All Academic, Inc. Research Logo

Info/CitationFAQResearchAll Academic Inc.
Document

Gay Marriage and Civil Unions: The Impact of Network Diversity on Opinion
Unformatted Document Text:  11 were more likely to prefer no recognition to some recognition, and those that support some recognition are more likely to prefer civil unions. On the other hand, higher income appears to be associated with greater support for civil unions versus no recognition, but income also appears to reduce support for marriage versus civil unions. That is to say, higher income may increase the probability of supporting some recognition, but the increased support is more likely to be towards civil unions, not marriage. Though the initial findings are interesting, the interpretation of the multinomial logit results can be difficult, as it is both multivariate and logistic (recalling that logistic regression is actually predicting the probability of support for each of the three dependent outcomes). Therefore, it is more helpful to turn to post-estimation techniques to observe how strongly any changes in the independent variables might impact support for the three policy alternatives. For this purpose, I relied on the CLARIFY software module for Stata (Tomz, Wittenberg & King, 2003). <INSERT TABLE 8 ABOUT HERE> Table 8 shows the predicted mean change in the probability of each outcome when each variable changes from zero to one (for indicators) or from the 25 th to the 75 th percentile (for income and education) while all other variables are held constant at the baseline category. Confidence intervals of the estimated probability change are also provided. The inclusion of the interaction term in the model (high network diversity * gay friend) makes the post-estimation a little more complicated so I will discuss the main variables of interest shortly. First, however, some results in Table 8 bear examination. The hypothesized effect of gender is apparent as being female unequivocally increases the probability of supporting full marriage (versus men) and decreases the probability of supporting no legal recognition. However, though the mean change in probable support for civil unions is also negative, the confidence interval includes some positive values so it is less certain what the effect of being female is on that alternative. The effect of age can also be seen with young people more likely to support full marriage than those middle-aged and older people less likely to support full marriage, though for older people it appears that most of the displaced probability shifts towards civil unions rather than no recognition at all. Race also has some influence though the results are more equivocal. Being black appears to reduce support for marriage, though the confidence intervals are quite broad. However, being black was also highly correlated with belonging to a fundamentalist religion (Pearson correlation coefficient = 0.28), which may have reduced the significance of the coefficient on race. Being Hispanic also reduced the probability of supporting full marriage but it appears to increase the probability of supporting civil unions. Turning to income, it appears that higher income leads to higher support for civil unions, but it is less clear whether that support is shifting from marriage, from no recognition, or from some combination. Education, however, has unequivocal influence, reducing the probability of support for no recognition by mean 30%, with most of the support from higher education shifting to support for full marriage.

Authors: Jensen, Micah.
first   previous   Page 11 of 24   next   last



background image
11
were more likely to prefer no recognition to some recognition, and those that support some
recognition are more likely to prefer civil unions. On the other hand, higher income appears to be
associated with greater support for civil unions versus no recognition, but income also appears to
reduce support for marriage versus civil unions. That is to say, higher income may increase the
probability of supporting some recognition, but the increased support is more likely to be towards
civil unions, not marriage.
Though the initial findings are interesting, the interpretation of the multinomial logit results can
be difficult, as it is both multivariate and logistic (recalling that logistic regression is actually
predicting the probability of support for each of the three dependent outcomes). Therefore, it is
more helpful to turn to post-estimation techniques to observe how strongly any changes in the
independent variables might impact support for the three policy alternatives. For this purpose, I
relied on the CLARIFY software module for Stata (Tomz, Wittenberg & King, 2003).
<INSERT TABLE 8 ABOUT HERE>
Table 8 shows the predicted mean change in the probability of each outcome when each variable
changes from zero to one (for indicators) or from the 25
th
to the 75
th
percentile (for income and
education) while all other variables are held constant at the baseline category. Confidence intervals
of the estimated probability change are also provided. The inclusion of the interaction term in the
model (high network diversity * gay friend) makes the post-estimation a little more complicated so
I will discuss the main variables of interest shortly.
First, however, some results in Table 8 bear examination. The hypothesized effect of gender is
apparent as being female unequivocally increases the probability of supporting full marriage (versus
men) and decreases the probability of supporting no legal recognition. However, though the mean
change in probable support for civil unions is also negative, the confidence interval includes some
positive values so it is less certain what the effect of being female is on that alternative.
The effect of age can also be seen with young people more likely to support full marriage than
those middle-aged and older people less likely to support full marriage, though for older people it
appears that most of the displaced probability shifts towards civil unions rather than no
recognition at all. Race also has some influence though the results are more equivocal. Being black
appears to reduce support for marriage, though the confidence intervals are quite broad. However,
being black was also highly correlated with belonging to a fundamentalist religion (Pearson
correlation coefficient = 0.28), which may have reduced the significance of the coefficient on race.
Being Hispanic also reduced the probability of supporting full marriage but it appears to increase
the probability of supporting civil unions.
Turning to income, it appears that higher income leads to higher support for civil unions, but it is
less clear whether that support is shifting from marriage, from no recognition, or from some
combination. Education, however, has unequivocal influence, reducing the probability of support
for no recognition by mean 30%, with most of the support from higher education shifting to
support for full marriage.


Convention
Convention is an application service for managing large or small academic conferences, annual meetings, and other types of events!
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 11 of 24   next   last

©2012 All Academic, Inc.