 |
CHRRDBA - DOS
13 Dec 98
When the file specified in the Save File box is valid and the function "Perform an Extract" is activated from the Main Menu screen in Figure 4.1, the screen shown in Figure 6.1 will appear. From this screen the user may finalize the data file to be extracted in several ways:
| |
| Figure 6.1 Perform an Extract: Main Screen |
6.1 Specifying the Sample Size
The Sample Specification box allows the user to manipulate the size of the sample universe by combining four methods.
Each method is discussed in a section below. 6.1.1 Boolean QualificationWhen Construct a Boolean specification is activated from the Sample Selection box in Figure 6.0, the screen shown in Figure 6.3 appears in which a Boolean phrase can be constructed to manipulate the sample universe and perform operations on the variables in the extract file that are listed in the right column. Rules of algebraic syntax such as balanced parentheses must be followed. The maximum length of the Boolean string allowed is 255 characters.
If violations of syntax or length occur, an error message will be displayed.
| |
| Figure 6.3 Boolean Qualification |
The Case Selection Criterion box is where the Boolean phrase will appear as it is being constructed.
The Elements box includes Boolean and arithmetic operators, constants, and variables.
The Variables box contains the variables selected in the extract specifications file.
The Title of the highlighted variable is displayed on the bottom line fo the screen.
6.1.1.1 Boolean Edit Box
In Figure 6.4 the Boolean phrase as it is being constructed will appear in the Case Selection Criterion box. To construct a Boolean phrase, use the function keys shown in the function key menu at the bottom of the screen.
To edit the Boolean
Place the cursor in the Case Selection Criterion box where the typing will occur, click to activate the text cursor, and type in the edit. You may also construct portions of the Boolean phrase by typing the phrase in the box.
| |
| Figure 6.4 The Boolean Phrase |
Figure 6.4 shows a simple Boolean phrase. in which the variable R0273200 must be greater than 10, AND R0273300 must be greater than 20 for a case to be considered.
Supplying the "titles" of the variables, this translates as: "the number of weeks worked in the past year" (R0273200) must be greater than 10 AND the "number of hours worked per week usually worked during the weeks worked in the past year" (R0273300) must be greater than 20 for a case to be selected.
Other criteria explained below may further limit case selection.
When the operation Select 1 of every 1 case(s) is highlighted, the number of cases for the extract may be altered. A fraction of the cases may be specified by changing the denominator of cases, i.e., 1/1, 1/2, 1/4, 1/10, 1/20, 1/50, or 1/100.
| |
| Figure 6.5 Selecting the Number of Cases |
To change the fraction, make sure the Select 1 of every 1 case(s) operation is highlighted, and use
TIP
|
Instead of always beginning with the first case in the file as the reference point from which the file is constructed, the First case to read can be changed.
To change the first case read,
| |
| Figure 6.6 First Case to Read |
After <Enter> has been pressed, the cursor will blink next to the number 1 in the line.
After <Enter> has been pressed the screen will resemble Figure 6.6, and changes in the universe will be reflected in the Extract File Information box.
Like the First Case to Read, the Last Case to Read may also be changed.
To change the last case to read,
| |
| Figure 6.7 Last Case to Read |
After <Enter> is pressed, the cursor will blink next to the number, e.g., 5034, in the line.
After <Enter> is pressed the screen will resemble Figure 6.7, and changes in the universe will be reflected in the Extract File Information box.
6.2 File Type Specification
Output file specifications may be changed in the File Type Specification box. Each specification listed in this box excludes all others. That means that if one specification is toggled ‘YES,’ all the others will automatically be toggled to ‘NO.’ All specifications may, however, be toggled to ‘NO.’
| |
| Figure 6.8 Changing the Output File Specifications |
To toggle a desired specification to ‘Yes’,
To toggle a desired specification to ‘No,’
The following file formats are available in the File Type Specifications box for various statistical packages.
Note: The SASS and SPSS control statements generated include basic data location, label and missing value information. While every attempt has been made to provide "ready-to-use" statements, the platform and version of your specific installation may require modification of these generic control programs. Please consult your local SPSS or SAS coordinator for site-specific problems.
