MKT5612 Applied Marketing Research
The Complete Exam Bible · Semester A, 2026/27MKT5612 Overview
- City University of Hong Kong
- Semester A, 2026/27
- Postgraduate marketing course
- Three credit units
- Two-hour closed-book final exam
What this course trains you to do
Applied Marketing Research treats evidence as an input to managerial decision making. The course is not a catalogue of methods.
- Assessed by Two group projects, peer evaluation, a mid-term test, class participation and a final exam.
- Final exam The published final is two hours, closed book and closed notes.
- Hardest step Matching the design, measurement and sample to the exact managerial claim.
What you get in the full MKT5612 Exam Bible
- 7 chapters, 40 pages — every examinable topic
- 19 original practice questions, each with a model answer in the Final Exam format
- 7 worked examples, solved the way MKT5612 marks
- 11 computed figures, redrawn from the course’s own numbers
- Exam-morning plan for the Final Exam (35%) — what to revise last, where marks are lost
Free on this page: assessment table, chapter map, one worked example, key terms, FAQ. The rest is in the full exam bible.
How MKT5612 is assessed
| Component | Weight | Format |
|---|---|---|
| Group Projects I: Survey Design | 15% | 30 points; proposal, qualitative report and questionnaire stages |
| Group Projects II: Data Analytics | 20% | 40 points |
| Peer Evaluation | 5% | 10 points |
| Mid-Term Test | 15% | 30 points; held during class |
| Class Participation | 10% | 20 points; quality and frequency of participation |
| Final Exam | 35% | 70 points; two hours, closed book and closed notes |
The current outline publishes six components worth 200 points in total. Exact conversion gives 15%, 20%, 5%, 15%, 10% and 35%, matching the CityU catalogue split of 65% continuous assessment and 35% examination. The 70% minimum attendance expectation is a separate pass-risk condition, not an additional weighted component; students below the threshold may receive a failing course grade and should confirm attendance recording and approved-absence procedures on the course Canvas page.
Assessment structure
The six exact percentage weights come from the published two-hundred-point grading table and total 100%.
What other students are asking about MKT5612
- Where can I find lecture notes or study guides for MKT5612 at CityU?
- The MKT5612 study guide in AskSia Library covers Applied Marketing Research in 7 chapters, with the assessment table, a chapter-by-chapter topic map, key terms and a worked example, free to read on this page.
- Is there a final exam in MKT5612, and how much is it worth?
- Yes. In the offering this AskSia Library guide is built from, Final Exam carries 35% of the MKT5612 mark; the full split is Group Projects I: Survey Design 15%, Group Projects II: Data Analytics 20%, Peer Evaluation 5%, Mid-Term Test 15%, Class Participation 10%, Final Exam 35%.
- What does MKT5612 cover on secondary data and qualitative inquiry?
- In AskSia Library's MKT5612 guide, the Secondary Data and Qualitative Inquiry chapter explains source fit, focus groups, depth interviews, saturation and the handoff from findings to survey design.
- What does MKT5612 cover on measurement scales and construct quality?
- In AskSia Library's MKT5612 guide, the Measurement Scales and Construct Quality chapter explains nominal, ordinal, interval and ratio permissions, plus systematic error, random error, validity and reliability.
- What does MKT5612 cover on questionnaire design and survey flow?
- In AskSia Library's MKT5612 guide, the Questionnaire Design and Survey Flow chapter explains objective mapping, neutral wording, funnel order, screening branches, response options and pretesting.
Current MKT5612 dates
| Date | Item | Control |
|---|---|---|
| 18 September 2026 | Survey Design research proposal | Published in the current project instructions. |
| 5 October 2026 | Qualitative finding and questionnaire draft | Published in the current project instructions. |
| 19 October 2026 | Questionnaire final version | Published in the current project instructions. |
Dates are as published in the Semester A, 2026/27 survey design project instructions. Confirm exact deadlines and submission settings in the live LMS.
What MKT5612 covers
Seven chapters follow the available teaching materials from research problems and qualitative inquiry through measurement, questionnaire design, sampling, confidence intervals and causal experiments.
