Week 2 Notes - Course Introduction

Published

September 15, 2025

Key Concepts Learned

Part 1: Algorithmic Decision Making

Key Terms → Data Science: Computer science/engineering focus on algorithm and methods → Data Analytics: Application of Data Science methods to other disciplines → Machine Learning: Algorithm for classification and prediction that learn from data → AI: Algorithms that adjust and improve across iterations (neural networks, etc)

Government data collection history: Civic registration system Census Data Administrative records Operations Research (Post-WWII) What’s new in data collection: More data that are official and accidental Accidental → we turned on our location when updating on instagram Focus on prediction rather than explanation Harder to interpret and explain

Algorithmic decision making is especially appealing because it promises: Efficiency - process more cases faster Consistency - same rules applied to everyone Objectivity - removes human bias Cost savings - fewer staff needed

Data Analytics is subjective because every step involves human choices. For example during Data cleaning decisions; Data coding or classification; Data collection - use of imperfect proxies; How you interpret results; What variables you put in the model. These choices embed human values and biases.

Part 2: Active Learning Exercise

Small group challenge scenario: School enrollment assignment Proxy: zipcodes stand in for “assignment-distance” Blindspots: wealthy/lower economic class neighborhood tend to be grouped together Harm + guiderail: low-income neighborhood get low quality education -> we’d add more demographic data into consideration like racial data and income data into account when assigning school rather than just distance to achieve racial and economic diversity in certain neighborhood.

Part 3: Census Data Foundations

  • The Decennial Census counts every person in the U.S. every 10 years to determine population counts for congressional apportionment and redistricting, asking basic questions about age, sex, and race.
  • In contrast, the American Community Survey (ACS) is a continuous, year-round survey sent to a sample of addresses that replaces the decennial “long form” by gathering detailed, timely socioeconomic, housing, and transportation data for communities to inform planning and funding for services and programs.
  • ACS Data 1-Year Estimates (areas > 65,000 people) Most current data, smallest sample

5-Year Estimates (all areas including census tracts) Most reliable data, largest sample What you’ll use most often

Census Geographic Hierarchy : Nation>Regions>States>Counties>Census Tracts (1,500-8,000 people)>Block Groups (600-3,000 people)>Blocks (~85 people, Decennial only)

Most policy analysis happens at: County level - state and regional planning Census tract level - neighborhood analysis Block group level - very local analysis (tempting, but big MOEs)

Accessing Census Data in R Traditional approach: Download CSV files from Census website Modern approach: Use R packages to access data directly –> use the tidycensus package

Benefits of programmatic access:

Always get latest data Reproducible workflows Automatic geographic boundaries Built-in error handling

When New Data Comes Out - ACS 1-year estimates: Released in September (previous year’s data) - ACS 5-year estimates: Released in December - Decennial Census: Released on rolling schedule over 2-3 years

Helpful Data Sources

TIGER/Line Files - Geographic boundaries (shapefiles) - Census tracts, counties, states - Now released as shapefiles (easier to use!)

Historical Data Sources: - NHGIS (nhgis.org) - Historical census data - Neighborhood Change Database - Longitudinal Tract Database - Track changes over time

Part 4: Census Data with R

total_pop table –> B01003_001 median_income table –> B19013_001

Coding Techniques

  • [New R functions or approaches]
  • [Quarto features learned]

Questions & Challenges

  • [What I didn’t fully understand]
  • [Areas needing more practice]

Connections to Policy

  • [How this week’s content applies to real policy work]

Reflection

  • [What was most interesting]
  • [How I’ll apply this knowledge]