{ "culture": "en-US", "name": "", "guid": "", "catalogPath": "", "snippet": "The Social Vulnerability Index (SOVI) was added to the Virginia 2019 Tiger/Line Block Groups downloaded from the U.S. Census Bureau.", "description": "

Following other social vulnerability indexes, including the SoVI® developed by the Hazards & Vulnerability Research Institute at the University of South Carolina, this vulnerability index is based on a principal component analysis (PCA). PCA is a statistical technique that takes as its input a matrix of interrelated socioeconomic variables \u2013 in this case those considered to measure various dimensions of social vulnerability \u2013 and creates a new set of orthogonal principal components that extract the important variation the underlying input data while reducing the noise and redundancy in the data. After conducting the PCA, the researcher combines the newly created component variables into a composite index that provides a single value for each observation in the dataset, in this case a social vulnerability score. The utility of a PCA-based index is that it encapsulates a lot of information in an easily consumed form and individual observations can be ranked relative to each other. <\/SPAN><\/P>

This update uses data from the 2015-2019 American Community Survey at the census block group level where available and at the census tract level where block group data is not available. It is an update of the Social Vulnerability Index on the Adapt VA Portal and uses the same or similar variables to the ones used in that analysis. These variables, shown in the next table, are those that we consider to be the most direct determinants of social vulnerability. <\/SPAN><\/P>

Variable<\/SPAN><\/P><\/TD>

Description<\/SPAN><\/P><\/TD>

Block Group or Tract Level<\/SPAN><\/P><\/TD><\/TR>

Income<\/SPAN><\/P><\/TD>

Per capita income <\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Black<\/SPAN><\/P><\/TD>

Percent of population that is Black or African American<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Hispanic<\/SPAN><\/P><\/TD>

Percent of population that is Hispanic<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Native<\/SPAN><\/P><\/TD>

Percent of population that is Native American<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Over 65<\/SPAN><\/P><\/TD>

Percent of population that is over 65 years of age<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Unemployed<\/SPAN><\/P><\/TD>

Percent of civilian labor force 16 and over that is unemployed<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Poverty<\/SPAN><\/P><\/TD>

Percent of population for whom poverty status is established that is living in poverty<\/SPAN><\/P><\/TD>

Tract<\/SPAN><\/P><\/TD><\/TR>

No High School<\/SPAN><\/P><\/TD>

Percent of population 25 and older with no high school degree or equivalent<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Group Quarters<\/SPAN><\/P><\/TD>

Percent of population in group quarters including nursing homes and prisons<\/SPAN><\/P><\/TD>

Tract<\/SPAN><\/P><\/TD><\/TR>

Female Labor Force<\/SPAN><\/P><\/TD>

Percent of females 16 and over in civilian labor force<\/SPAN><\/P><\/TD>

Tract<\/SPAN><\/P><\/TD><\/TR>

Female Households<\/SPAN><\/P><\/TD>

Percent of households with female head, no spouse<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR>

Social Security<\/SPAN><\/P><\/TD>

Percent of households with social security income<\/SPAN><\/P><\/TD>

Block Group<\/SPAN><\/P><\/TD><\/TR><\/TBODY><\/TABLE>

Before conducting the PCA, the variables were first standardized to z-scores with zero means and unit variances to avoid any confounding effects that might arise from using variables of different magnitudes in the analysis. We then conducted a PCA, keeping those components with eigenvalues greater than 1 (the Kaiser selection criterion). As a next step, we conducted a Varimax rotation of the components to facilitate interpretation of each component because \u2013 as is the case with all PCA-based indices \u2013 the researcher must determine the directionality of each retained component, that is whether higher values of the component increase the level of social vulnerability (positive directionality) or decrease the level of social vulnerability (negative directionality). Where the directionality of the component was clearly negative, we scaled the component by a factor of -1 before including it in the composite index so that higher values of the scaledcomponent would increase the overall vulnerability index. As is common in the literature, in instances when the effect of the component on vulnerability is ambiguous (as is the case when the different variables that make up the component work in opposite ways), we assume a positive directionality. Each component is then multiplied by the variance it captures from the total input matrix and the weighted components are added together to form the index. To ensure that the index can be compared to other indices, the resulting aggregated values to z-scores with zero means and unit variances. Since all values of the index are relative, it can be used to rank observations relative to each other in terms of vulnerability. However, many studies also identify a group of \u201chighly vulnerable\u201d observations \u2013 that is those observations whose standardized index score exceeds a threshold value of 1 (i.e., whose value is one standard deviation above the mean value of the index). We note that vulnerability indices depend on the variables included in the PCA as well as the geographic area of the study and the component selection and weighting criteria. Thus our vulnerability index will not necessarily match the vulnerability indices created by other researchers.<\/SPAN><\/P>

<\/P>

<\/P>

The TIGER/Line shapefiles and related database files (.dbf) are an extract of selected geographic and cartographic information from the U.S. Census Bureau's Master Address File / Topologically Integrated Geographic Encoding and Referencing (MAF/TIGER) Database (MTDB). The MTDB represents a seamless national file with no overlaps or gaps between parts, however, each TIGER/Line shapefile is designed to stand alone as an independent data set, or they can be combined to cover the entire nation.<\/SPAN><\/P>

Block Groups (BGs) are clusters of blocks within the same census tract. Each census tract contains at least one BG, and BGs are uniquely numbered within census tracts. BGs have a valid code range of 0 through 9. BGs have the same first digit of their 4-digit census block number from the same decennial census. For example, tabulation blocks numbered 5001, 5002, 5005,.., 5999 within census tract 1210.02 are also within BG 5 within that census tract. BGs coded 0 are intended to only include water area, no land area, and they are generally in territorial seas, coastal water, and Great Lakes water areas. Block groups generally contain between 600 and 5,000 people. A BG usually covers a contiguous area but never crosses county or census tract boundaries. They may, however, cross the boundaries of other geographic entities like county subdivisions, places, urban areas, voting districts, congressional districts, and American Indian / Alaska Native / Native Hawaiian areas. <\/SPAN><\/P>

<\/P><\/DIV><\/DIV><\/DIV>", "summary": "The Social Vulnerability Index (SOVI) was added to the Virginia 2019 Tiger/Line Block Groups downloaded from the U.S. Census Bureau.", "title": "SocialVulnerabilityIndex_SOVI_updatedAug2021_Selected_ERWtrshd_wm", "tags": [ "Virginia", "US Census Bureau", "Block Groups", "Coastal Virginia", "Social Vulnerability Index SOVI" ], "type": "", "typeKeywords": [], "thumbnail": "", "url": "", "minScale": 150000000, "maxScale": 5000, "spatialReference": "", "accessInformation": "U.S. Census Bureau, 2015-2019 American Community Survey", "licenseInfo": "

Use Constraints:The TIGER/Line Shapefile products are not copyrighted however TIGER/Line and Census TIGER are registered trademarks of the U.S. Census Bureau. These products are free to use in a product or publication, however acknowledgement must be given to the U.S. Census Bureau as the source.<\/SPAN><\/P>

The boundary information in the TIGER/Line Shapefiles are for statistical data collection and tabulation purposes only; their depiction and designation for statistical purposes does not constitute a determination of jurisdictional authority or rights of ownership or entitlement and they are not legal land descriptions.Coordinates in the TIGER/Line shapefiles have six implied decimal places, but the positional accuracy of these coordinates is not as great as the six decimal places suggest.<\/SPAN><\/P><\/DIV><\/DIV><\/DIV>", "portalUrl": "" }