Two actions may be carried out on the extracted file:
| |
| Figure 6.9 Actions to be Executed on the File |
Optionally, all processing may be abandoned and the user may exit this screen.
To perform any of these actions,
6.3.1 Run the Extract
The action 'Run the Extract' will execute the extract specifications that were defined on this menu. Carefully read the screen to assure that all selected specifications are correct. When they are correct, in the Actions box,
| |
| Figure 6.10 Extract of "Weeks/Hours Worked" In-progress" |
Figure 6.10 shows the extract operation in-progress as it runs on the Boolean phrase constructed in Figure 6.4.
Information about its progress appear at the bottom of the screen in the Record Counter box. More information will appear on the screen as the extract is completed. Read it carefully to continue.
The NLSY79 is a 2-CD set. When making an NLSY79 extract, you will be prompted to 'Insert CD Number 2' at the appropriate time. Upon completion of reading the data on CD number 2, you will be prompted to reinsert CD number 1.
TIP
|
| |
| Figure 6.11 Results of Extract" |
Summary information on the extract run will appear at the end of processing in the Extract Summary box. This information includes the resulting number of
The final event, e.g., FINISHED will also appear. Instructions will tell the user what to do. If there are errors, error messages will appear and tell the user what to do.
Follow the instructions, e.g., "Press <Esc> to continue..."
After <Esc> has been pressed, the user will be returned to the Actions box to carry out further actions or revise sample specifications. In addition, a message box at the bottom of the screen will appear that specifies the name of the the document file (e.g., DEMO-2.DOC) that was created to accompany the data extract file.
| |
| Figure 6.12 Document File Created Message |
When this option is selected and <Enter> is pressed, no window appears on the screen. A codebook file is created and placed in the output directory specified in the initial startup screen. This file contains a codebook representation of the variables in the file specified in the Save Box. The name of this codebook file is the same file name as specified in the Save File box with a "cdb" extension, e.g., [filename].CDB.
NOTE: This codebook file should not be confused with the complete codebook file created when using the Print Documentation function on the Main Menu screen shown in Figure 6.18. The file name of the complete codebook will be specified at the time of creation; see Figure 6.19.
When the Exit option is selected and <Enter> is pressed, the user is returned to the Main Menu screen shown in Figure 4.1.
Below is a complete list of files that can be produced when the Perform an Extract option is chosen from the Main Menu. This list includes the extract specification file that depends on the data set used, and the accompanying documentary files that may be specified as output. The asterisk (*) below represents the file name that was specified in the Save File box.
Extract file types depending on the dataset used,
| *.MSR | a.k.a. Older Men, Men 45-59 in 1966 extract specification file used to store variables. |
| *.BSR | a.k.a. Boys, a.k.a. Young Men, Men 14-24 in 1966, extract specification file used to store variables. |
| *.WSR | a.k.a. Women, a.k.a. Mature Women, Women 30-44 in 1967 extract specification file used to store variables. |
| *.GSR | a.k.a. Girls, a.k.a. Young Women, Women 14-24 in 1968 extract specification file used to store variables. |
| *.YSR | a.k.a. Youth, a.k.a. NLSY79, Youth 1979-1994 extract specification file used to store variables. |
| *.CYA | a.k.a. Child, a.k.a. Children of the NLSY, Children 1986-1994 extract specification file used to store variables. |
| *.RSR | NLSY97 |
Documentary files produced,
| *.CDB | Codebook file, one page per variable in the master extract specification file. |
| *.DAT | Raw data file produced as a result of the "perform an extract function" on a sample universe of variables from the extract specification file. |
| *.DCT | Stata Dictionary file that can be used to read data into Stata software. |
| *.DOC | Documentation file produced to accompany the data file. |
|
*.SAS and/or *.SAS | and/or SPSS control statements. These read the extracted *.DAT or the *.SPS binary file depending on the selection in "File Type Specification." |
| *.DBF | A dBase 3 compatible file. |
| [PRINTFILE] | A documentation file specified, named, and produced on the current database as a result of the "Print Documentation" function, see Figure 6.19. |
E-mail: editor
