What is PeopleAnalyst?

PeopleAnalyst is the front door for people-analytics research: 205+ works indexed and profiled, 40+ citation-grade findings extracted, and peer-reviewed behavioral science translated from academic to actionable — the missing manual for the people analytics you always meant to do.

What is people analytics?

People analytics is not a dashboard. It is behavioral science and statistical inference applied to workforce decisions — a discipline with its own methodology, spanning measurement, organizational design, talent, leadership, and analytics craft.

Why does AI in HR need measurement science?

AI is being deployed in high-stakes people decisions — hiring, performance, attrition — without the measurement science to evaluate whether it works or whom it harms. Construct validity, effect sizes, and criterion validity are the vocabulary for asking an AI vendor the right questions.

How is the research made accessible?

The evidence is indexed and searchable: 205+ works, 40+ citation-grade insight cards, and 8 research arcs, so the right finding reaches the right decision at the right time.

What separates good people measurement from assertion?

Good measurement has a method: construct validity, reliability, and effect-size interpretation are not optional — they are what separates evidence from assertion.

library / lib2e0ef04e75968549

Case Study Research Design and Methods

Robert K. Yin

In a sentence

A comprehensive methodological guide for designing and conducting rigorous case study research in the social sciences to produce valid, reliable, and generalizable findings.

Case Study Research: Design and Methods is the definitive guide for students, academics, and professional researchers seeking to conduct high-quality case study research. Author Robert K. Yin demystifies this powerful research method, arguing against the common misconception that it is a 'soft' or purely exploratory approach. The book provides a rigorous, step-by-step framework, from defining the right research questions and designing the study to collecting, analyzing, and reporting the evidence. Distinguishing case study research from other methods, Yin offers a clear technical definition and practical guidance on tackling its greatest challenges, such as defining the 'case,' selecting appropriate designs (single vs. multiple, holistic vs. embedded), and analyzing complex data. By emphasizing the use of theory, the triangulation of evidence, the maintenance of a chain of evidence, and the logic of 'analytic generalization,' the book equips researchers to produce defensible, insightful, and theoretically significant case studies that can withstand scrutiny and make a lasting contribution to their fields.

The four lenses

Science
Statistics
Systems
Strategy

The model

This model outlines the causal pathway from methodological practices in case study research to the ultimate quality of the research. It posits that specific procedural tactics related to design, data collection, and analysis directly lead to achieving the four key criteria of research quality (construct validity, internal validity, external validity, and reliability), which in turn determine the overall quality of the case study.

Use of Multiple Sources of Evidencedesign lever

The practice of collecting data from several different sources (e.g., documents, archival records, interviews, observations) to allow for the triangulation and corroboration of findings.

Establishment of a Chain of Evidencedesign lever

The principle of creating explicit links between research questions, protocol, collected data, and conclusions, allowing an external observer to trace the derivation of evidence in either a forward or backward direction.

Informant Review of Draft Reportdesign lever

The procedure of having the draft case study report reviewed by the informants and participants in the case to corroborate facts and enhance the accuracy of the account.

Use of Pattern-Matching Analysisdesign lever

The analytic technique of comparing an empirically based pattern from the case study data with a predicted pattern (or several alternative predicted patterns) specified before data collection.

Use of Explanation-Building Analysisdesign lever

An iterative analytic technique, mainly for explanatory case studies, that aims to build a causal explanation about a case by revising theoretical propositions in light of the evidence.

Addressing Rival Explanationsdesign lever

The analytic strategy of identifying and systematically testing plausible alternative explanations for the case study's findings.

Use of Logic Models Analysisdesign lever

The analytic technique of stipulating and testing a complex chain of cause-and-effect events by matching empirically observed events to a theoretically predicted logic model.

Use of Theory in Design and Generalizationdesign lever

The development and use of theoretical propositions to guide the research design, data collection, and analysis, forming the basis for analytic generalization.

Use of a Case Study Protocoldesign lever

The practice of creating and following a formal document that contains the procedures, questions, and general rules for conducting the data collection for a single case.

Creation of a Case Study Databasedesign lever

The assembly of a formal, orderly archive of all case study evidence (notes, documents, tabular materials, etc.) separate from the final case study report.

Construct Validityoutcome metric

The extent to which the study identifies correct operational measures for the concepts being studied, avoiding subjective judgments.

Internal Validityoutcome metric

The extent to which a study establishes a sound causal relationship between conditions, distinguishing it from spurious relationships (applicable to explanatory studies).

External Validity (Analytic Generalization)outcome metric

The extent to which a study's findings can be generalized to a broader theory, as opposed to a population or universe.

Reliabilityoutcome metric

The extent to which the operations of a study, such as its data collection procedures, can be repeated by another researcher with the same results.

Overall Case Study Qualityoutcome metric

The overall rigor, credibility, and contribution of the case study research, judged by its significance, completeness, consideration of alternatives, and presentation.

