Marketing Research Notes PDF

Presentation 2 - Julia Just Presentation 3&3.5 - Oliwia Sokołowska Presentation 4 - Patrycja Grzesiak Presentation 5 - Ania Czernik Presentation 6 - Julia Sotel Introduction to Conducting Marketing Research Definition and Roots of Marketing Research ​ General Definition of Research:​ Rese...

Presentation 2 - Julia Just Presentation 3&3.5 - Oliwia Sokołowska Presentation 4 - Patrycja Grzesiak Presentation 5 - Ania Czernik Presentation 6 - Julia Sotel Introduction to Conducting Marketing Research Definition and Roots of Marketing Research ​ General Definition of Research:​ Research is the process of gathering data, information, and facts to advance knowledge (Martyn Shuttleworth). ​ Marketing Research Definition:​ Marketing research is defined by the American Marketing Association (AMA) as:​ "The process of planning, collecting, analyzing, and interpreting data relevant to a marketing decision." Changing Meaning of Marketing Research 1.​ 1990s:​ Surveys and Quantitative (numeric) Data 2.​ 2000s:​ Internet Research, e.g. online surveys and web analytics. 3.​ 2010s:​ Real-Time Big Data Research, emphasis on the systematic use of customer big data to adjust more quickly to tendencies 4.​ 2020s:​ Channel Integration and Customer Co-creation, e.g. emphasis on analyzing customer journey through various channels and consumer touchpoints and using customer data to co-create offer more effectively with consumers, e.g. in IKEA. Marketing Information System (MIS) Definition ​ Marketing research is a key element within the total marketing information system. ​ According to AMA Marketing Information System (MIS) is a multi-resource system for collecting, analyzing, storing, and disseminating marketing data to support marketing decision-making. Components of a Marketing Information System (MIS) 1.​ Internal Records: ○​ Digitalized ○​ Printed ○​ Sales ○​ Claims​ ​ 2.​ Management and Personal Knowledge: ○​ Pre-understanding ○​ Unwritten ○​ Attitudes ○​ Motives  3.​ Marketing Research: ○​ Desk research ○​ Field research Tendencies in the Use of MIS 1.​ Trend 1: Increased Use of Big Data​ Example:Amazon and Allegro use big data analytics regarding millions of consumers to provide recommendations. 2.​ Trend 2: Integration of AI and Machine Learning​ Example: Netflix employs machine learning algorithms to analyze viewing patterns and recommend customized movies, Allegro provides AI-based summaries to customer opinions 3.​ Trend 3: Real-Time Analytics​ Example: Coca-Cola uses social media real-time analytics to adjust quickly their communication campaigns. 4.​ Trend 4: Enhanced Data Privacy and Ethical Responsibility​ Example: Apple introduced „App Tracking Transparency”, which empowers users to choose more easily and effectively whether to share their data with advertisers. EXAMPLE: Marketing Information System in a Retail Clothing Store Data Collection ​ Point of Sale (POS) Systems:​ The store uses POS systems to capture transaction data when customers purchase items. This includes information like what items are sold, time of sale, payment method, and customer demographics (if loyalty cards are used). ​ Online Analytics:​ If the store has an e-commerce platform, it uses web analytics tools (like Google Analytics) to track customer behavior online. This includes page views, click-through rates, and abandoned carts. Data Integration ​ The store integrates data from various sources, including POS transactions, e-commerce sales, customer feedback from surveys, and social media interactions. ​ This centralized data hub helps create a comprehensive view of customer behavior and preferences.  Data Analysis ​ Customer Segmentation:​ Using analytical tools, the store segments its customers based on purchasing behavior, demographics, and preferences. For example, they might identify a segment of young adults who are particularly interested in sustainable fashion. ​ Trend Analysis:​ The store examines sales data to identify trends over time. Exemplary Trends: ​ Sustainable fashion ​ Second-hand and vintage shopping ​ Subscription and rental services ​ Inclusivity and diverse representation Decision-Making ​ Marketing Communication:​ Let us assume that consumers are increasingly concerned about environmental impacts (trend). As a result, brands like Patagonia or Everlane promote their products with the aspect of transparency in their sourcing and production processes. ​ Inventory Management:​ The insights also inform inventory decisions, ensuring that items getting more popular are well-stocked while phasing out less popular products Secondary data research Data type ​ Hard data: verifiable facts, from reliable sources, measurable, factual and indisputable ​ Soft data: qualitative information, rating, survey or poll, later it is quantified ​ Big data: large volume of data Market Research Primary Market Research Secondary Market Research Conducted by you or the hired research firm Conducted by someone else  Online survey, focus groups Internet, Census data Specific to your needs Cost effective, quick Three types of data costs → speed of delivery ← Tertiary information Secondary information Primary information ​ summary ​ reference ​ original record ​ data classification ​ complete record ​ comprehensive ​ browsing ​ low costs, lower ​ original sources ​ compactness accuracy, time ​ high costs, time ​ quick response consuming approach consuming ​ subjectivity ​ example: scientific ​ example: own survey ​ example: textbooks papers and public results data Secondary Data Classification of Secondary Data ​ Internal ○​ Ready to use ○​ Requires further processing ​ External ○​ Published materials ○​ Computerized databases ○​ Syndicated services Benefits and limitations Benefits Limitations ​ low cost ​ no control over data collection ​ less time taken ​ not very accurate, could be outdated ​ some information can be obtained ​ you are not the owner of the only from secondary data information ​ much data available internally (MIS) Process of Marketing Research 1.