SOSC 1210 - First-Year Seminar for Quantitative Social Analysis: Introduction

Governments:  

• Purpose:  administrative functions  & social control  puproses (taxation or licensing)
• Different bureau's or departments keep different data
  • Fo example. HK transport dept keeps stats on car registrations)

Non-govermental organizations (including religions and businesses)

• Purpose: administrative functions, control, and advocacy

Individuals -

• Own data  for admin (e.g. receipts kept for tax purposes)
• Own data for health, sentiment or other personal reasons (blood pressure readsings, glucose readings  descriptions of dreams, etc.)
• Other people's data for admin (e.g. parents keep vaccination records for kids)
• Other people's data for sentiment  (e.g. list of birth dates of friends)
• Other people's data - for research (e.g. an academic who collects data on opinions)

Data collected for one purpose may get re-used for other purposes

Example:

• USA Social Security Administration- data on "most popular names" https://www.ssa.gov/OACT/babynames/index.html
  • Not gathered for that purpose, but in 1990s once the data became usable online, it became a popular tool  - https://www.ssa.gov/OACT/babynames/background.html

Organizations and Governments collect data on a variety of schedules

• Continually (e.g. social media, business apps for "surge pricing", etc.)
• Weekly (e.g. "reportable" illnesses)
• Monthly   (employment figures, inflation)
• Quarterly
• Annual - Yearly
• Every 10 years

Information on individuals & then often aggregated

• Names 
• Gender
• Births
• Marriage
• Deaths
• Illness
• Property owned (houses, cars, etc.)
• Movements
• Income
• Physical Information (height, weight, DNA etc.)
• Cultural or ethnic information (education attained, languages spoken, religions observed)
• Beliefs, opinions

Organizational information

• Size (number of members, employees, etc)
• Type of business or industry

Economic Information of a particular location or regime (often aggregated from personal information)

• Population
• Wages
• Unemployment
• Inflation
• Productivity

Free or Fee?

• Some data is made available to the public for free
• Other data is bought and sold.  It's a big market.

 Format

• Some data is originally in physical format (paper, clay, etc.) and needs to be transcribed  (e.g. https://cdli.ucla.edu/?q=downloads)
• Some data is available in table format as documents or pdf
• Some is available in common easily manipulated formats like .csv or excel, others in tab  deliminated txt