Market Research MKT702 Study Guide

Three Marketing Research Designs

1. Exploratory Research

2. Descriptive Research

3. Predictive or Causal Research

1. Exploratory Research- Research Designs

• Description: Aims to discover ideas and insights to better understand a problem or situation. It is often used to understand consumer motivations, attitudes, and behaviors.

• Data Collection Technique Example: Qualitative methods such as focus groups, in-depth interviews, and observation.

2. Descriptive Research - Research Designs

• Description: Collects quantitative data to describe characteristics of existing market situations and evaluate current marketing mix strategies. It identifies relationships between variables and determines if differences exist between groups.

• Data Collection Technique Example: Image assessment surveys or customer satisfaction surveys. Also, structured surveys and observational studies.

3. Predictive or Causal Research -Research Designs

• Description: Compares two or more variables to understand how one variable impacts a dependent variable. It investigates the concept of causality between independent variables (X) and one dependent variable (Y), stated as "If X, then Y".

• Data Collection Technique Example: Experiments and test markets. Also, the use of questions framed on the specific impact one variable causes on another variable.

Advantages and Disadvantages of Qualitative data

Qualitative Data

• Advantages:

  • Discovery of ideas and preliminary insights.

  • Richness of data and high validity.

  • Can be completed quickly.

• Disadvantages:

  • Lack of generalizability and low reliability.

  • Difficult to estimate scope.

  • Requires skilled researchers to interpret findings accurately.

Advantages and Disadvantages of Quantitative Data

Quantitative Data

• Advantages:

  • Validation of facts, estimates, and relationships.

  • Good representation of target populations.

  • Statistical analysis and interpretation of analysis, descriptive, and causal predictions are possible.

  • Large sample sizes and generalizable results.

  • Facilitates advanced statistical analysis.

• Disadvantages:

  • Questions that accurately measure attitudes/behavior can be challenging to develop.

  • In-depth data are difficult to obtain.

  • Low response rates can be a problem.

 Focus Groups

• Description: Small groups engage in an interactive discussion about a specific topic.

• Advantages:

  • Stimulates new ideas and fosters understanding of consumer behavior.

  • Allows client participation and elicits wide-ranging responses.

  • Brings together hard-to-reach respondents.

• Disadvantages:

  • Generalizability issues due to small sample size.

  • Sensitive topics may be difficult to discuss.

  • Social desirability bias and group dynamics can influence responses.

  • Limited depth and can be costly and time-consuming.

• When to Use: Use focus groups for open and honest dialogue to gather rich insights for product development, advertising and branding, and political research.

 In-Depth Interviews (IDIs)

• Description: One-on-one interviews with trained interviewers, using semi-structured questions.

• Advantages:

  • Offers detailed insights.

  • No social pressure.

  • More depth compared to focus groups.

• Disadvantages:

  • Requires skilled interviewers with strong interpersonal communication, listening, probing, and interpretation skills.

• When to Use: Use for sensitive topics or when detailed individual perspectives are needed, such as executive decision-making.

Observational Data Techniques

• Description: Researchers collect primary data by observing human behavior and marketing phenomena.

• Advantages:

  • Captures actual behavior, not self-reported behavior.

  • Reduces recall errors, bias, and interviewer errors.

  • Time and cost-efficient.

• Disadvantages:

  • Difficult to generalize.

  • Cannot explain behaviors unless combined with other methods.

  • Challenges in setting up and recording observations.

• When to Use: Ideal for tracking shopping behavior or analyzing website navigation patterns.

Null Hypothesis

• The null hypothesis states there is no difference between group means.

• Accepting the null means there is no statistically significant relationship between the variables.

a null hypothesis is the default assumption that nothing special is happening or that there is no effect or difference in whatever you’re testing.

For example, if you’re testing a new diet pill to see if it helps with weight loss, the null hypothesis would be:

The diet pill has no effect on weight loss.

Rejecting the Null Hypothesis

• Chi-Square: Reject if there are statistical differences between groups.

• T-test: Reject if the t-statistic is greater than the critical value.

• F-test (ANOVA): Reject if the F-statistic is greater than the critical value.

• Chi-Square:

Reject if there are statistical differences between groups.

• T-test:

• Reject if the t-statistic is greater than the critical value.

• F-test (ANOVA):

• Reject if the F-statistic is greater than the critical value.

Type I & Type II Errors

• Type I Error: Rejecting a true null hypothesis (false positive).

• Type II Error: Failing to reject a false null hypothesis (false negative).

Sampling Techniques - Two Broad Categories:

1. Probability Sampling: Each sampling unit has a known probability of selection.

2. Nonprobability Sampling: The probability of selection is not known.

Probability Sampling:

• Ensures unbiased selection and proper sample representation.

• Allows generalization to the target population.

• Can measure sampling error.

Nonprobability Sampling:

• Selection is based on researcher judgment.

• Cannot measure sampling error, limiting findings.

Specific Sampling Techniques:

• Probability Sampling: Simple Random Sampling – Each member has an equal chance of selection.

• Nonprobability Sampling: Convenience Sampling – Selection is based on ease of access.

Survey/Questionnaire Design and Question Type Nuances

• 
  

  • Types of Information Collected in Surveys:
    
    

    • State-of-Being: Demographics, socioeconomic characteristics.

    • State-of-Intention: Future behavioral intentions.

    • State-of-Mind: Attitudes, emotions.

    • State-of-Behavior: Past/current observable actions.

  • Pretesting Surveys:
    
    

    • Pilot Study: 50–200 respondents.

    • Pretest: 10–30 respondents focusing on a specific component.

Four Types of Scales

1. Nominal Scale: Categorical labels, no ranking.

2. Ordinal Scale: Ordered ranking, unequal gaps.

3. Interval Scale: Equal spacing, no true zero.

4. Ratio Scale: Equal spacing, true zero.

Four Types of Scales examples

• Nominal Scale: "What is your hair color?"

• Ordinal Scale: "Rate customer satisfaction: Very Unsatisfied to Very Satisfied."

• Interval Scale: "Temperature over a week (°C)."

• Ratio Scale: "Annual income?"

• 
  

Measures of Central Tendency:

• Nominal Scale: Mode.

• Ordinal Scale: Median and Mode.

• Interval & Ratio Scale: Mean and Standard deviation.

Likert Scale

• Measures attitudes using five- or seven-point scales.

• Balanced scale (equal positive and negative points).

• Lowest value: Strongly Disagree.

• Highest value: Strongly Agree.

Statistical Tests: When to Use and Why

• Chi-Square: Nominal data – Association between categorical variables.

• T-Test: Interval/Ratio data – Compares two means.

• ANOVA: Interval/Ratio data – Compares three or more means.

When to Use Conjoint Analysis, Factor Analysis, Regression Analysis

• Conjoint Analysis: Evaluates customer value for product features.

• Factor Analysis: Reduces large datasets into key variables.

• Regression Analysis: Predicts future outcomes.

Key Elements of a Research Report

1. Background, Objectives, Research Questions.

2. Literature Review & Secondary Data.

3. Research Methods.

4. Findings (Clear Visuals).

5. Interpretation, Conclusions, Recommendations.

6. Executive Summary.