All Academic, Inc. Research Logo

Info/CitationFAQResearchAll Academic Inc.
Document

A Moderating Role of Channel Responsiveness in the Effects of Online Information Source
Unformatted Document Text:  10 Attrition The present study was a two-part study with three days interval. In part one, control variables including demographic variables were measured in a pre-manipulation survey. In part two, the main experiment was conducted and key outcome variables were measured in a post- manipulation survey. Since not all participants completed both parts of the study, we assessed whether any differences existed between those who completed both parts of the study and those who completed either part one or part two only. We first removed participants whose assignment of experimental condition was not recorded due to participants’ failure to provide their ID or computer error. We then removed participants who answered less than 80 percent in the pre- or post-manipulation survey because they deemed to be less responsive to the overall study than others. The resulting sample size was 234 for the pre-manipulation survey and 190 for the post-manipulation survey, with 131 participants completing both surveys. Informal interviews with students from the recruited classes revealed that many of them had already completed most of the available extra credit for the course and they believed that they only needed to complete one part of the study to fulfill their total requirement. Chi-square tests on demographic variables such as sex and ethnicity as well as a series of t-tests on pre-manipulation measures revealed that there was no significant difference between those who participated in both parts of the study and those who participated in part one only (see Table 1). A series of t-tests on the post-manipulation measures also indicated that responses of participants who completed both tests were comparable with responses of those who completed part two only (see Table 2). As we were assured of the comparability of our sample, we used two different samples for the analysis of our dependent variables. When a pre-manipulation measure was a significant covariate for a dependent variable, we used the sample of N = 131 (i.e., participants who completed both surveys). When no covariates were entered in the analysis, however, we used the sample of N = 190 (i.e., participants who completed part two only).

Authors: Kim, Hyojin. and Stephens, Keri.
first   previous   Page 10 of 34   next   last



background image
10
Attrition
The present study was a two-part study with three days interval. In part one, control
variables including demographic variables were measured in a pre-manipulation survey. In part
two, the main experiment was conducted and key outcome variables were measured in a post-
manipulation survey. Since not all participants completed both parts of the study, we assessed
whether any differences existed between those who completed both parts of the study and those
who completed either part one or part two only. We first removed participants whose
assignment of experimental condition was not recorded due to participants’ failure to provide
their ID or computer error. We then removed participants who answered less than 80 percent in
the pre- or post-manipulation survey because they deemed to be less responsive to the overall
study than others. The resulting sample size was 234 for the pre-manipulation survey and 190
for the post-manipulation survey, with 131 participants completing both surveys. Informal
interviews with students from the recruited classes revealed that many of them had already
completed most of the available extra credit for the course and they believed that they only
needed to complete one part of the study to fulfill their total requirement.
Chi-square tests on demographic variables such as sex and ethnicity as well as a series of
t-tests on pre-manipulation measures revealed that there was no significant difference between
those who participated in both parts of the study and those who participated in part one only (see
Table 1). A series of t-tests on the post-manipulation measures also indicated that responses of
participants who completed both tests were comparable with responses of those who completed
part two only (see Table 2). As we were assured of the comparability of our sample, we used
two different samples for the analysis of our dependent variables. When a pre-manipulation
measure was a significant covariate for a dependent variable, we used the sample of N = 131
(i.e., participants who completed both surveys). When no covariates were entered in the
analysis, however, we used the sample of N = 190 (i.e., participants who completed part two
only).


Convention
Need a solution for abstract management? All Academic can help! Contact us today to find out how our system can help your annual meeting.
Submission - Custom fields, multiple submission types, tracks, audio visual, multiple upload formats, automatic conversion to pdf.
Review - Peer Review, Bulk reviewer assignment, bulk emails, ranking, z-score statistics, and multiple worksheets!
Reports - Many standard and custom reports generated while you wait. Print programs with participant indexes, event grids, and more!
Scheduling - Flexible and convenient grid scheduling within rooms and buildings. Conflict checking and advanced filtering.
Communication - Bulk email tools to help your administrators send reminders and responses. Use form letters, a message center, and much more!
Management - Search tools, duplicate people management, editing tools, submission transfers, many tools to manage a variety of conference management headaches!
Click here for more information.

first   previous   Page 10 of 34   next   last

©2012 All Academic, Inc.