coding Developing rules for interpreting, categorizing, recording and transferring the data to the data storage media Analysis Application of reasoning to understand the data Analysis may involve summarising relevant findings, determining consistent patterns, statistical analysis etc. How are conclusions and final reports prepared? Researchers should look at the analysis of information collected and ask, ‘What does this mean to management?’ Consists of interpreting information and making conclusions for managerial decisions Research reports should effectively communicate the findings of the research What is the research program? The overall plan to conduct a series of marketing research projects Researchers may design specific research projects for each aspect of the marketing mix What is the process to defining a problem? Problem definition Ascertain the decision makers objectives Customer convenience, Customer happiness… Probe decision maker to uncover objectives Understand the background of the problem Situational analysis → Background info Literature review → Past research in area Pilot Studies (primary data) Isolate and identify the problem, not the symptoms Determine the unit of analysis Researchers must specify whether the investigation will collect data about individuals, households, organisations, etc Can be more than one level of analysis Determine the relevant variables A variable is anything that varies in value For example, attitudes toward airlines may be a variable ranging from positive to negative Continuous: e.g. personal height Ordinal: e.g. dislike, neutral, like Categorical: e.g. Male/female Dependent: variable that is to be predicted or explained Independent: variable that is expected to influence the dependent variable State the research questions and research objectives Written statement of research questions and objectives that clarify ambiguity about research hopes to accomplish You want to be specific so you can come up with a hypotheses How is a hypothesis created? EG Shoppers will walk into a restaurant to use toilet and not go to another floor for a toilet at westfield Having an unproven hypothesis allows researchers to be more clear about what they expect to find Tests whether we are specific enough Linking to the research design The statement of a marketing problem influencers the research objectives, which becomes the basis for the research design What is a research proposal? A written statement of the research design, including a statement explaining the purpose of the study Outlines a particular research methodology Outlines procedures associated with each stage of the research process Preparation of a research proposal forces the researcher to think critically about each stage of the research process A mechanism that allows managers to evaluate the details of the proposed research design and determine if alterations are necessary Also, is a pitch to a client. So, the info and results should be attractive to a practical decision-maker Proposal must communicate exactly what information will be obtained, where it will be obtained and how it will be obtained. For this reason, it must be explicit about sample selection, measurement, fieldwork and so on Project help PROBLEM DEFINITION What is the purpose of the study? How much is already known? Is additional background information necessary? What is to be measured? How? Can the data be made available? Should research be calculated? SELECTION OF BASIC RESEARCH DESIGN What types of questions need to be answered? Are descriptive or causal findings required? What is the source of the data? How quickly is the information needed? How should survey questions be worded? How should experimental manipulations be made? SELECTION OF SAMPLE Who or what is the source of the data? Can the target population be identified? Is a sample necessary? How accurate must the sample be? Is a probability sample necessary? Is a national sample necessary? How large a sample is necessary? How will the sample be selected? 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? DATA ANALYSIS AND EVALUATION Will standardized editing and coding procedures be used? How will the data be categorized? Will computer or hand tabulation be used? What is the nature of the data? What questions need to be answered? How many variables are to be investigated simultaneously? What are the criteria for evaluation of performance? TYPE OF REPORT Who will read the report? Are managerial recommendations requested? How many presentations are required? What will be the format of the written report? OVERALL EVALUATION How much will the study cost? Is the time frame acceptable? Is outside help needed? Will this research design attain the stated research objectives? When should the research begin? Question Practice “Red bull isa very successful energy drink and based on market share, it is the most popular energy drink in the world. Red bull has been the target of criticism concerning the possible health risks associated with the drink and in recent months they have also experienced a plateau in sales” Question Specify a marketing research question, at least two marketing research objectives and hypotheses for the following scenario: Week 3/4 Qualitative Research What is Qualitative research? Is qualitative research ‘fuzzy’ Qualitative research is not fuzzy Some of the most reliable marketing research results - often in relation to branding - are based on qualitative marketing research There are no quantitative measurements for brand identity What are the three purposes of qualitative research? Diagnosing a situation Screening alternatives Discovering new ideas What are the differences between quantitative and Qualitative research based on in-depth observation or interviews or some other type of interaction with the respondents The ‘data’ you collect are notes, narratives, photos, recordings, videos, or transcripts. Looking for themes, concepts, symbols, emotions, explanations and actions *Useful when a researcher has a limited