Page 266 - [Uma_Sekaran]_Research_methods_for_business__a_sk(BookZZ.org)

250 DATA COLLECTION METHODS

to respondents, who may use their own personal computers for responding to
the questions. These will, of course, be helpful only when the respondents know
how to use the computer and feel comfortable responding in this manner.
As stated earlier, CAPPA, which facilitates the preparation and administration
of questionnaires, is particularly useful for marketing research. The CAPPA sys-
tem includes 10 programs enabling the user to design a sophisticated computer-
ized questionnaire, computerize the data collection process, and analyze the data
collected. More reliable data are likely to result since the respondent can go back
and forth and easily change a response, and various on- and off-screen stimuli
are provided to sustain respondents’ interest.
A program is designed into the CAPPA system that checks for syntactical or
logical errors in the coding. Even as the survey is in progress, descriptive sum-
maries of the cumulative data can be obtained either on the screen or in printed
form. After data collection is complete, a data-editing program identifies missing
or out-of-range data (e.g., a 6 in response to a question on a 5-point scale). The
researcher can set the parameters for either deleting the missing responses where
there are too many, or computing the mean on other responses and substituting
this figure for the missing response. CAPPA also includes data analytic programs
such as cross-tabs, ANOVA, multiple regression, and others (discussed later in the
book). Randomization of questions and the weighting of respondents to ensure
more representative results (in cases where the sample either overrepresents or
underrepresents certain population groups—discussed later, in the chapter on
Sampling) are some of the attractive features of CAPPA.
Several programs are developed to administer questionnaires electronically. As
disks are inexpensive, mailing them across the country is no problem either. The
PC medium nonresponse rates may not be any higher than those of the mail
questionnaire response. With increase of computer literacy, we can expect elec-
tronic questionnaire administration to take on an increasing role in the future.
SPSS (Statistical Package for the Social Sciences) has several software programs
for research purposes including (1) SPSS Data Entry Builder for creating surveys that
can be administered over the web, phone, or mail; (2) SPSS Data Entry Enterprise
Server for entering the responses; and (3) SPSS 11.0 for data analysis and charts.
The advantages and disadvantages of personal or face-to-face interviews, tele-
phone interviews, personally administered questionnaires, mail questionnaires, and
questionnaires distributed through the electronic system are tabulated in Table 10.1.
It should be pointed out that information obtained from respondents either
through interviews or questionnaires, being self-report data, could be biased.
That is the reason why data should be collected from different sources and by
different methods, as discussed later.

PART III: OTHER METHODS OF DATA COLLECTION

Observational Surveys
Whereas interviews and questionnaires elicit responses from the subjects, it is
possible to gather data without asking questions of respondents. People can be