Q. What do you mean by a data set? What format of data are you referring to?

A. A data set is a coded response to a questionnaire in format such as raw ASCII. For example, a questionnaire might ask if the respondent is female or male. Instead of entering the actual answer "female" or "male" into the dataset, the answers are coded: "female" might be represented as "1" and "male" as "2". When all the codes have been recorded, for all the questions, for everyone who answered the questionnaire, the dataset might look something like this:

10010862206112310000000057043011000000000000043000722116222112002001130020015837 10010862206000000000000000000000000002001002992929911191344000112524243400025837 10010862206044424200020041444449013421111000222111120023750702000000000200035837 10010862206012222112222122000000000112203120100005201582523200034000000000045837 10010862206002222221221222222222222222222222222222222222222002222222212222255837 10010862206002222222222221222222221222222000000000000000000000000000000000065837
A statistical software program such as SPSS or SAS is generally used to analyze the dataset (for example, to find out what percentage of respondents were male).

Q. What is the difference between a search engine, a directory (web guide), and a hybrid? Your reply would greatly be appreciated. Thanks.

A. A directory is a hierarchical listing of subject groupings for the information that is available through a particular web search page. A search engine is made up of an interface, a web "robot" or "spider," and a data base. The robot or spider are let loose to roam the WWW and collect web sites which are then put into a database. When an individual enters a query via the search interface, it is run against the database. A hybrid is just that, a combination of both of these options provided on one search page.

Q. What is a codebook? And how do I access it?

A. A codebook is a necessary companion to any dataset; codebooks help users interpret codes used in datasets by defining which codes have been used to represent which responses.

Codebooks for most of the studies within the DPLS Online Archive may be viewed online in .HTML format (prior to downloading). The codebook (or documentation) files may also be downloaded along with the data files.

Q. What is meant by the acronym F.T.P.?

FTP (File Transfer Protocol) is a utility for transferring files between computers, electronically. Most computer platforms (DOS, Unix, etc.) allow you to run FTP. The FTP option is generally found within the an accessories or internet communications folder or menu.

Steps include accessing the FTP program; accessing the remote host from which files are to be read or to which files are to be written; identifying and providing the user ID of the remote host; and entering a set of commands to access directories of local and remote hosts. Please refer to our FTP and Anonymous FTP Users' Guide for additional information.