amount of experience or knowledge about a research issue Common purpose Quantitative → Test hypothesis or specific research questions Qualitative → Discover ideas; used in exploratory research with general objects Approach Quantitative → Measure and test Qualitative → Observe and interpret Data collection approach Quantitative → Structure response categories provided Qualitative → Unstructured, free form Researcher independence Quantitative → Researcher uninvolved observer; results are objective Qualitative → Researcher is intimately involved,r results are subjective Samples Quantitative → Large samples to produce generalisable results Qualitative → Small samples - often in natural settings Most often used Quantitative → Descriptive and causal research designs Qualitative → Exploratory research designs What are the four major schools of thought influencing choice of technique? Phenomenology Ethnography Grounded theory Case studies Netnography Participatory Action research What is phenomenolo gy? People have their own reasons for what they do. Their actions have meaning to them. When people go to the shops and buy product A instead of product B there’s meaning to it. They do it for their own reasons. As a marker research we see them picking up product A or B but we don’t know why they did it. We have to figure out the reasoning; what brought them to decide to pick product a over b. This approach is about uncovering key themes or patterns in their reasoning. You should understand the person in a fairly deep way, their upbringing, their thinking, etc. Qualitative research tools include conversations, collages and thematic apperception/cartoon tests What is ethnography? Requires researcher to become immersed in the culture of interest and observe participants in that culture Qualitative research tools include focus group interviews, depth interviews, semi-structured interviews and observation Time consuming Hard to get a sample size that is efficient enough Tend to rely on a relatively small sample size Hawthorne effect – observation alters behavior; when workers know they’re being observed they behave correct to the books but once they’re no longer being watched they go back to how they usually act What is Grounded theory? Explain the case studies philosophy? In-depth investigation of a similar situation Careful study of order of events May require cooperation of party being studied Qualitative research tools include focus group interviews, depth interviews and observation What is netnography The compiling and analysis of data regarding social behaviour os individuals on the internet Unobstructed behaviour Basically ethnography but on the internet What is the participatory action framework theory? Belief that those who are most impacts by research should be the ones taking the lead in framing questions Legitimising knowledge generated by marginal communities What are common form of qualitative research? Focus groups Moderated discussion about brand so group of people can discuss their true feelings, anxieties and frustrations in their own words Group size: 6-12 Group composition: Homogenous Physical setting: Relaxed and informal Duration: 1-3 hours Moderators role is to outline general questions and progress the conversation Opening, transition, critical and closure questions Advantages Stimulates new ideas Foster understanding of why Allows client participation Elicit a range of responses Speed Disadvantages Reliability and generalisability Group think Projective techniques (Indirect approaches) Word association tests Sentence completion methods Thematic apperception test Respondent is presented a series of pictures and is asked to provide a story about pictures Cartoon tests Similar to thematic apperception test where respondent suggests dialogue for cartoon Practical data collection Researcher poses questions to get deeper explanations of something What is happening here, what are you doing, why did you do it ??? Qualitative research tools include depth interviews, conversations, semi-structured interviews, word association/sentence completion and observation Using text data from social networking sites, recorded conversations from call centers, emails…. In depth interviews Researcher asks many questions and probes for additional elaboration after answer “Can you give me an example of that? “Why do you say that?” Application Gain detailed information Discuss confidential topics Discussion of topics where strong norms exist Access to professional information Advantages Greater depth Ideas attributed to participant Free exchange of ideas Disadvantages Reliability and generalisabilitiy Susceptibility to interviewer influence Time & Cost What are some common data analysis tools? Nvivo Atlas Leximancer What are some limitations of qualitative research? Cannot take the place of conclusive, quantitative research Interpretation of findings typically judgmental Most techniques use small samples that may not be representative Surveys What are surveys A method of collecting primary data in which information is gathered by communicating with a representative sample of people What are Surveys used for? Identify characteristics of target markets Measure consumer attitudes Describe consumer purchasing patterns Types of survey questioning Verbally (person administered) Advantages Opportunity for feedback, Probing complex answers, Questioning Length, Reduction of non response bias, Use of props and visual aids, Participation rate Disadvantages Interviewer influence, lack of animosity, cost Written (Mail, online administered) Advantages Geographic flexibility, cost, respondent convenience, anonymity, sped Disadvantages Limited questions flexibility, non response, respondent monitoring Orally (Telephone administered) Advantages Cost speed interviewer supervision, geographic flexibility Disadvantages No non audio stimuli, Limited question suitability, survey length, public attitude Types of Survey Research Methods Structured Questions: Limits allowable answers Unstructured