How they connect

use of multiple evidence sources → influences construct validity
establishment of chain of evidence → influences construct validity
informant review of draft report → influences construct validity
use of pattern matching analysis → influences internal validity
use of explanation building analysis → influences internal validity
addressing rival explanations → influences internal validity
use of logic models analysis → influences internal validity
use of theory in design and generalization → influences external validity analytic generalization
use of case study protocol → influences reliability
creation of case study database → influences reliability
establishment of chain of evidence → influences reliability
construct validity → influences overall case study quality
internal validity → influences overall case study quality
external validity analytic generalization → influences overall case study quality
reliability → influences overall case study quality

The process

The book's operating playbook outlines a rigorous, systematic process for conducting high-quality case study research. It positions the case study not as a 'soft' or preliminary method, but as a comprehensive and demanding form of empirical inquiry suitable for answering 'how' and 'why' questions about contemporary phenomena in their real-world contexts. The playbook begins with a critical design phase, where the researcher develops a theoretical framework, defines the 'case' or unit of analysis, and establishes a logical plan linking research questions to data collection and analysis. This design is solidified through a preparatory phase that includes developing a detailed case study protocol, obtaining ethical approvals, and conducting a pilot study. The core of the playbook involves a multi-faceted data collection process that emphasizes triangulation from six different sources of evidence (documents, archives, interviews, observations, etc.). To ensure reliability and validity, the researcher must create a formal case study database and maintain a clear chain of evidence. The analysis phase is not an afterthought but a structured activity guided by one of several strategies, such as pattern-matching empirical data to theoretical propositions, building explanations iteratively, or examining rival hypotheses. The process culminates in composing a compelling report, tailored to a specific audience, that presents sufficient evidence and considers alternative perspectives. Overall, the playbook transforms case study research from an intuitive practice into a formal, replicable methodology. It emphasizes structure and rigor at every stage—from design to reporting—to produce findings that are not just descriptive but can be analytically generalized to expand theoretical understanding. The process is linear but iterative, with each stage building upon the last to create a robust and defensible study.

Conducting Case Study Research

To provide a comprehensive, step-by-step method for rigorously designing, conducting, analyzing, and reporting a single- or multiple-case study to investigate contemporary phenomena in their real-world context.

When to use: When a researcher needs to understand a complex social phenomenon holistically and in-depth, and believes that contextual conditions are highly pertinent to the phenomenon of study.

Step 1Determine the appropriateness of the case study method and frame the research questions.
Entry: A topic of interest has been identified.
Exit: A determination is made that the case study method is the most appropriate choice, and initial research questions are formulated.
- Is the primary research question a 'how' or 'why' question?
- Does the researcher have little or no control over the behavioral events to be studied?
- Is the focus on a contemporary, real-world phenomenon?
In: A topic of interest, A review of existing literature on the topic · Out: A set of 'how' or 'why' research questions, Justification for using the case study method
Step 2Design the case study.
Entry: The case study method has been chosen and initial research questions are framed.
Exit: A complete research design is articulated, specifying the case(s), propositions, design type, and analytic logic.
- Will this be a single-case or multiple-case study?
- Will the design be holistic (one unit of analysis) or embedded (multiple units of analysis)?
- If multiple cases, what is the replication logic (literal or theoretical)?
In: Research questions, Relevant theories and literature · Out: Defined study propositions, Defined unit of analysis (the 'case'), with clear boundaries, Selected case study design (e.g., multiple-case embedded), A plan for linking data to propositions and criteria for interpretation (including plausible rival explanations)
Step 3Prepare for data collection.
Entry: A research design has been established.
Exit: The researcher or team is fully prepared to begin formal data collection with a finalized protocol and selected case(s).
- Which candidate cases should be selected for the final study?
- Does the pilot study suggest a need to modify the protocol or data collection procedures?
In: The research design, A pool of potential candidate cases · Out: Institutional Review Board (IRB) approval for protecting human subjects, A comprehensive case study protocol containing an overview, procedures, data collection questions, and a report guide, Final selection of the case(s) to be studied, Findings from a pilot case study
Step 4Collect evidence from multiple sources.
Entry: Preparation for data collection is complete, including a finalized protocol and selected case(s).
Exit: Sufficient evidence has been collected to address the research questions, including data to test rival hypotheses and achieve triangulation for key findings.
- Which sources of evidence are most relevant for a given research question?
- Is there converging evidence for a key finding?
In: Case study protocol, Access to field sites, participants, and documents · Out: Collected evidence from multiple sources (documentation, archival records, interviews, observations, etc.), A structured case study database containing all collected data, A documented chain of evidence linking questions to data
Step 5Analyze the case study evidence.
Entry: Data collection is complete and a case study database has been created.
Exit: Empirically based findings are produced that address the research questions and consider rival explanations.
- Which general analytic strategy is most appropriate (e.g., relying on propositions, building from the ground up)?
- Which specific analytic technique(s) should be applied (e.g., pattern matching, explanation building, time-series analysis)?
In: The complete case study database, The original research design and propositions · Out: A set of analyzed findings, supported by evidence, An assessment of how the findings support or challenge the initial propositions, An evaluation of plausible rival explanations
Step 6Compose and share the case study report.
Entry: The analysis of case study evidence is complete.
Exit: A final, reviewed case study report is composed and disseminated to the intended audience(s).
- Who is the primary audience for the report?
- Which compositional structure (e.g., linear-analytic, comparative, chronological) is most effective?
- Should the case and participant identities be real or anonymous?
In: Analyzed findings, The case study database, The original research questions · Out: A draft case study report, Feedback from peer and participant reviewers, A final, compelling case study report (written, oral, or other format)

