The Short Drinks sample
The Short Drinks sample is supplied in two formats:
▪A backup of a SQL Server relational MR database. The backup file is called
short_drinks_backup and by default it is in the
[INSTALL_FOLDER]\IBM\SPSS\DataCollection\7\DDL\Data\Rdb folder. For step-by-step instructions on restoring the backed-up database, see
Restoring the Short Drinks sample database.
▪A UNICOM Intelligence Data File called short_drinks.ddf, which by default is in the [INSTALL_FOLDER]\IBM\SPSS\DataCollection\7\DDL\Data\Data Collection File\ folder.
Both formats contain case data that was collected using UNICOM Intelligence Interviewer 1.2. Both samples also include a UNICOM Intelligence metadata document file called short_drinks.mdd, which was originally created in Quanquest 1.3 and is suitable for use in UNICOM Intelligence Interviewer - Paper. All texts are available in English and Spanish.
The short_drinks.mdd file contains the following metadata versions:
▪Version 1. This was created when the UNICOM Intelligence Interviewer project was activated in test mode. Five cases were collected using this version. A paper representation of the questionnaire is included with the samples: see short_drinks_v1.doc.
▪Version 2. This was created when the UNICOM Intelligence Interviewer project was first activated in live mode. 45 cases were collected using this version. There were no significant changes in this version.
▪Version 3. A category (Fulltime parent) was added to Q3 (sclass). 24 cases were collected using this version.
▪Version 4. A category was deleted from Q4 (hhsize) and the text on another category in this question was changed. 20 cases were collected using this version.
▪Version 5. The text of one category in Q7 (numdrksz) was changed and the categorical Q3 (sclass) was replaced with an open-ended question (occup). 27 cases were collected using this version. A paper representation of the questionnaire is included with the samples: see short_drinks_v5.doc.
▪Version 6. New system variables were added to support 5.6 features.
Note that the data is dirty and includes time-outs and test data.
See also