Questions: Do not restrict responses Temporal classification Cross sectional studies Collecting data from individuals once Longitudinal studies Collecting data from the same individuals over a period of time What should you keep in mind when thinking of using a survey? Respondents should be representative of your target population When asking hypothetical questions, surveys are not best option because customers wouldn't be as aware Advantages Quick Inexpensive Accurate Flexibility Ease of data analysis What are the two main types of error in survey research? Random error Systematic error (Bias) What is random error? Difference between findings based on the sample and true value of the population Sources Sampling approach Sample size Reduce sampling error by increasing sample size What is systematic error (Bias) When the results of a survey are skewed due to observation methods and environmental factors Administrative error Respondent error What is Administrative error? Some administrative matters can introduce bias Data processing error Sample selection error Interviewer error Interviewer cheating What is respondent error? When the surveyee does not respond When the result is skewed towards a different result Deliberate falsification & Unconscious misrepresentation Acquiescence Bias → blind agreement to research statements Extremity bias → Preference for extreme content Interviewer bias → Interviewer with agenda Social desirability Bias → Subconsciously conforming to social norms to “fit in” Auspices Bias → Indicating a response because of the organisation conducting th study Guide for selecting appropriate survey design What Is Pre-testing A trial run with a group of respondents to iron out fundamental problems in the instructions or design of questionnaire Avoids problems of having respondents misunderstand a particular question, skip a series of questions or misinterpret instructions What are some ethical issues in survey research? Research must protect the public from misrepresentation and exploitation Respondents have a right to refuse to participate or to answer questions Researchers need to protect the confidentiality of the participants Researchers need to record responses honestly What is causal research? Main goal is to identify cause and effect relationships among variables Planned and structured design Data collected via an experiment Independent (Or causal) variables manipulated Relatively controlled environment Measure the effect of independent variable (Manipulation) on dependent variable (outcome) Descriptive VS casual research Descriptive research determines degree of association between variables, not causal relationships Three conditions of causality X must always occur before Y The window didn't smash the soccer ball, the soccer ball smashed the window A repeated association between X and Y demonstrated (replicable) Just because it happened once doesn't mean it will happen again Extraneous variables are accounted for (controlled) Making sure there are no environmental influences How are experiments used in market research? Experiments Experiments try to define a cause and effect relationship between two variables X must always occur before Y The window didn't smash the soccer ball, the soccer ball smashed the window A repeated association between X and Y demonstrated (replicable) Just because it happened once doesn't mean it will happen again Extraneous variables are accounted for (controlled) Making sure there are no environmental influences Experimental design process Field vs laboratory experimental design Field → Conducted in a real setting + low control → High external validity Laboratory Experiments → Conducted in an artificial setting + High control → High Internal Validity Choice of independent and dependent variables Experimental treatments How independent variable will be manipulated Must be distinct ($1.79, $1.89, $1.99) Experimental group Group of participants exposed to experimental treatment Control Group Group of participants in control condition; Not exposed to experimental treatment Select and assign test units Test units: Subjects whose responses to experimental treatments are measured Can occur thorugh randomisaiton (random assignment) or matching Address issues of validity Internal validity Whether an experimental treatment was the sole cause of changes in the dependent variable EG whether the things being changes was the reason that was was being measured changed History effect → An external event that may influence dependent variable Maturation effect → Participants maturing and hence changing answer Testing effect → Respondents may remember what they previously answered Instrumentation effect → Bias introduced because research technique may change Mortality effect → people die… Selection effects → Experimental groups are not = (sample selection) Demand characteristics → Experiments which over inform the respondent and hence bias the experiment External validity Whether the findings of an experiment can be applied to other areas An application of field experiments → Test markets Provides opportunity to measure sales or profit potential for a new product or to test marketing plans under realistic conditions Test market Select and implement an experimental design Basic Experimental designs One shot case study Asking two separate test units specific research questions → Allowing for comparison Pre test post-test design Asking participants to answer questions before the experimental treatment and then after → Allowing for comparison Repeated measures Experimental design The same participant is exposed to all experimental treatments Eliminated problems associated with participant differences Demand characteristics they understand purpose of research Ask question, Show treatment, ask question, show treatment Factorial Experiment design Allows for the investigation of two or more independent variables Between subject design: Participant is exposed to a single experimental treatment (Manipulation) Address ethical