The story

The reader A graduate student, academic, or professional researcher who wants to understand a complex, real-world issue in-depth. They have 'how' or 'why' questions that cannot be answered by a survey or lab experiment and they want to produce a credible, defensible, and impactful piece of research.

External problem

Lacks a clear, systematic methodology for conducting case study research, making it difficult to design a study, collect and analyze data rigorously, and report findings in a way that is considered valid and generalizable.

Internal problem

Feels uncertain and anxious about their research being dismissed as 'unscientific,' anecdotal, or 'soft.' They fear their findings will be seen as subjective and not generalizable, undermining their confidence and the impact of their work.

Philosophical problem

It is fundamentally wrong that a powerful method for gaining deep understanding of complex social phenomena is so often misunderstood and poorly executed. Researchers deserve a clear, rigorous framework to unlock these crucial insights.

The plan

Chapter 1: Understand when to use the case study method based on your research questions.
Chapter 2: Design your case study by defining your case(s), developing propositions, and establishing a logical structure.
Chapter 3: Prepare for data collection by developing researcher skills, creating a detailed protocol, and conducting a pilot study.
Chapter 4: Collect evidence from multiple sources, create a database, and maintain a chain of evidence.
Chapter 5: Analyze your evidence using systematic techniques like pattern matching, explanation building, and addressing rival explanations.
Chapter 6: Compose and report your case study clearly and persuasively for your intended audience.

Success

The researcher conducts a methodologically sound and rigorous case study.
Their findings are seen as credible, defensible, and a significant contribution to their field.
They can confidently generalize their findings to theory and answer complex 'how' and 'why' questions.
They become a skilled and respected researcher, capable of tackling complex real-world problems.

At stake

The research is poorly designed and executed, leading to anecdotal or biased findings.
The study is criticized as 'soft' and unscientific, and its conclusions are dismissed.
The researcher wastes time and resources on a study that fails to produce meaningful or generalizable insights.
The researcher remains stuck, unable to answer their key research questions and feeling like a failure.

Questions this book answers

When and why should a researcher choose the case study method over other social science methods like experiments, surveys, or histories?
What are the critical components of a rigorous case study research design?
How can a researcher define the 'case' or unit of analysis and establish clear boundaries for the study?
What are the different types of case study designs (e.g., single vs. multiple, holistic vs. embedded) and when should each be used?
How can a researcher ensure the quality of their research design in terms of construct validity, internal validity, external validity, and reliability?

Glossary

Use of Multiple Sources of Evidence: The practice of using several sources of evidence (e.g., documents, archival records, interviews, direct observation, participant-observation, physical artifacts) to establish converging lines of inquiry, a process also known as triangulation.
Establishment of a Chain of Evidence: The principle of explicitly linking the components of the research process to allow an external observer to trace the derivation of any evidence from the initial research questions to the ultimate case study conclusions, and vice versa.
Informant Review of Draft Report: The procedure of sharing a draft of the case study report with the key informants or participants in the case to check for factual accuracy and to corroborate the essential findings.
Use of Pattern-Matching Analysis: An analytic technique that compares an empirically-based pattern from the collected case study data with a pattern predicted before data collection. The pattern can involve dependent variables or rival patterns of independent variables.
Use of Explanation-Building Analysis: An iterative analytic process for explanatory case studies where an initial theoretical proposition is revised repeatedly as evidence from one or more cases is examined, with the goal of developing a sound causal explanation.
Addressing Rival Explanations: A general analytic strategy that involves identifying, operationalizing, and empirically testing plausible alternative explanations for the case study's findings.
Use of Logic Models Analysis: An analytic technique where a sequence of cause-and-effect stages is stipulated theoretically (the logic model) and then compared against the empirically observed chain of events from the case study.
Use of Theory in Design and Generalization: The role of theory or theoretical propositions in guiding the research design from the outset, serving as a blueprint for the study and as the vehicle for generalizing the findings through analytic generalization.

Related in the library

Tools these methods power