Browse Proceedings

Numerous economists, analysts and bureaucrats now devote a large part of their time working with statistical summary data. Such data is produced from cross-tabulation or multi-level aggregation of unit-record or individual case data. When receiving ...

This paper identifies issues that are important to statisticians, namely, the need for a central query language and statistical database which can easily interact with a variety of systems and stand-along programs; discusses the requirements of a host ...

This paper proposes to add some facilities to a conventional database management system (DBMS) to support interactive survey analysis of statistical data. Data dictionaries were developed, derived statistical data is treated as regular data and summary ...

This paper describes the Genealogical Information System, GENISYS, developed for use by a project doing historical demography and medical genetics research. Project requirements and goals are presented and design and implementation decisions are ...

Statisticans and database designers have expended much effort to protect data from users [DiMillo 78, Denning 79]. It is also important to protect users from inaccurate data.

This paper describes an interactive database management system which interfaces with the International Mathematical and Statistical Libraries (IMSL) statistical package. The interface is transparent to the user and is designed to perform statistical ...

The GPI (Generalized Package Interface) strives to ease the task of the general user in applying programs against census and survey data. Specifically, the system addresses two design goals: 1) reducing the dependency of such generalized programming ...

Statistical analysis of large data sets often involves an initial data editing and preparation phase to check the validity of individual data items, check for consistency among related data, correct erroneous data, and supply (impute) values for missing ...

Data dictionary systems, such as the Table Producing Language (TPL) Descriptive Codebook system, provide a facility for separating the description of a data file from the use of the data. The benefits of this approach are well known. The TPL Associative ...

This paper describes the metadata facilities of the RAPID DBMS developed at Statistics Canada and contains a discussion of metadata in application systems.

Minitab is a general purpose, interactive, statistics package. Unlike most other statistics packages, Minitab stores data in main memory. This allows great flexibility in manipulating data. This paper describes data manipulation operations in Release ...

Several important data manipulation issues of statistical databases are discussed with respect to their treatment and implementation in SAS. The issues are: why aren't conventional database management systems used for statistical data; what data ...

Statistical calculations can take large amounts of time in a large database. Precomputed summary values may be stored to improve access speed, but they can only cover a small fraction of the great number of sets queriable. We suggest a compromise using ...

This paper considers a problem found in many statistical databases. In particular, we are interested in situations where different measurements are based on different partitionings of the same entity. In such a situation a statistical interpretation is ...

The Abe query language is described. Abe is a relational language designed to make easy the formulation of complicated statistical queries. Abe is similar to Zloof's Query-By-Example in that it makes use of the entire terminal screen. It is similar to ...

Integrated statistics, synthesized from many survey statistics, form an important part of government statistics. Its typical example is the System of National Accounts. To develop such a system, it is necessary to make consistent preparation of 1) ...