Data Quality and Consistency Issues Flashcards
What are some quality issues with the census?
− Under-enumeration
− Misreporting of information – e.g. health is self reported so v subjective
− Methods used to avoid risk of disclosure
What are some quality issues with Geographic Data?
− Accuracy of the boundaries
− GPS not giving accurate readings
− When no metadata available
− When images scanned or digitised
− When digital data is transformed e.g. vector to raster
− Datasets held by different organisations that don’t match
− Errors in data (e.g. polygons that don’t join up)
Name the three main issues with data consistency.
− Consistency over time when comparing data from the same source
− Consistency between different datasets measuring the same variable
− Temporal inconsistency due to: Changing spatial units, Changing definitions of variables and Changing classification systems
What is the National Geographic (2005) definition of migration?
“Migration (human) is the movement of people from one place in the world to another for the purpose of taking up permanent or semi-permanent residence, usually across a political boundary.”
What is the ONS procedure for estimating immigration?
Uses a variety of data sources;
Censuses (Only every 10 years)
Surveys (Not many people complete them so inconsistent and have poor geographical detail)
Administrative datasets (Narrow data capture)
Name the benefits of using the National Insurance Number registrations for Immigration data
\+ Comprehensive geographical coverage \+ Residential postcode captured \+ Compulsory process (for those in work) \+ Continuous data capture \+ Country of origin and age information
Name the problems of using the National Insurance Number registrations for Immigration data
− Only migrants aged 16+, planning to work or claim benefits are covered (excludes students, dependents and those not working)
− There may be a delay between arrival and registration
− Data reflect migrant’s location at registration, they do not reflect the stock of migrants nationally or where they may settle
− No information on outflows is available (no de-registration)
Name the benefits of using the Higher Education Statistics Agency for Immigration data
+ Comprehensive coverage of international students
+ All higher education establishments
+ Length of study provided
+ Continuous data capture
Name the problems of using the Higher Education Statistics Agency for Immigration data
− Students only
− Institution-based not residence-based
− Some universities are split sites
Name the benefits of using the Workers registration scheme for Immigration data
+ Continuous data capture
+ Full geographical detail
+ Data on origin, occupation and age
Name the problems of using the Workers registration scheme for Immigration data
− A8 migrants only, voluntary registration
− Excludes self-employed
− Register by employer not employee residence
− Temporary scheme?
− No length of stay information
Name the benefits of using GP Registrations (Flag 4) for Immigration data
+ Full geographical detail
+ Data on age
+ Real Time
Name the problems of using GP Registrations (Flag 4) for Immigration data
− No information on delay between arrival and registration
− No information on patients who leave the UK
− Some migrants may not register for GP services at all
− Internal migration not recorded
− Age and gender are only data recorded
What is the Local Migration Indicators database?
The Office for National Statistics database of international migration data that provides data at region and district level
