Lecture week 1 - Introduction
Independent variable: The variable that is manipulated or controlled to observe its effect on the
outcome.
Dependent variable: The variable that is measured or observed to assess the effect of the independent
variable.
Levels of measurement (measurement scales):
Nominal (unranked groups)
Categorical (ranked groups)
Interval (comparative distances)
Ratio (true zero)
Types of data:
Quantitative research: Involves numerical data and statistical analysis to quantify variables and
identify patterns (e.g., surveys, experiments). Good for:
o Profiling detailed usage and behavior.
o Highlighting variations between different sub-groups.
o Precisely measuring consumer preferences for different products and services.
o Measuring the exact priorities consumers attach to different product features.
Qualitative research: Involves non-numerical data to explore concepts, opinions, or experiences
in depth (e.g., interviews, focus groups). Good for:
o Mapping the customer’s overall range of behavior and attitudes.
o Pinpointing the motivations behind people’s behavior.
o Stimulating new and creative ideas.
o Providing a forum for fresh creative thinking.
Research designs:
Exploratory research: Conducted to investigate a problem that is not well understood, aiming to
gain insights and generate ideas (e.g., literature reviews, interviews).
o Purposes:
Increase familiarity with problem.
Clarify concepts.
Develop specific hypotheses.
o Approaches:
Literature survey.
Experience/key informant survey.
Case studies.
Focus groups.
Descriptive research: Aims to describe characteristics of a population or phenomenon, often
answering the "who, what, where, when" questions (e.g., surveys, case studies).
o Purposes:
Describe the characteristics of certain groups.
, Estimate the proportion of people in a specified population who behave in a
certain way.
Examine associations between two or more variables.
Make specific predictions.
Causal research: Seeks to identify cause-and-effect relationships between variables (e.g.,
experiments, controlled studies).
o Approaches:
Laboratory experiments.
Field experiments.
All methods taught in this course are descriptive by design.
Data sources:
Secondary data: Data that has already been collected by others and is used for a different
purpose (e.g., government reports, company records).
o Syndicated research: A type of secondary data collected and sold by research firms to
multiple clients (e.g., market reports).
Primary data: Data collected directly by the researcher for the specific research project at hand
(e.g., surveys, experiments).
Lecture 2 – Guest lecture
Canceled.
Lecture 3 – Reliability, Validity, Dimensionality
(Factor Analysis)
Measurement involves assigning numbers to characteristics based on predefined rules.
Scaling refers to placing objects along a continuum (e.g., rating brand attitudes).
Different analysis techniques are used for different measurement scales:
Tests that describe the relationship between variables but do not imply causality:
o DV: Nominal → Chi-squared test (used to check for associations between categorical
variables).
o DV: Interval & ratio → Pearson correlation coefficient (measures the strength and
direction of a linear relationship between continuous variables).
Tests that estimate relationships between variables and, under certain conditions, can be used to
infer causality:
o DV: Nominal → Logistic regression (used to predict the probability of a binary outcome
and estimate the influence of predictors).
o DV: Interval & ratio → (Multiple) linear regression (used to predict a continuous
outcome based on one or more predictors).
, Types of Scales:
Comparative scales: Respondents compare objects (e.g., rank order or paired comparisons).
o Rank order scaling: Respondents rank a list of items in order of preference or
importance.
Example: "Rank these brands from 1 to 3 (1 = most preferred).
o Paired comparison scaling: Respondents choose between two items at a time.
Example: "Do you prefer Brand A or Brand B?"
o Constant sum scale: Respondents allocate a fixed number of points among items based
on importance or preference.
Example: "Distribute 100 points across these products based on how much you
like them."
Non-comparative scales: Objects are rated independently (e.g., Likert scale, semantic differential
scale).
o Likert scale: Respondents rate their level of agreement with statements on a scale (e.g., 1
= strongly disagree, 5 = strongly agree).
Example: "I am satisfied with Brand A: 1 (Strongly Disagree) – 5 (Strongly Agree)."
o Semantic differential: Respondents rate an object on a scale between two opposite
attributes.
Example: "Rate Brand A: 1 (Unpleasant) – 7 (Pleasant)."
o Continuous rating scale (slider scale): Respondents place a mark on a continuous line to
indicate their rating of an object.
Example: "Rate your satisfaction with Brand A by sliding from 0 (extremely
unsatisfied) to 100 (extremely satisfied)."
Multiple item measurement:
Using multiple items to measure a construct (e.g., impulsive buying tendency) improves reliability
(consistent results) and validity (accurately measuring what is intended).
Single-item scales may suffice for simple, objective constructs (e.g., age).
Measured scores can be broken down into 3 separate components:
Xo = Xt + Xs + Xe
Xo = observed score (e.g., your IBT-score)
Xt = true score (e.g., your real impulsive buying tendency)
Xs = systematic error (non-random error) (e.g., social desirability bias)
Xe = random error (e.g., being distracted for a moment, mood)