Research Problems and the Evidence Process
managerial decisions, problem identification, research objectives and the six-stage evidence processApplied marketing research begins with a decision, not a questionnaire. A broad management concern must be translated into a research problem, then into objectives and answerable questions.
- Management decisions and research problems
- Exploratory, descriptive and causal purposes
- Research objectives and answerable questions
- The six-stage evidence process
- Design choices and decision criteria
- Traceability from evidence to recommendation
Secondary Data and Qualitative Inquiry
source fit, focus groups, depth interviews, saturation and the handoff from findings to survey designSecondary data already exist because they were collected for another purpose. They can define a market, reveal historical patterns and prevent unnecessary fieldwork, but only after a fit check covering relevance, accuracy, currency, units and coverage.
- Internal and external secondary data
- Relevance, accuracy, currency and coverage
- Qualitative purposes and evidence limits
- Focus-group interaction and moderation
- Depth interviews and sensitive topics
- Coding, saturation and survey handoff
Measurement Scales and Construct Quality
nominal, ordinal, interval and ratio permissions, plus systematic error, random error, validity and reliabilityMeasurement assigns observable responses to attributes according to rules. Nominal measures distinguish categories, ordinal measures add rank, interval measures add interpretable equal differences, and ratio measures also have a meaningful zero.
- Constructs, variables and operational definitions
- Nominal and ordinal measurement
- Interval and ratio measurement
- Permitted comparisons and summaries
- Random and systematic measurement error
- Reliability, validity and pretesting
Questionnaire Design and Survey Flow
objective mapping, neutral wording, funnel order, screening branches, response options and pretestingA questionnaire is a measurement system and a respondent journey.
- Objective-to-item traceability
- Neutral, singular and answerable wording
- Response-option construction
- Funnel order and context effects
- Screening, branching and termination
- Cognitive pretesting and pilot revision
Sampling Designs and Survey Error
target populations, frames, probability and nonprobability designs, systematic intervals and total survey errorA sampling plan links the target population to the units that can actually be selected. The target population, sampling unit and frame must be distinguished before choosing a design.
- Target populations, units and frames
- Probability and nonprobability designs
- Simple random and systematic selection
- Stratified and cluster designs
- Coverage, nonresponse and measurement error
- Total survey error and inference boundaries
Sampling Distributions and Confidence Intervals
parameters and statistics, repeated-sample distributions, permissible difference and the required sample-size calculationA population parameter is fixed but usually unknown; a sample statistic varies from one random sample to another. The sampling distribution describes that repeated-sample variation. Its centre reflects bias, while its spread is the standard error.
- Parameters, statistics and repeated samples
- Sampling distributions and standard error
- Sample size and precision
- Confidence levels and critical values
- Margins of error and interval interpretation
- Permissible difference and sample-size planning
Experiments and Causal Validity
causal conditions, selection bias, random assignment, pre-, true and quasi-experiments, internal and external validityA causal claim requires covariation, correct time order and a credible account that rules out rival explanations. Experiments strengthen that account by manipulating a treatment, observing an outcome and creating a comparison.
- Covariation, time order and rival explanations
- Manipulation, treatment and comparison groups
- Random assignment versus random sampling
- Pre-, true and quasi-experimental designs
- Internal-validity threats and design controls
- External validity, spillover and implementation
It asks you to identify the decision an organisation faces, translate that decision into a research problem, choose evidence that can distinguish the live explanations, and report a conclusion no stronger than the design permits. The available teaching materials build this chain through qualitative and quantitative research, questionnaire construction, sampling, statistical precision and experiments.
Separately from weighted assessment, students are expected to meet 70% minimum attendance; falling below that threshold may mean a student does not pass and may result in a failing course grade, so confirm attendance records and approved-absence procedures on the course Canvas page.
Research Problems and the Evidence Process
The opening chapter separates problem-identification research from problem-solving research and turns the six-stage research process into a decision audit.
It shows why a symptom such as falling sales is not yet a research problem, why secondary evidence should usually be checked before new collection, and how the managerial implication proves whether a question is worth asking.
Secondary Data and Qualitative Inquiry
The next chapter evaluates source fit and then compares focus groups with depth interviews.
