A. Process in Collecting Data: Train The Data Collectors

Module 3
Data Collection
A. Process in Collecting Data

Data Collection involves the collective actions that field a measurement instrument. The following task are included:
1. Train the data collectors.
2. Determine the data collection timeline.
3. Determine and implement an instrument disposition process.
4. Invite the chosen participants.
5. Activate the survey.
6. Remind the participant to complete the survey and return the instrument.
7. Enter the data.
Train the Data Collectors

Training is a critical step if the measurement instrument is complex or the interviewer has some latitude in selecting
participants. Knowing how to follow skip directions and other instructions is crucial to data quality. Interviewers are also
trained in approaching prospective participants and minimizing bias, including word emphasis, facial expression, use of
response aids, etc. Making sure the interviewer knows how to submit the completed measurement instrument is usually also
part of the training.
Determine the Data Collection Timeline

While your research study has a timeline, your actual data collection needs its own timeline. At minimum, it needs to include
the survey activation dates and times, when data entry starts and is expected to finish, when data editing starts and finishes,
and when the clean data files is ready. It may also include dates and times for training of data collectors when phone and
personal interviewers are used.
Determine and Implement Instrument Disposition

Completed measurement instruments are of little value unless they are returned. Instrument disposition refers to the
procedure(s) by which the completed instrument is returned to the researcher.
Invite the Chosen Participants

The invitation is critical to gaining cooperation and it is the first step of building rapport with the participant. Regardless of
the mode by which the survey is conducted, participants may be invited by phone, email, or mail. Participants may also be
prescreened as part of this invitation process. Preparing the screen questions and preparing the invitation script, email, or
letter are part of the data collection process.
Activate the Survey

The researcher must determine when the instrument is ready to launch. Survey activation is the decision that launches the
survey; it indicates the researcher has addressed all known measurement instrument problems, and the process is as error-free
as he or she can make it.
Remind the Participants
Participants are busy people. They have lives, and participating in research is not a top priority for most of them. Recognizing
this, a researcher can dramatically increase the study’s response rate by reminding participants if measurement instruments
are not submitted or retuned. Reminders often use email or phone contact.
Enter the Data

Data entry converts data gathered by secondary or primary methods into a medium for data viewing and manipulation. Once
data for a particular study is entered, it creates a data file.
What is data fields, records, files and databases?

Data fields represent variable (e.g. a participants’ responses to one measurement question). It can contain numbers, words,
images, etc.
Data record is a set of data fields from case (all a participant’s responses to all measurement questions). It represents rows in
a data file.
Data files are the responses of all participants in a single study.
Databases comprise of one or more data files that are interrelated (e.g. all employee surveys collected quarterly for the past
10 years).
Example:
Each row is a data record. Each column is a variable. In this data file, questions, 1, 3, and 5 are nominal variables that have
two response categories. Questions 6 uses multiple columns because it is a multi-item rating question using 1-to-5 scale; each
item is a variable so, each needs its own column. Each participant is assigned an identification number (CaseID). After a
descriptive statistical summary (above example) reveals odd value codes or missing data, you can use a CaseID to locate an
original measurement instrument to clean a data file.
Critical to accurate data entry, as well as data preparation and data analysis, is a coding scheme. A coding scheme
(codebook), contains each variable in a study and specifies the application of mapping rules to response codes of each
variable. Pretesting of an instrument provides sufficient information about the variable to test a coding scheme. A preliminary
scheme used with pretesting data may reveal coding problems that will need to be corrected before the data for the final study
are collected and processed. In many statistical programs, the coding scheme is integral to setting up the data file before the
data is entered. Most scheme contain the variable identification number (ID), variable name and level, location of the
variable’s code in the data record (a column designation), response option codes and labels, and type of variable (which
determines its possible statistical procedures).
Example:
Note: This coding scheme was created in excel, other statistical packages (SPSS) may also be used.
Keyboarding remains a mainstay for a researchers who need to create a dataset immediately and store it in a minimal space
on a variety of media. It can be a slow, exacting process to enter hundreds of variables for each of thousands instruments and
to do it correctly. However, researchers have profited from more efficient ways to for not only speeding up the data entry
process, but also increasing the accuracy:
Participant entry of data through online or mobile surveys
Barcode, optical character and mark recognition for paper surveys
Voice recognition for phone surveys
Electronic tablet use by intercept interviewers
Database programs, including spreadsheets and statistical analysis packages, serve as valuable data-entry devices.
Practice what you have learned
Suppose you are encoding the responses of the participants is a research study about the extent of satisfaction brought by
mobile baking. There are 15 respondents in your survey that contains 10 questions measuring the satisfaction brought by
mobile banking. The research instrument also includes; gender with options; male, female or prefer not to say; civil status
with options; single, married, widowed or separated; residence with options; town or barrio; age; no. of years in using mobile
banking. And if the researcher used a likert scale such as follows; (5 – Excellent, 4 – Good, 3 – Average, 2 – Poor, 1 – Very
Poor), for the questionnaire, construct a coding scheme for this research.

A. Process in Collecting Data: Train The Data Collectors

Uploaded by

Copyright:

Available Formats

A. Process in Collecting Data: Train The Data Collectors

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

A. Process in Collecting Data: Train The Data Collectors

Uploaded by

Copyright:

Available Formats

Module 3

A. Process in Collecting Data

Train the Data Collectors

Determine the Data Collection Timeline

Determine and Implement Instrument Disposition

Invite the Chosen Participants

Activate the Survey

Enter the Data

What is data fields, records, files and databases?

You might also like