​ Marketing problem 2.​ Research Design  3.​ Data Collecting 4.​ Data Editing and Analysis 5.​ Report and Presentation Research design Guides the collection and analysis of data in relation to given marketing problem Consists of: ​ Research questions ​ Data sources ​ Data gathering methods ​ In case of primary data collection: ○​ Sampling ○​ Research instrument Plagiarism Important aspect of using secondary data. The unacknowledged use or appropriation of another person’s words or ideas. When you borrow words or ideas from sources to support your argument or research you must give proper credit. Summary (Chat GPT) Data Typology ​ Primary Data: Collected first hand for specific needs; examples include surveys and focus groups. ​ Secondary Data: Gathered by others; examples include census data and market research reports. Data Types ​ Hard Data: Verifiable facts from reliable sources, measurable and indisputable. ​ Soft Data: Qualitative information (e.g., ratings, surveys) later quantified. ​ Big Data: Large, structured or unstructured datasets used for actionable insights. Market Research ​ Primary Research: Conducted by the organization; specific and tailored, but costly and time-consuming. ​ Secondary Research: Conducted by external entities; cost-effective and quick but may lack specificity or control. Three Types of Data 1.​ Tertiary Information: Summaries or overviews (e.g., textbooks); compact but lacks detail.  2.​ Secondary Information: References or existing records (e.g., scientific papers); lower cost but less accurate. 3.​ Primary Information: Original data (e.g., survey results); highly accurate but expensive and time-intensive. Classification of Secondary Data ​ Internal: Already available within an organization, requiring minimal processing. ​ External: Sourced externally, such as published materials, databases, or syndicated services. Advantages and Limitations of Secondary Data ​ Benefits: Low cost, quick access, longitudinal analysis, and wide availability. ​ Limitations: Lack of control over accuracy, outdated information, and public accessibility. Process of Marketing Research 1.​ Define the marketing problem. 2.​ Design the research framework. 3.​ Collect data (primary or secondary). 4.​ Edit and analyze data. 5.​ Present findings. Research Design Components ​ Research questions. ​ Data sources and gathering methods. ​ Sampling and instruments for primary data. Plagiarism and Proper Citing​ Plagiarism involves using another's words or ideas without acknowledgment and is a serious offense. Proper citation (e.g., APA format) is essential whenever summarizing, paraphrasing, or quoting. Type of research method ​ Qualitative research methods - An unstructured, primarily exploratory design based on small samples, intended to provide depth insight and understanding. ​ Characteristic: ​ Primary exploratory ​ Unstructured (or semi) ​ Small sample (6-12) ​ Scenario ​ Exemplary applications ​ Brand associations ​ New product ideas ​ Product use issues ​ ​ Base: ​ In-depth psychology ​ Social and ethnography (ethnography represents real life observation, which follows customs, habits and differences between people in everyday situations) ​ Research techniques: ​ Group interview ​ In-depth interview ​ Projective techniques ​ Observation: mystery shopping and netnography (trace analysis) ​ The procedure of qualitative research is divided into two. At the moment if the clients/participants in the study know what the purpose of the study is, interviews are conducted - individual, group, psychological. If they do not know and the action is not direct, observations and projective techniques are used. ​ Quantitative research methods - Research techniques that seek to identify data and typically apply some form of measurement and statistical analysis ​ Characteristics: ​ Primary descriptive or casual ​ Structured ​ Large sample (200-1000) ​ Questionnaire or observation list ​ Exemplary applications: ​ Customer satisfaction trend ​ Determinants of brand image  ​ Brand recognizability ​ ​ Research techniques: ​ Survey (offline or/and online) ​ CAPI/CATI/CAWI Neuromarketing research techniques EEG (Electroencephalography) - Monitors brain electrical activity to assess emotional responses and attention. fMRI (Functional Magnetic Resonance Imaging) – Captures activity of concrete parts of a brain activity to identify, e.g. concrete emotions (joy vs. fear), emotional engagement, product valuation and willingness to buy, familiarity of given stimuli. Eye Tracking - Tracks where consumers look in advertisements to determine attention-grabbing elements. Mystery shopping Mystery shopping or a mystery consumer or secret shopper, is a tool used externally by market research companies, watchdog organizations, or internally by companies themselves to measure quality of service, or compliance with regulation, or to gather specific information about products