Quantifying the Past

Lesson 1: Operationalization and Variables

Quantitative Methods for Causal Inference

CLIOMETRICS LAB

The Historian's Challenge

"How do we measure the 'political instability' of a 19th-century colonial outpost using nothing but tax ledger records and weather logs?"

— The Research Dilemma

Qualitative Concept

Complex, multi-faceted, and often subjective.

Operationalization

The process of defining a fuzzy concept as a measurable variable.

Types of Variables in Cliometrics

Independent Variable (\(X\))

The hypothesized cause. In historical terms, this is the catalyst or policy change.

Example:

Enclosure Acts (Policy change)

Dependent Variable (\(Y\))

The hypothesized effect. This is the historical outcome we are trying to explain.

Example:

Urban Migration Rates

Proxy Variables

Variables used to represent a concept that cannot be measured directly.

Concept:

Standard of Living

Proxy:

Average height of recruits / Caloric intake records

The Archival Gap

1. Survival Bias

Which records were kept? Often, only the records of victors, the wealthy, or the central state survive.

2. Measurement Error

Pre-modern records lack standardized units. A 'bushel' in 1720 may not be a 'bushel' in 1820.

3. Conceptual Drift

The meaning of "household" or "occupation" changes over time, potentially skewing longitudinal data.

4. Missingness

Data is rarely "Missing at Random" (MAR) in history; it is usually missing because of war, fire, or neglect.

Seminar Workshop

"Pick a historical concept (e.g., Religiosity, Social Mobility, Imperial Strength). In your groups, brainstorm three potential archival proxies and identify one major source of measurement error for each."

Form Groups

Brainstorm

Defend

Quantifying the Past Data and Variables

Quantifying the Past Slides

Operationalization Challenge Worksheet