All Academic, Inc. Research Logo

Info/CitationFAQResearchAll Academic Inc.
Document

An Invisible Leverage in the Adoption of Online Social Support Community
Unformatted Document Text:  Running Head: Invisible Leverage in Adoption of Online Social Support Community 16 mental illness communities remained as a final sample 3 , which exceeds the optimal sample size of 83 by Cohen (1977)’s power analysis 4 Data collection The present study took full advantage of the digitized nature of the data. First, each OSSC’s posting list was converted into an excel file. The list includes posting ID number, poster’s name and/or poster’s yahoo ID, and posting date. 5 Each list was sorted by name or yahoo ID to determine whether one poster used multiple names or yahoo IDs. If such case was found, multiple names or yahoo IDs were changed into one single name or yahoo ID so that the poster would not be counted as multiple posters. 6 Second, each converted posting list was transformed into a pivot table in order to automatically count the posting frequency and locate the initial and the last posting dates for each poster. 7 Third, an excel programming was executed to automatically identify whether each poster was an adopter or a one-time poster, to recognize who is the major contributor, and to count the frequency and duration of each poster. Postings by September 15, 2002 were included. Three trained coders collected the data from September 16, 2002 to October 15, 2002. Since all variables were manifest, and collected through a computerized procedure as described above, the researchers concluded no need for inter-coder reliability. Data Analysis Three statistical analysis techniques were employed to test the hypotheses: t-test (Hypothesis 1), curvilinear regression (Hypotheses 2, 3, and 4), and third-order polynomial 3 Detailed steps are provided in Appendix A. 4 According to Cohen, 83 was the optimal sample size for a curvilinear regression analysis with three predictors (three different measures of network size) for a medium power (.80) and a medium effect size (.15) using the significance criterion of a=.05. L=10.90, f 2 = .15, u=3, w=6. N = L/ f 2 + u + w + 1= 73 + 3 + 6 + 1 = 83. The polynomial power used was 3 instead of 2 just in case that a cubic rather than quadratic relationship would be found between a predictor and a dependent variable. 5 The list also provides title of posting and size of posting. 6 Such cases were easily detected because most posters used their own names or initials instead of pseudonyms. This may reflect the nature of communities under study. That is, posters in illness communities may not need fashion their identities as posters in entertainment-oriented communities such as game or movie. 7 Three excel functions were used to transform posting lists into pivot tables; sort, text to columns, and pivot table. Detailed steps are provided in Appendix B.

Authors: Yun, Haejin., Park, Songyi. and Kim, Hee-Jung.
first   previous   Page 16 of 37   next   last



background image
Running Head: Invisible Leverage in Adoption of Online Social Support Community
16
mental illness communities remained as a final sample
3
, which exceeds the optimal sample size
of 83 by Cohen (1977)’s power analysis
4
Data collection
The present study took full advantage of the digitized nature of the data. First, each
OSSC’s posting list was converted into an excel file. The list includes posting ID number,
poster’s name and/or poster’s yahoo ID, and posting date.
5
Each list was sorted by name or
yahoo ID to determine whether one poster used multiple names or yahoo IDs. If such case was
found, multiple names or yahoo IDs were changed into one single name or yahoo ID so that the
poster would not be counted as multiple posters.
6
Second, each converted posting list was
transformed into a pivot table in order to automatically count the posting frequency and locate
the initial and the last posting dates for each poster.
7
Third, an excel programming was executed
to automatically identify whether each poster was an adopter or a one-time poster, to recognize
who is the major contributor, and to count the frequency and duration of each poster. Postings
by September 15, 2002 were included.
Three trained coders collected the data from September 16, 2002 to October 15, 2002.
Since all variables were manifest, and collected through a computerized procedure as described
above, the researchers concluded no need for inter-coder reliability.
Data Analysis
Three statistical analysis techniques were employed to test the hypotheses: t-test
(Hypothesis 1), curvilinear regression (Hypotheses 2, 3, and 4), and third-order polynomial
3
Detailed steps are provided in Appendix A.
4
According to Cohen, 83 was the optimal sample size for a curvilinear regression analysis with three predictors
(three different measures of network size) for a medium power (.80) and a medium effect size (.15) using the
significance criterion of a=.05. L=10.90, f
2
= .15, u=3, w=6. N = L/ f
2
+ u + w + 1= 73 + 3 + 6 + 1 = 83. The
polynomial power used was 3 instead of 2 just in case that a cubic rather than quadratic relationship would be found
between a predictor and a dependent variable.
5
The list also provides title of posting and size of posting.
6
Such cases were easily detected because most posters used their own names or initials instead of pseudonyms.
This may reflect the nature of communities under study. That is, posters in illness communities may not need
fashion their identities as posters in entertainment-oriented communities such as game or movie.
7
Three excel functions were used to transform posting lists into pivot tables; sort, text to columns, and pivot table.
Detailed steps are provided in Appendix B.


Convention
All Academic Convention makes running your annual conference simple and cost effective. It is your online solution for abstract management, peer review, and scheduling for your annual meeting or convention.
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 16 of 37   next   last

©2012 All Academic, Inc.