Koh Hwee Keng, Science Library

The Current Index to Statistics is an organisation sponsored jointly by the American Statistical Association (ASA) and the Institute of Mathematical Statistics (IMS). Under the direction of a management committee, the organisation produces an annual printed index to the statistical literature appearing in the previous year, and a cumulative database issued in electronic form. The 1997 edition of the Current Index to Statistics Extended Database (CIS/ED) contains approximately 28 MB of bibliographic information, including entries from volumes 1-22, covering the statistical literature published in 1975-1996. CIS/ED includes many pre-1975 journal articles not originally contained in the printed CIS.

The database is a command driven one. A list of commands can be obtained at any time by using Help.

How the program works

CIS/ED consists of a set of files containing the entries, as well as a set of index files, made up of tables of keywords and location of the records. Keywords indexed are those:

• Beginning with an alphabetic character
• Followed by a numeral, punctuation mark or blank space
• Contain at least two characters and less than six characters

Words in the database exceeding 6 characters are truncated to 6 characters for the purpose of indexing. Hence the words regress, regression, regressor are all considered instances of the index word regres. Upper and lower case are considered equivalent. Common words such as of, by, and are not indexed.

The author, title, keyword and alternative spelling fields of the records are indexed.

A search looks up one or more keywords in the index files, and uses the list of CIS/ED entries found to construct a new search result containing all the entries that match the keyword criteria. This search results can be refined by adding additional constraints or combining with an earlier search result.

CIS/ED operates on a stack of search results (similar to calculators that used reverse Polish notation). Each new search command creates a new search result which becomes the main records (topmost search results) on the stack. All previous results become the backup records and are pushed down onto the stack in the order they were created.

The search refinement commands do not operate on the database as a whole, but only on the subset of records contained in the main records file. Each command that operates on the main results files leaves the results in the main records, and the previous result goes to the backup records.

CIS/ED creates a stack of search results, with 2 visible elements, main results and backup results. This stack can be manipulated with these commands:

push

move forward one search step

pop

move backward one search step

swap

interchange main and backup search

stack

give status report of all files in the stack

Search example

To find all indexed works by Paul Switzer, without co-authors and excluding reviews.

=>	search switzer [40 records / 0 backup records]
=>	author switzer (which gets rid of Switzerland) [34 (of 40) records meet criteria] [34 main records / 40 backup records]
=>	noauth (rev) (which removes reviews written by Switzer) [28 main records / 34 backup records]
=>	noauth ; (which removes all multi-authored works) [14 (of 28) records meet criteria] [14 main records / 28 backup records]
=>	author "Switzer, P" (which verifies that the author field has Switzer as last name and P as given name) [14 main records / 14 backup records]
=>	list (to view the records)

Type quit followed by clear to exit current program and erase all search results.

How to interpret records

A record of a journal article is illustrated below:

The four common fields that are usually displayed in the record are:

Field 1: Location contains information on the year of publication, source and location or size of the item indexed. Several different formats are used, depending on the type of publication being referenced. E.g. 88MathGeo 20 49-61 J gives Year, Journal abbreviation, Volume, Pages, Type of publication.

Type of Publication Codes

B

Book

J

Article in journal or other periodical (not electronic)

P

Article in proceedings or edited book

C

Computer-readable database, software, etc.

E

Article or entry in electronic journal or periodical

Z

Administrative record (no bibliographic information)

D

Dissertations (not used in 1997)

T

Technical reports (not used in 1997)

Field 2: Title shows the title of the indexed item as it appeared in the source. When non-English titles are translated into English, the name of the original language is given in parentheses.

Field 3: Author contains authors' names spelt as shown in the source, except to correct confirmed typographical errors in the source. Multiple authors are separated by semicolons. Different formats are used for corporate or institutional authors and individuals.

Field 4: Keywords and phrases contains edited versions of keywords published in the source or they may have been prepared by a CIS/ED editor.

Hints for searching

Consider starting with a search that will retrieve too much and find ways to trim the results to what you want. This is easier than retrieving too little and needing to figure out how to expand the inadequate result.

CIS/ED includes abstracts and book reviews from the following journals beginning with the publication years given in parentheses.

• The American statistician (1996)
• Journal of agricultural, biological and environmental statistics (1996)
• Journal of the American Statistical Association (1996)
• Journal of business and economic statistics (1996)
• Journal of computational and graphical statistics (1992)
• Journal of statistics education (1993)
• Technometrics (1996)

CIS/ED is available from the Science Library Information Desk.