the process of [social research theory/model/framework conceptual relationships hypotheses working...

The process of [social research• theory/model/framework

• conceptual relationships

• hypotheses

• working hypotheses and measurement

• research design

• data collection

• data analysis

• interpretation of results given hypotheses

• revision of theory

Measure concepts in order to:

• describe attributes, patterns, variation (univariate analysis)

• determine existence of relationships (association, causal)

• determine nature of the relationship(s) (direction, linear, non-linear, bivariate, multivariate, etc.)

population

processes characteristics

fertility sizemortality growthmobility composition

population

processes characteristics

fertility sizemortality growthmobility composition

SO

CIE

TY

EN

VIR

ON

ME

NT

population

processes characteristics

fertility sizemortality growthmobility composition

SO

CIE

TY

EN

VIR

ON

ME

NT

SO

CIE

TY

EN

VIR

ON

ME

NT

Units of analysis:

• individuals

• groups/communities

• organizations

• artifacts (technology, texts)

primary data collection or field studies

• observation/participant observation

• interviews

• survey research

• self-administered (mail)

• face-to face administered

• phone

secondary data collection

• tabulations

• archives

• other “texts”

public use data files; micro-data analysis:

analysis of raw data collected by others straddles primary and secondary data analysis

combination of primary and secondary data analysis

Categories of population attributeswith implications for data collection

• Stock– size

– growth

– composition

– distribution

• Flow– components of

change• fertility

• mortality

• mobility

• boundary change

Primary sources of population data:

• Censuses– Coverage error

• reliability

– Measurement of error• Post enumeration surveys

• Dual system estimation

• Demographic analysis

– Content error• Validity and reliability

• Surveys

U.S. Bureau of the Census

• Decennial census– Content

• Short form

• Long form

• Current Population Survey

• American Community Survey

• Business Surveys

Geographic Hierarchy

Census Regions and Divisions of the United States

Metropolitan Areas

• Defined by the Office of Management and Budget (OMB)

• Made up of a county or counties (or equivalent entities)

• Contain large population nucleus

• High socioeconomic integration

• MSA, CMSA, PMSA

Urbanized Areas• Densely settled areas with population of at

least 50,000

• Geographic core of block groups or blocks that have a population density of at least 1,000 people per square mile – Urban Cluster

Counties

• Counties in 48 States• Independent Cities in 4 States• Parishes in Louisiana• Cities and Boroughs in Alaska

Small-Area Geography Overview

Census Tracts

• For the first time for Census 2000: Cover the nation

• Relatively homogenous population characteristics

• 65,000 Census tracts across U.S.

• Size: optimally 4,000 people, range between 1,000 and 8,000

Blocks

• Smallest units of data tabulation

• Cover the entire nation

• Do not cross census tracts or counties

• Generally bounded by visible features and legal boundaries

• Block numbers completely different from 1990

• Size: average about 100 people

Census Block Map

Block Groups

• Groups of blocks sharing the same first digit

• Smallest areas for which sample data available

• Size: optimally 1,500 people, range between 300 to 3,000

Primary sources of event data:

• Registration of demographic events (vital statistics– Vital registration systems– Population registration systems

• US: – National Center for Health Statistics

• County registration of vital events• National Health Surveys

– prevalence– Centers for Disease Control

• Reporting of disease – Incidence

• New York State Department of Health

RatesEvents per population at risk of event

Usually standardized (per k population)k = 1,000, or 10,000, or 100,000

Ratios

Comparison of values

Crude Death Rate (CDR):

CDR = deaths during year

per mid-year population ( x 1,000)

CDR = (d / P ) x 1,000

where

d = deaths occurring during the year

P = mid-year population

Age Standardized rates