issues Deception Right to be informed Debriefing Participants provided with all relevant information following the experiment Week 5/6 Question Notes What is observatio n? Observation is the systematic process of recording the behavioural patterns of people, objects and occurrences as they are witnessed What can be observed? Physical movements Verbal behaviour Expressive behaviour and psychological reactions Spatial tensions and locations Temporal patterns (how long it takes for car to go thru a drive thru) physical objects What is the nature of observatio n? Visible/Hidden Visible observation observers presence is known to the subject Hidden observation Subject is unaware that the observation is taking place Direct/Contrived observation Direct Observation Observation in natural environment Subject to observers bias Contrived Observation Artificial environment created to test a hypothesis Ways to observe behaviour Facial expressions Body language Eye activity Personal space Gestures Manners What can be observed Artifacts Inventories Content analysis Observation of communication materials eg social media What can be observed in mechanical observation? Television monitoring Scanner based research Camera surveillance Smart phones Website traffic Measuring physical reactions Eye tracking Pupilometers What is content analysis? What is mechanical observatio n? Psychogalvanometer Voice pitch analysis Neurological devices Content analysis is the systematic observation and quantitative description of content in communication Content or messages of advertisements, newspaper articles, television programs etc. E.g. frequency of appearance of women or minorities in mass media Whether advertisers use certain themes or appeals more than others Television monitoring: OzTAM estimates national television audiences Electronic boxes hooked up to television sets to capture program choices, length of viewing time and identity of viewer Monitoring website traffic E.g. Nielsen has its web monitoring software installed in 225 000 computers in homes and workplaces in 26 countries Scanner-based research Optical character recognition and bar code scanners can show a marketer week by week how a product is doing, even in a single shop, and track sales in response to local ads or promotions At-home scanning systems enable consumer panels to perform self-scans at home after product purchase What is the benefit of contrived observatio ns No skewed response Natural behaviour (Hawthorne effect about being knowingly watched) Unobtrusive When is observatio n scientific? Serves a formulated research purpose Is planned systematically Is recorded systematically and related to general propositions rather than simply reflecting a set of interesting curiosities What can be observed? What are some errors associated with direct observatio n? Not error-free because the observer may record events subjectively Observer bias: What is scientificall y contrived observatio n? Contrived observation: Investigator intervenes to create an artificial environment in order to test a hypothesis Contrived situations reduce the research time spent waiting and observing a situation For example, mystery shoppers to come into a store and pretend to be interested in a particular product or service; after leaving the store, the ‘shopper’ evaluates the salesperson’s performance What are some ethical issues in observatio n of humans? Hidden observations raise issues of the respondent’s right to privacy Contrived observation raises issues of deception If you do some intervention, should try to debrief the person after Why would the observatio n of physical objects be useful? Physical-trace evidence is a visible mark of some past event or occurrence Wear on library books to determine books most read Erosion traces on museum floor tiles to determine most popular exhibits Counting and recording physical inventories by means of retail or wholesale audits allows. Researchers to investigate brand sales on regional and national levels, market shares, seasonal purchasing patterns and so on What is content analysis? What is mechanical observatio n? What is the measureme nt process? Content analysis is the systematic observation and quantitative description of content in communication Content or messages of advertisements, newspaper articles, television programs etc. E.g. frequency of appearance of women or minorities in mass media Whether advertisers use certain themes or appeals more than others Television monitoring: OzTAM estimates national television audiences Electronic boxes hooked up to television sets to capture program choices, length of viewing time and identity of viewer Monitoring website traffic E.g. Nielsen has its web monitoring software installed in 225 000 computers in homes and workplaces in 26 countries Scanner-based research Optical character recognition and bar code scanners can show a marketer week by week how a product is doing, even in a single shop, and track sales in response to local ads or promotions At-home scanning systems enable consumer panels to perform self-scans at home after product purchase Determine what is to be measures Concrete concepts Age, income, household size Abstract concepts Attitude towards the brand, service quality, WOM Determine how it is to be measured Find an operational definition Gives meaning to a concept Specifies the activities or operations required to measure it Apply a rule of measurement Nominal Scale → Numbers or letters are assigned to objects as labels for classification EG “What colour car do you drive most often Ordinal Scale → Arranges objects in order of their magnitude EG “Rank your brand preference from 1 to 3 Interval Scale → Scale that arranges objects according to their magnitudes and distinguishes this ordered arrangement in units of equal intervals EG Rate your attitude towards nivea/Dove/Rexona from 1-7 Ratio Scale A scale that has absolute rather than relative qualities, and an absolute zero where there is an absence of a given attribute Equal