and services. The mystery consumer's specific identity and purpose is generally not known by the establishment being evaluated. Mystery shoppers perform specific tasks such as purchasing a product, asking questions, registering complaints or behaving in a certain way, and then provide detailed reports or feedback about their experiences. Personal visits: How long were you in the queue? How many tills were open? Did the counter clerk apologise if you were kept waiting? What form of greeting or farewell was given? Telephone calls: How many rings were there before the phone was answered? Did the person who answered the phone go on to answer all your questions? Were you asked for a password? How many times during the conversation was your name used? Questionnaire Design - Lecture 5 The questionnaire must motivate the participant to cooperate, become involved and provide complete, honest and accurate answers. Questionnaire is a formalized set of questions for obtaining information from respondents Classification of Survey Methods ​ phone ○​ traditional ○​ CATI ​ face-to-face ○​ household ○​ office ○​ street ○​ CAPI ​ mail ○​ traditional ○​ ON-line ○​ panel Questionnaire design stages 1.​ Formulating general research questions 2.​ Constructing the questionnaire with scales 3.​ Pretesting the questionnaire (PILOT SURVEY!) 4.​ Utilizing final version of questionnaire in field research Questions Types ​ Open-end ​ Semi-closed ​ Closed ○​ Dichotomous questions ○​ Questions with more answers ○​ Multiple response set ○​ Scales Unstructured questions ​ are open-ended questions that respondent answer in their own words (What would you recommend to improve in our theatre?) ​ good first questions on a topic, they enable the respondents to express general attitudes and opinions ​ this type of question is necessary to code (to transfer from verbal version to numerical one), coding means the process of clustering similar answers in one bundle, the reason is to reduce huge array of answers to reasonable number Examples of Open-end Questions Which brand of cars do you know? Spontaneous Knowledge What is your favourite brand of drink? Brand preference What is in your mind hearing about brand Nike? Association Why people are unemployed? Opinion To help disabled people is necessary because Attitude Which cultural event would you recommend to your colleague? Recommendation, Attitude In the case you refuse to drink tap water, give a reason. What is your occupation? Identification of respondent How many employees work in your company? Identification of company What is your net income? Identification of respondent Semi-closed Question Choose three activities you like to do the most. If you miss your favourite activity in the list please add it. Submit card. Watching TV, video, DVD, listening the music Walking in parks, stay in nature Supporting (visiting sport matches) Making pictures, making videos (recording) Reading books, newspapers and journals Active physical exercises (swimming, skiing, riding the bicycle, aerobic etc.) 6 Meeting friends, parents visits Original hobby : playing musical instrument, collecting etc. Visit of cultural events (film, theatre, concerts) Eating out (cafe or restaurants) Shopping Tourist trips (visit s of museum and castles, ZOO) Additional activities: ……………………………….................. Ad.1. nie jestem pewna o co chodzi w tym xd, więc macie ss z prezentacji też, może on Wam więcej powie: Ad.2. chyba jednak wiem - chodzi o to, że na żółto są zaznaczone niby wybrane opcje i że to jest po prostu wielokrotny wybór Dichotomous Question ​ Exclusive type of question, you ask respondent to choose from contradictory answers, such as yes or no ​ the easiest type of questions to code and analyse, but the response can be influenced by the wording of the question Have you ever visited ZOO in Ostrava? ​ yes ​ no Filter Do you smoke the cigarettes? ​ yes ​ no  Filter What type of shopping centre do you prefer? 1 with entertainment zone 2 without entertainment zone Questions with More Options What is the main purpose of your visit at the shopping centre? ​ weekend purchase (purchase in hypermarket) ​ sales promotion (sale out, discounts, limited edition) ​ buying of product in the outlets of shopping centre ​ unplanned shopping walk Imagine that you are on weekend purchase in the shopping centre. It is noon. What is your the most frequent way of behaviour in that situation? ​ You have a lunch in restaurant ​ You visit fast food ​ You will have lunch after your return from shopping centre Multiple Response Set Respondent is asked to answer the question by choosing one or more alternative Which of given type of shop or entertainment would you prefer? Please choose three the most important. Submit card. luxury restaurant multiplex (cinema) post office 6 internet café typical restaurant Restaurant with service - middle category wellness centre Scaling Scaling can be considered a higher level measurement, scaling involves creating a continuum upon which measured objects are located. 1.​ Likert Scale ​ The Likert scale requires the respondents to indicate a degree of agreement or disagreement with each of a series of statements about the stimulus objects. ​ The analysis can be conducted on an item-by-item basis (profile analysis), or a total (summated) score can becalculated. 2.