Adult Literacy in America - National Center for Education Statistics ...
Adult Literacy in America - National Center for Education Statistics ...
Adult Literacy in America - National Center for Education Statistics ...
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
124 ......Appendix A<br />
Response Rates<br />
Instrument <strong>National</strong> Prison<br />
Screener 89.1% N/A<br />
Background Questionnaire 81.0% 85.7%<br />
Exercise Booklet 95.8% 96.1%<br />
Data Collection Quality Control<br />
Several quality control procedures relat<strong>in</strong>g to data collection were used. These<br />
<strong>in</strong>cluded the <strong>in</strong>terviewer field edit, a complete edit of all documents by a tra<strong>in</strong>ed<br />
field editor, validation of 10 percent of each <strong>in</strong>terviewer’s close-out work, and<br />
field observation of both supervisors and <strong>in</strong>terviewers.<br />
At the <strong>in</strong>terviewer tra<strong>in</strong><strong>in</strong>g session, <strong>in</strong>terviewers were <strong>in</strong>structed on<br />
procedures <strong>for</strong> per<strong>for</strong>m<strong>in</strong>g a field edit of all data collection documents. The ma<strong>in</strong><br />
purpose of this edit was to catch and correct or expla<strong>in</strong> any errors or omissions <strong>in</strong><br />
record<strong>in</strong>g, to learn from mistakes so they were not repeated, and to remove stray<br />
marks and completely fill <strong>in</strong> bubbles on the documents that were to be optically<br />
scanned.<br />
Additionally, a complete edit was per<strong>for</strong>med on all documents by a tra<strong>in</strong>ed<br />
field editor. An item-by-item review was per<strong>for</strong>med on each document, and each<br />
error was fully documented on an edit <strong>for</strong>m. The supervisor reviewed the results<br />
of the edit with the <strong>in</strong>terviewer dur<strong>in</strong>g his or her weekly telephone conference.<br />
Validation is the quality control procedure used to verify that an <strong>in</strong>terview<br />
was conducted and it took place at the correct address and accord<strong>in</strong>g to specified<br />
procedures, or that nonresponse statuses (e.g., refusals, vacancies, language<br />
problems) were accurately reported by the <strong>in</strong>terviewers. Interviewers knew that<br />
their work would be validated but did not know to what extent or which cases. A<br />
10 percent subsample of dwell<strong>in</strong>g units were selected and flagged <strong>in</strong> the<br />
supervisor’s log and <strong>in</strong> the automated survey control system (ASCS). The<br />
supervisors per<strong>for</strong>med validation <strong>in</strong>terviews by telephone if a phone number was<br />
available. Otherwise, validation was per<strong>for</strong>med <strong>in</strong> person by the supervisor or<br />
by another <strong>in</strong>terviewer.<br />
Field observations of both supervisors and <strong>in</strong>terviewers were per<strong>for</strong>med<br />
by Westat field management staff. One purpose of the <strong>in</strong>terviewer observation<br />
was to provide home office staff with an opportunity to observe effectively both<br />
per<strong>for</strong>mance of field procedures and respondents’ reactions to the survey.<br />
Another purpose was to provide feedback to weak <strong>in</strong>terviewers when there was<br />
concern about their skills and/or per<strong>for</strong>mance. In addition to <strong>in</strong>-person<br />
observations, <strong>in</strong>terviewers were required to tape record one complete <strong>in</strong>terview