Focus groups reveal shared language, norms and disagreement through interaction. Interviews follow private experience and sequence. Both develop explanations and wording; neither estimates population prevalence. The practical handoff is from a qualitative finding to a construct, branch or response option in the later survey.
Measurement Scales and Construct Quality
Measurement levels are treated as permissions.
Nominal values identify, ordinal values order, interval values add equal distance and ratio values add a meaningful zero. The chapter then separates reliability from validity and uses the observed-value error model to show how a scale can be consistent but systematically wrong.
Questionnaire Design and Survey Flow
Question wording, response options and flow are designed together.
The chapter repairs double-barrelled, leading and ambiguous items, builds a funnel from broad behaviour to sensitive profile questions, and uses screening and branching to keep every path relevant.
The attached flowchart is read as the executable logic of the questionnaire rather than as decoration.
Sampling Designs and Survey Error
The sampling chapter begins with the target population and the operational frame, then compares convenience, judgmental, quota and snowball methods with simple random, systematic, stratified and cluster sampling.
It works the systematic interval and distinguishes random sampling error from measurement, frame, selection and respondent errors that do not disappear when the sample grows.
Sampling Distributions and Confidence Intervals
This chapter explains why sample statistics vary, why a larger sample narrows the sampling distribution, and how permissible difference, confidence and variability determine required sample size.
The published example is recomputed step by step and rounded upward, with response yield handled as a separate operational adjustment.
Experiments and Causal Validity
The final concept chapter asks what comparison can approximate the unobserved outcome without treatment.
It applies the three conditions for causality, separates two kinds of selection bias, compares pre-, true and quasi-experiments, and keeps internal validity distinct from generalisation.
Randomisation is treated as a protection for group comparability, not as a cure for spillovers, attrition or poor measurement.
How to use the guide
Read the chapters in order once, then revise by question type: classify a problem, choose a qualitative setting, diagnose a scale, repair an item, select a sample, recompute precision and evaluate a causal comparison.
Every practice item includes a complete answer and uses an original scenario. The source folder contains no past examination or official exam solution, so the practice mirrors taught methods rather than reproducing a University paper.
Worked example · free
Compute a systematic sample and check the frame
- 2Calculate the interval from frame size and required sample size.
- 3Apply the random start and list the next three positions.
- 3State the periodicity and coverage checks before interpretation.
Key terms
- Research Problem
- The information question that must be answered so a manager can choose among actions.
- Secondary Data
- Evidence collected previously for a purpose other than the current research problem.
- Focus Group
- A moderated group discussion used to reveal shared language, norms, reactions and disagreement.
- Depth Interview
- A private, flexible interview used to follow personal experience, sequence and sensitive detail.
- Interval Scale
- A scale with ordered, equal distances but no meaningful absolute zero.
- Content Validity
- The extent to which a measure covers the domain of the intended construct.
- Sampling Frame
- The operational list of sampling units from which a sample can actually be selected.
- Systematic Sampling
- A probability method using a random start followed by every kth unit in the frame.
- Sampling Distribution
- The distribution of a sample statistic across all possible samples of the same size.
- Permissible Difference
- The largest accepted distance between an estimate and population value at a chosen confidence level.
- Internal Validity
- The extent to which an observed treatment-control difference was caused only by the treatment.
- External Validity
- The extent to which an experimental effect generalises beyond participants and the study setting.
MKT5612 FAQ
How is the course assessed?
The current outline allocates fifteen per cent to Survey Design, twenty to Data Analytics, five to Peer Evaluation, fifteen to the Mid-Term Test, ten to Class Participation and thirty-five to the Final Exam. Those values are exact conversions from the published two-hundred-point table and add to one hundred per cent.
What is published about the final exam?
The current outline states that the Final Exam lasts two hours and is closed book and closed notes. It says the timetable is normally available through AIMS in week ten. No section structure, question count or permitted-material exception appears in the available materials, so confirm those operational details on the live course surfaces.
What does the survey design project require?
The project develops a proposal, a qualitative report, a questionnaire draft and a final questionnaire. The draft must follow the taught questionnaire rules, use a funnel, make every branch explicit, include numbering and attach a flowchart. The qualitative report must show how its findings changed the survey design.
