Qualitative Methods for Quantitative People with GenAI Course

Lesson 1 • Core Assumptions of Qualitative Inquiry

Contrasts positivist and interpretivist epistemologies. Learners understand how ontological stance shapes research design choices.

Lesson 2 • Language and Vocabulary of Qualitative Work

Introduces key terms: saturation, thick description, emic/etic, and trustworthiness. Precise vocabulary prevents misapplication of methods.

Lesson 3 • The Quantitative Researcher's Blind Spots

Identifies what numeric models miss: motivation, context, and narrative. Sets the stage for why qual methods fill critical gaps in analysis.

Lesson 1 • Sampling Strategy and Participant Selection

Covers purposive, theoretical, and snowball sampling. Learners justify sample size and composition without defaulting to statistical power logic.

Lesson 2 • Choosing a Qualitative Methodology

Compares grounded theory, phenomenology, ethnography, case study, and narrative inquiry. Learners match methodology to research purpose.

Lesson 3 • Writing a Qualitative Research Proposal

Structures a complete proposal: rationale, questions, methodology, sampling, and ethics. Learners produce a proposal reviewers can evaluate.

Lesson 4 • Formulating Qualitative Research Questions

Teaches how to craft open, exploratory questions that guide qual inquiry. Poorly formed questions are the most common design failure.

Lesson 1 • Focus Group Facilitation

Teaches group dynamics management, stimulus materials, and capturing interaction data. Focus groups generate data unavailable in one-on-one settings.

Lesson 2 • Document and Artifact Analysis

Extends data collection to texts, images, and organizational artifacts. Learners triangulate primary data with secondary documentary sources.

Lesson 3 • Designing Semi-Structured Interviews

Builds interview guides with probes, sequencing, and neutral language. Guide quality directly determines data richness.

Lesson 4 • Observation and Field Notes

Introduces participant and non-participant observation, field note formats, and observer effect. Observation captures behavior that self-report cannot.

Lesson 1 • Preparing Data for Analysis

Covers anonymization, data cleaning, and segmentation into analyzable units. Clean, de-identified data protects participants and enables rigorous coding.

Lesson 2 • AI-Assisted Transcription Tools

Evaluates GenAI transcription tools for accuracy, speaker diarization, and privacy risk. Learners apply quality-control checks to AI-generated transcripts.

Lesson 3 • Data Organization and Corpus Management

Establishes file naming, version control, and metadata schemas for qualitative corpora. Organized data enables efficient retrieval and audit.

Lesson 1 • Intercoder Reliability and Calibration

Covers Cohen's kappa, percent agreement, and calibration sessions. Reliability metrics translate qual rigor into language quant practitioners trust.

Lesson 2 • Building and Managing a Codebook

Structures codebook entries with definitions, inclusion rules, and examples. A well-maintained codebook ensures consistency across coders and time.

Lesson 3 • First-Cycle Coding Methods

Introduces descriptive, in vivo, process, and emotion coding. First-cycle codes stay close to the data before interpretation begins.

Lesson 4 • AI-Assisted Coding with GenAI Tools

Uses large language models to suggest codes, apply codebooks, and flag new patterns. Learners critically evaluate AI code suggestions against human judgment.

Lesson 1 • Writing Analytic Memos

Uses memos to document interpretive decisions, emerging insights, and analytic pivots. Memos create an audit trail and deepen reflexive thinking.

Lesson 2 • GenAI for Theme Generation and Review

Applies GenAI to cluster codes, draft theme descriptions, and stress-test theme boundaries. Human interpretive authority must remain central.

Lesson 3 • Generating and Reviewing Themes

Guides collating codes into candidate themes, reviewing fit, and refining boundaries. Themes must be internally coherent and externally distinct.

Lesson 4 • Interpreting Themes in Context

Connects themes to theory, literature, and the research question. Interpretation moves analysis from description to explanation.

Lesson 1 • Reflexivity and Positionality

Examines how researcher identity, assumptions, and biases shape data and interpretation. Reflexivity is a quality marker, not a confession of weakness.

Lesson 2 • Dependability and Confirmability

Establishes audit trails, reflexivity statements, and inquiry audits. These criteria address consistency and neutrality in qualitative work.

Lesson 3 • Transferability and Thick Description

Teaches how to write context-rich descriptions that enable readers to judge applicability. Transferability replaces generalizability in qual logic.

Lesson 4 • Credibility Strategies

Covers prolonged engagement, triangulation, member checking, and peer debriefing. Credibility is the qual equivalent of internal validity.

Lesson 1 • GenAI for Report Drafting and Synthesis

Uses GenAI to draft report sections, synthesize themes, and generate executive summaries. Learners maintain authorial control and verify AI-generated claims.

Lesson 2 • Integrating Qual and Quant Findings

Applies joint display, sequential explanation, and embedded design integration strategies. Integration produces insights neither method yields alone.

Lesson 3 • Structuring Qualitative Research Reports

Covers standard report sections: context, methodology, findings, interpretation, and implications. Structure signals rigor and aids reader navigation.

Lesson 4 • Using Quotes and Excerpts Effectively

Teaches selecting, framing, and attributing participant quotes. Quotes are evidence, not decoration, and must be analytically justified.