
A Change in Attitudes Toward Muslims? A Bayesian Investigation of Pre and Post 9/11 Public Opinion

 Unformatted Document Text:
2000
25% of applicable cases were observed;
Applicable to 2799 cases
0%
25%
50%
mean = 2.78 sd = 0.83
Frequency
2001
70% of applicable cases were observed;
Applicable to 2041 cases
0%
25%
50%
Frequency
mean = 2.67 sd = 0.80
2002
36% of applicable cases were observed;
Applicable to 2002 cases
0%
25%
50%
Frequency
mean = 2.60 sd = 0.83
2005
42% of applicable cases were observed;
Applicable to 2000 cases
0%
25%
50%
Frequency
mean = 2.71 sd = 0.79
Respondents' Attitudes toward Muslim
1: Very unfavorable
2: mostly unfavorable
3: mostly favorable
4: very favorable
Figure 1: Summary statistics of respondents’ attitudes toward Muslim of 4 diﬀerentyears. The distribution of each of the categories of the 4 years is almost identical.Most respondents show that Muslims are ‘most favorable’ to them. The mean of 2.6of 2002, the smallest among the 4 years, indicates that respondents of this year favorMuslim less than any other year. Nonetheless, the standard deviations show thatthey are statistically indiﬀerent.
like this is to postulate the existence of an underlying latent (unobserved) variable
z associated with each response κ of y (McCullagh 1980; Johnson and Albert 1999;
Agresti 2002) such that:
y
i
=
1 if z
i
< c
1
2 if z
i
∈ (c
1
, c
2
)
3 if z
i
∈ (c
2
, c
3
)
4 if z
i
> c
3
z
i
= Xβ +
i
−∞ < c
1
≤ c
2
≤ c
3
≡ ∞
where c
κ
represents the cutpoints between two response categories κ’s and
is a
random variable drawn from a standard logistic distribution that
i
∼ logistic(0, 1).
When z
i
falls between the cutpoints c
κ
and c
κ+1
, the observation is classiﬁed into
category κ. We assign empirical weak informative priors of t(mean = 0, scale =
2.5, df = 30) on coeﬃcients of predictors as we rescale all the predictors (Gelman,
11

 Authors: Kalkan, Kerem. and Su, YuSung. 




2000
25% of applicable cases were observed;
Applicable to 2799 cases
0%
25%
50%
mean = 2.78 sd = 0.83
Frequency
2001
70% of applicable cases were observed;
Applicable to 2041 cases
0%
25%
50%
Frequency
mean = 2.67 sd = 0.80
2002
36% of applicable cases were observed;
Applicable to 2002 cases
0%
25%
50%
Frequency
mean = 2.60 sd = 0.83
2005
42% of applicable cases were observed;
Applicable to 2000 cases
0%
25%
50%
Frequency
mean = 2.71 sd = 0.79
Respondents' Attitudes toward Muslim
1: Very unfavorable
2: mostly unfavorable
3: mostly favorable
4: very favorable
Figure 1: Summary statistics of respondents’ attitudes toward Muslim of 4 diﬀerent years. The distribution of each of the categories of the 4 years is almost identical. Most respondents show that Muslims are ‘most favorable’ to them. The mean of 2.6 of 2002, the smallest among the 4 years, indicates that respondents of this year favor Muslim less than any other year. Nonetheless, the standard deviations show that they are statistically indiﬀerent.
like this is to postulate the existence of an underlying latent (unobserved) variable
y
i
=
1 if z
i
< c
1
2 if z
i
∈ (c
1
, c
2
)
3 if z
i
∈ (c
2
, c
3
)
4 if z
i
> c
3
z
i
= Xβ +
i
−∞ < c
1
≤ c
2
≤ c
3
≡ ∞
where c
κ
represents the cutpoints between two response categories κ’s and
is a
random variable drawn from a standard logistic distribution that
i
∼ logistic(0, 1).
When z
i
falls between the cutpoints c
κ
and c
κ+1
, the observation is classiﬁed into
category κ. We assign empirical weak informative priors of t(mean = 0, scale =
2.5, df = 30) on coeﬃcients of predictors as we rescale all the predictors (Gelman,


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, zscore 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. 