distance on the scale represents equal values in the characteristic being measured EG i am ___ Years of age EG i spent ___ at woolworths Determine if the measure consists of several measures Complex concepts may require more than one question to capture all attributes Index (or composite) measures Multi item instruments (More than one question to measure a concept) for measuring a single concept with several attributes EG if you wanted to measure attitudes you would require separate questions for affective, cognitive and behavioural variables Asking different questions in order to measure the same concept provides a more accurate cumulative measure Computing scale variables Usine a scale to Combine questions into one concept EG Consumer attitudes towards a brand are split into four different questions Reverse coding Thinking about how questions are worded so that peoples answers align on the scale Also have one question is opposite so that you can track acquiescence bias Summative VS Average scale Summative → Adding the scores of the scales Average → Finding an average of the sum Determine the type of scale to be used Hypothetical constructs = Abstract concepts → Variable that is not directly observable but is measured through indirect indicators Likert Scale Semantic differential Scale Stapel scale Graphic rating scale Constant sum scale Evaluate the measure There are 3 major criteria for evaluating measurements: Reliability The degree to which measures are free from random error and therefore yield consistent results Has more to do with the scale When you repeat it will you get the same answer? Validity The ability of a scale to measure what was intended to be measured Did you measure what you wanted? Sensitivity The ability to accurately measure variability in stimuli or responses Increasing options or range of responses etc Practicality Shorter, while maintaining reliability, validity and sensitivity Advantage s and disadvanta ges of the scales How should a measureme nt be selected? No single best answer The choice of scale will depend on: The nature of the attitudinal object to be measured The manager’s problem definition Clarity and common sense What is validity The ability to measure what was intended to be measured For example, a hard-working student who understands statistics does poorly on a test that measures ability to do arithmetic and memorise formulas Did you measure what you wanted? What is reliability? The degree to which measures are free from random error and therefore yield consistent results Has more to do with the scale When you repeat it will you get the same answer? The sensitivity of a scale based on a single question or item can be increased, by adding additional questions or items In other words, because index measures allow for a greater range of possible scores, they are more sensitive than single-item scales Reliability vs Validity? What is sensitivity? Questionnaires - Designing Data collections Questions Notes - What are the objectives of Questionnaires Translate information needed into questions respondents can answer Minimise response errors What are the steps involved in the questionnaire design? Specify what information will be sought Determine the type of questionnaire and survey research method Determine the content of individual questions Determine the form of response to each question Determine the wording of each question Determine questions’ sequence Determine physical characteristics of the questionnaire Re-examine and revise steps 1-7 if necessary Pretest the questionnaire How to specify what information will be sought? Two basic criteria for questionnaire design: Relevance and Accuracy (Reliable and valid) List your research questions/Objectives to guide questionnaire design Omit issues that are not vital to the research Have a clear idea of the target population How to Determine the type of questionnaire and survey research method The type of survey used depends on the types of respondents and nature of the information Personal administered Lengthy, varies and complex questions Telephone intern administered iews: Short and simple questions with no visual stimuli Self administered (Mail and online surveys): Simple with detailed instructions provided How do researchers determine the content of individual questions? Is the question necessary? Are several questions needed instead of one? Do the respondents have the necessary information to respond to the question? Will respondents give the information freely and accurately? Dealing with sensitive questions Fixed alternative question Random placement (Normalising question by putting it among other normal questions) End of questionnaire How to determine the form of response to each question Open-ended response Advantages Exploratory research - range of responses unknown Free response - Lower response bias Disadvantages Not always appropriate for general population Interviewer bias Less effective in self administered questionnaires Cost Coding Closed ended questions Advantages Quick/Easy Reduced interviewer bias Coding Participation cooperation Disadvantages Answer bias What to avoid Complexity - Simple, conversational language Leading or loaded questions How to determine the wording of each question? Ambiguous wording What to avoid Complexity - Simple, conversational language Leading or loaded questions Ambiguous wording Generalizations or estimates How to determine the question sequence? Double barrelled items Memory Questions regarding past events place demands on memory Opening Questions Interesting non threatening Screening question Type of information Critical information - linked to research objectives Classification information (eg demographics) Funnel technique Asking general questions before specific questions in order to obtain unbiased questions EG Asking what they prioritise the most (Price, Sustainability or quality) before asking how important quality is for respondents Branch Question (filter question) A filter question used to determine which version