Knight Foundation Soul of the Community

Knight Foundation Soul of the Community

Data Documentation

Please review all materials before using data.

Data type: the data is provided as an SPSS portable file which can be read by SPSS (and retain all of its labeling and annotation), SAS and by many other data programs. The file name is “Knight Foundation 2009 SOTC data.por”

Knight Communities: Specific Knight Communities can be identified by variable QSB.

Survey item scales and recoding: The Soul of the Community survey instrument contained survey items using a variety of scales (i.e., 5 response categories, 4 response categories, etc.). To provide for consistency in reporting across the different metrics, all survey items were recoded (or rescaled) to a three-point scale (low, medium and high). Different scales were recoded in the following manner:

7-point scale (Q26 only): 1-2=low, 3-5=medium, 6-7=high

6-point scales: 1=low, 2-4=medium, 5-6=high

5-point scales: 1-3=low, 4=medium, 5=high

4-point scales: 1=low, 2-3=medium, 5=high

3-point scales: unchanged (response categories were still reordered from low to high)

Yes/no items: Yes=high, low=no

Open-ended scale (Q23 only): 0=low, 1-2=medium, 3+=high

The dataset contains both the originally-scaled survey items and the recoded survey items. The variable names for the originally-scaled survey items are the letter “Q” following by the question number – e.g., “Q5”. The variable names for the recoded survey items are the letter “Q” and the question number following by the letter “R” – e.g., “Q5R”.

Index Variables: These variables are calculated as the mean of several variables measuring a specific concept – e.g., the economy or education. They therefore summarize a large amount of information in a single score. Index variables for the following are included in the dataset:

Community Attachment (CA)

Community Loyalty (LOYALTY)

Community Passion (PASSION)

Basic Services (BASIC_SERVICES)

Leadership (LEADERSHIP)

Education (EDUCATION)

Safety (SAFETY)

Aesthetics (AESTHETICS)

Economy (ECONOMY)

Social Offerings (SOCIAL_OFFERINGS)

Community Offerings (COMMUNITY_OFFERINGS)

Civic Involvement (INVOLVEMENT)

Openness (OPENNESS)

Social Capital (SOCIAL_CAPITAL)

Community Domains (DOMAINS)

The majority of index variables were calculated using the recoded (three-point) survey items. The two exceptions to this rule are community loyalty (LOYALTY) and community passion (PASSION), which were calculated using the original five-point scales.

Demographic Indicators: The dataset contains respondent demographic data for the following questions: sex, age, years lived in the community, job category, number of dependent children (childrens' ages--in categories), marital status, own or rent residence, income, ethnicity (Hispanic/not Hispanic), race, and number of residential telephone lines. These can be identified in the file with variable names beginning with QD distinction.

Geographic Indicators: Knight Communities were organized into 5 urbanicity groups for comparison purposes. The definition of urbanicity is that used by the US Census Bureau: the percentage of the population living in urban areas. The Census Bureau classifies as "urban" all territory, population, and housing units located within an urbanized area (UA) or an urban cluster (UC). It delineates UA and UC boundaries to encompass densely settled territory, which consists of: (a) core census block groups or blocks that have a population density of at least 1,000 people per square mile; and (b) surrounding census blocks that have an overall density of at least 500 people per square mile. In addition, under certain conditions, less densely settled territory may be part of each UA or UC. The Census Bureau's classification of "rural" consists of all territory, population, and housing units located outside of UAs and UCs. The rural component contains both place and non-place territory. Geographic entities, such as census tracts, counties, metropolitan areas, and the territory outside metropolitan areas, often are "split" between urban and rural territory, and the population and housing units they contain often are partly classified as urban and partly classified as rural.

The 5 urbanicity groups used in the Soul of the Community study are:

Very high urbanicity-very large population

Very high urbanicity-large population

Very high urbanicity-medium population

High urbanicity-medium population

Medium/low urbanicity-low population

The indicator in the dataset for these urbanicity groups is the variable URBAN_GROUP.

The dataset also contains an indicator for the principal city, where individual respondents are classified as either residing in the principal city or in the surrounding area (but still residing in the study area) based on ZIP code. This indicator is the variable CITY.

Weights and weighting: Each community survey was weighted to community-specific parameters for the following: age, sex, race, ethnicity (Hispanic/non-Hispanic) and education. These weights correct for non-response and non-coverage to create unbiased, representative results.

Two weight variables are included with the data: the survey weight (WEIGHT) and the projection weight (PROJWT). WEIGHT should be used when analyzing data from one community, comparing results (i.e., means, percentages) across two or more communities, or when conducting inferential statistical tests (i.e., significance testing). PROJWT should be used when analyzing results for a combination or aggregation of two or more communities: this weight place communities in the correct proportions to one another by projecting the results up to the total community population 18 years of age or older. This weight should never be used for inferential statistical tests, as it will produce incorrect results.

Below is the data dictionary from the SPSS data file:

Variable Information