When should I use a focus group instead of an interview?
Use a focus group when interaction, shared language, norms or disagreement is part of the evidence. Use a depth interview when private disclosure, personal sequence or a sensitive experience would be distorted by an audience. Neither method estimates population prevalence; both develop explanations and language for a later structured design.
Which measurement level should I choose?
Choose the level whose meaning supports the planned claim. Nominal values identify categories, ordinal values add order, interval values add equal distance and ratio values add a meaningful zero. Do not choose by whether the data column contains numbers. Write the intended comparison first, then confirm the scale permits it.
Does a larger sample fix survey bias?
A larger probability sample can reduce random sampling error. It does not repair frame undercoverage, voluntary response, a leading questionnaire or respondent misunderstanding. Those nonsampling errors can persist while an estimate becomes more precise. Diagnose the error mechanism before recommending more observations.
Can attendance affect whether I pass?
The current outline states a 70% minimum attendance expectation and says students below it may receive a failing grade. That condition sits outside the weighted assessment table. Treat it as a pass-risk requirement, and confirm how attendance is recorded and any approved absence process on the course Canvas page.
Questions students ask in each MKT5612 chapter
- Why should a research brief begin with a decision?
- A decision specifies what the evidence must enable. Starting with a preferred method invites irrelevant data collection, whereas a clear action choice exposes which uncertainty matters, what comparison is needed and how accurate the answer must be. Chapter 01 · Research Problems and the Evidence Process
- Why not always collect new primary data?
- Primary data cost time and money and may duplicate knowledge already available. A disciplined secondary-data review can narrow the question, establish benchmarks and expose coverage gaps, making any later collection more focused and defensible. Chapter 02 · Secondary Data and Qualitative Inquiry
- Does a numerical response automatically have an interval scale?
- No. Numbers may be category codes or ordered labels. Interval status requires the differences between adjacent values to represent equal empirical differences, which cannot be established merely by printing digits beside response options. Chapter 03 · Measurement Scales and Construct Quality
- Why must every question map to an objective?
- Traceability prevents interesting but unused questions from increasing burden and context effects. It also makes omissions visible: if an objective has no measure, the eventual analysis cannot answer it regardless of sample size. Chapter 04 · Questionnaire Design and Survey Flow
- Does a large convenience sample become representative?
- No. Size can reduce random sampling variability only within a design that supports the calculation. It cannot repair unknown selection mechanisms, systematic undercoverage or response patterns that differ with the variables being studied. Chapter 05 · Sampling Designs and Survey Error
- Why must a calculated sample size be rounded upward?
- The unrounded result is the minimum implied by the desired precision. Rounding downward makes the planned standard error slightly larger and fails the stated requirement, whereas rounding upward preserves or improves it. Chapter 06 · Sampling Distributions and Confidence Intervals
- Why is random assignment different from random sampling?
- Random assignment creates comparable treatment groups and supports an internal causal contrast. Random sampling gives population units known selection chances and supports generalisation. A study can have one without the other, so the two claims must be justified separately. Chapter 07 · Experiments and Causal Validity
How to study for the exam
Build one research chain on a real marketing decision and carry it through all seven chapters. Write the managerial choice and the unknown first. Add the secondary evidence you would check and choose either a focus group or interview for the remaining meaning. Define one construct at the correct measurement level, write two neutral items, draw the branch flow and name the target population and frame.
Choose a sampling mechanism and compute one interval or sample-size requirement. Finally, design a treatment-control comparison and state one internal and one external validity threat. This produces a connected revision artifact rather than seven isolated lists. For the final pass, work every practice item without looking at its answer, then circle the population noun, causal verb and numerical direction in what you wrote.
Repair any conclusion whose design cannot support those three features. Confirm the exam timetable and any later SPSS coverage on Canvas because the captured teaching materials do not contain detailed explanations for the scheduled later analysis topics.
Your AI Marketing tutor for MKT5612
Stuck on a hard MKT5612 question? Sia is AskSia’s AI Marketing tutor — ask any MKT5612 Applied Marketing Research question and get a clear, step-by-step explanation grounded in how the course is actually taught and assessed. Read this whole study guide free, then take your hardest questions to Sia.