of a second question will be asked How to Determine the physical characteristics of the questionnaire How to pretest the questionnaire? Traditional questionnaires Layout should be neat, attractive and interviewer instructions easy to follow (e.g. decent margins, white space to separate blocks of print). Internet questionnaires Make it clean and simple Software programs facilitate questionnaire design Self administered questions Clear instructions for respondent Person administered Questionnaires Clear instructions for field worker to manage respondent participation and maintain reliability and validity Pre test questionnaire on a small sample of respondents to identify potential problems Pilot tests would also be carried out using administration methods Sampling, sampling design and sample size Questions Notes What is a confounding variable? A confounding variable is an outside influence that changes the effect of a dependent and independent variable EG → An experiment shows that ice cream sales increase as murders increase. A confounding variable would be the weather because as the temp increases, ice cream sales increase and then murders What is sampling used for? Researchers often use samples to infer different characteristics of the population without contacting or surveying every member of the population What is a population element? An individual member of a population Why is a sample used? Sampling is often more beneficial that a census for: Pragmatic reasons, such as budget and time constraints Accurate and reliable results What are the stages of a sample? Define the target population Select a sampling frame Determine if a probability or nonprobability sampling method will be chosen Plan procedure for selecting sampling units Determine sample size Select actual sampling units Conduct fieldwork What is the sampling frame? Sampling frame: a list of elements (e.g. a membership list, a student email list) from which a sample may be drawn What are random sampling and non samping errors? Random sampling error The difference between a sample result and the result of a census conducted using identical procedures Non-sampling (systematic) errors Result from some imperfect aspect of the research design, such as mistakes in sample selection, sampling frame error or nonresponses Sampling frame error What are all the errors associated with sampling? Random sampling error Non response error What is the difference between probability and nonprobability sampling? Probability sampling: A sampling technique in which every member of the population has a known, non-zero probability of selection Nonprobability sampling: A sampling technique in which units of the sample are selected on the basis of personal judgement or convenience What are the various probability sampling methods? What is simple random sampling? A sampling procedure (e.g. drawing names from a hat) that assures each element in the population of an equal chance of being included in the sample What is Systematic sampling? A sampling procedure in which a starting point is selected by a random process and then every nth number on the list is selected What is clustered sampling? An economically efficient sampling technique in which the primary sampling unit is not the individual element in the population but a large cluster of elements Clusters are selected randomly What is stratified sampling? A sampling procedure in which simple random subsamples that are more or less equal on some characteristic are drawn from within each stratum of the population Simple random sampling Systematic sampling Stratified sampling Simple random sampling What are the types of non probability sampling? What is convenience sampling? The sampling procedure of obtaining those people or units that are most conveniently available, e.g. a lecturer who uses students for a study What is judgement sampling? A nonprobability sampling technique in which an experienced individual selects the sample based on personal judgement about some appropriate characteristic of the sample member What is quota sampling? A nonprobability sampling procedure that ensures various subgroups of a population will be represented to the extent that the investigator desires Introduces bias because quota samples tend to include people who are easily found and willing to be interviewed What is snowball sampling? A sampling procedure in which initial respondents are selected by probability methods and additional respondents are obtained from information provided by the initial respondents Convenience sampling Judgement sampling Quota sampling Snowball sampling What are the factors in determining sample size? The variance or heterogeneity of the population Only a small sample is required if the population is homogenous The magnitude of acceptable error Higher precision requires a larger sample The confidence level (e.g. 90%, 95% or 99% CL) Higher confidence requires a larger sample Vegan product extensions make brands look environmentally conscious Vegans care more about the environment than non vegans Sustainable packaging influences brand sentiment People who are health conscious have are more involved with product purchase Now that we know that vegans care more about the environment, does that mean if we create a vegan product line, vegans will pay more + non vegans will see it as an environmental brand? Now that we know that vegans are more likely to purchase vegan chocolate, they are willing to pay more, and a vegan product line will increase perceptions of environmental consciousness, which packaging most influences purchase intention and which packaging promotion enhances brand loyalty. 1. 2. Vegans will pay more for a vegan claim 3. Non vegans have a positive attitude towards a brand if it has an environmentally conscious product line 4. Vegan claim increases brand sentiment 5. Vegan benefits claim will maximize purchase intention for vegans but less for non vegans 6. Vegan benefits claims will maximize brand sentiment across all diets of consumers