​ Semantic differential Scale ​ The semantic differential is a seven-point rating scale with end points associated with bipolar labels that have semantic meaning. ​ The negative adjective or phrase sometimes appears at the left side of the scale and sometimes at the right. Asking questions 1.​ Response choices should not overlap: Along with the tenets of clarity and precision goes the idea of mutual exclusivity. What this means is that the response choices to a question should not overlap with one another. Problematic example: Which of the following categories best describes your total household income before taxes in 1993? 1) less than $10 000, 2) $10 000-$15 000, 3) $15 000-$25 000, 4) $25 000 or higher. 2.​ Do not use words or phrases that suggest answers Problematic example: Do you use social media for marketing as one of most effective tools nowadays? 3.​ Avoid double-barreled questions Questions in which two opinions are joined together are called double-barreled. With these questions, the respondent must answer two questions at once even though his or her opinions about the two diverge. Problematic example: Do you believe that McDonald’s has fast and courteous services? Choosing Question Wording – Use Ordinary Words! “Do you think the distribution of soft drinks is adequate?” (Incorrect) “Do you think soft drinks are readily available when you want to buy them?” (Correct) Choosing Question Wording – Use Unambiguous Words In a typical month, how often do you shop in shopping malls? _____ Never _____ Occasionally _____ Sometimes _____ Often _____ Regularly (Incorrect) In a typical month, how often do you shop in shopping malls? _____ Less than once _____ 1 or 2 times _____ 3 or 4 times _____ More than 4 times (Correct) Choosing Question Wording – Avoid ambigous questions “What is the annual per capita expenditure on hairdresser in your household?” (Incorrect) “What is the monthly (or weekly) expenditure on hairdresser in your household (more or less)?” (correct) and “How many members are there in your household?” (Correct) Questionable questions! ​ What are your annual spending in supermarkets? ​ Are you an occasional or frequent donor? ​ How many charity ads did you see on TV last year? ​ What are the most determinant attributes in your evaluation of charities? ​ Do you think it is right for the government to tax charities and deprive them of income? Introduction to PLS- structural equation modeling (PLS-SEM) as one of methods used in marketing research The causality issue in marketing research… In strict sense causality denotes a necessary relationship between one event (called cause) and another event (called effect) which is the direct consequence (result) of the first. This strict meaning of causality is seldom transferable to marketing phenomena because there is usually more events necessary for particular event to occur. In analysis of marketing research data casual relationships are usually identified with regard to both: quantitative research results (data) and some theoretical (qualitative) assumptions. What is Structural Equation Modeling (SEM)? SEM is a statistical technique for testing and estimating causal relationships using a combination of statistical data and qualitative causal assumptions. SEM usually starts with a hypothesis, represents it as a model, operationalises the constructs of interest with a measurement instrument, and tests the model. The advantages of SEM technique (in comparison to simple regression): ​ Test models with multiple dependent variables, ​ Ability to test mediating variables - enables measurement of direct and indirect, ​ Ability to test moderating effects, which take place if some other factors („third factors”) influence on the main causal relationship (eg. between two variables), ​ Ability to work with relatively small sample sizes. When to use PLS-SEM (partial least squares SEM) vs. CB-SEM (covariance-based SEM) PLS-SEM: ​ If the research is exploratory or an extension of an existing structural theory, select PLS-SEM. ​ If formative constructs are part of the structural model, select PLS-SEM. ​ If the structural model is complex (many constructs and many indicators), select PLS-SEM. ​ If the sample size is relatively low, select PLS-SEM. Other: ​ If the data are to some extent nonnormal, use PLS-SEM; otherwise, under normal data conditions, CB-SEM and PLS-SEM results are highly similar Structured Equation Modeling (SEM) Structural model ​ the assumed causation among a set of dependent and independent constructs Measurement model ​ loadings of observed items (measurements) on their expected latent variables (constructs). Structured Equation Modeling (SEM) The combined analysis of the measurement (outer model) and the structural model (inner model) enables: SEM ​ factor analysis and hypotheses are tested in the same analysis PLS-SEM outer moder and inner model Im SEM factors (latent constructs) are represented by ellipses and indicator (measured) variables by rectangles. The factor ellipses and arrow creating them are called the inner or structural model. The indicator rectangles and arrows connecting them are called the outer or measurement model. Latent variable example Constructing baseline model Structured Equation Modeling (SEM) Path Model (Causal Model)  Reflective measurement models Reflective indicator loadings >0.708 Internal consistency reliability Cronbach’s alpha minimum 0.70 (or 0.60 in exploratory research) and maximum of 0.95 to avoid indicator redundancy. Convergent validity AVE > 0.50 Discriminant validity For conceptually similar constructs: HTMT 0.1 is acceptable