The LIS data archive refers to the collection of databases created by, and made available through, LIS.
LIS generally uses database to mean a collection of harmonised microdatasets. LIS currently maintains two databases, the Luxembourg Income Study Database and the Luxembourg Wealth Study Database. See also Complementary Databases.
A dataset is a collection of microdata from a single country in a single year. LIS acquires datasets, mostly based on household surveys (e.g., the Swiss Income and Consumption Survey 2004, the French Household Budget Survey 2000, the Colombian Continuous Household Survey 2004) and harmonises them into a common template. All harmonisation is done ex post. LIS does not conduct surveys.
We use the term documentation to refer to our extensive collection of explanatory materials that provide information about, for example, the scope of the datasets included in the databases, characteristics of the original surveys, the rules of variable construction, variable availability across datasets, and features of the institutions that correspond to the tax and transfer variables. Some of the materials are applicable to an entire database, and some are specific to particular datasets.
We use the terms harmonisation and harmonise to refer to the general, overall process of preparing the datasets – according to the common template for either the LIS or LWS Databases –for the purposes of cross-national research. All harmonisation is done ex post. LIS does not conduct surveys.
When referring to specific variables, we use the term harmonised to refer to variables is which the overall content is the same across countries, but the variable categories vary by country.
See also standardised.
JSI, Job Submission Interface
Statistical queries may be made using a job submission interface (JSI) to facilitate queries. The JSI tracks the status of job requests in progress and retains a history of previous jobs sent.
The Luxembourg Income Study Database is known as LIS, pronounced: lĭs.
LIS vs. LIS
LIS (straight font) refers to the organisation, “LIS Cross-National Data Center in Luxembourg” as an organisation. LIS and Luxembourg Income Study, denoted by italics, refer to the Luxembourg Income Study Database.
LISSY is the name given to the remote-execution data access system that permits registered users to query the microdata while respecting the confidentiality restrictions imposed by certain countries. Queries to LISSY are made via a job submission interface or via email, using statistical code in SAS, SPSS, or Stata.
The Luxembourg Wealth Study Database is known as LWS, pronounced: lo͞os.
We use the term microdata to refer to data with records available at the household and/or person level. All datasets in the LIS and LWS databases contain microdata.
Microdata at LIS may be queried from anywhere in the world, via statistical queries sent through LISSY, our proprietary data access system. Direct access to the data, outside of the LIS office in Luxembourg, is never permitted.
Remote-execution allows the microdata to be queried while respecting privacy restrictions placed on the data. While the vast majority of statistical commands are permitted, commands that enable users to print individual records are disallowed.
We use the term standardised to refer to variables in which the variable categories are the same across all countries. See also harmonised.
Web Tabulator, Web Tab
The Web Tab is an application that allows users to design and generate cross-national descriptive tables based on the underlying LIS datasets without the need for programming.