The average cumulative AIDS rate per 100,000 people of Brooklyn, New York is
1933, which exceeds 5.65 times the national rate. In order to get a better
understanding of this extreme high AIDS rate, correlations of various aspects
influencing the big increase of AIDS in the area has been analyzed.

In Brooklyn, there are a total of 37 zip codes. This would make
“n,” the degree of freedom, 35 (n= 37-2). With the confidence of 95% confidence
interval, any correlation coefficient is higher than and between 0.304 and 0.349
would be considered as significant (p=.05, n=35). However, in all the presented
tables and charts, the zip code of 11237, the area of Bushwick, is taken out of
the calculation of the correlation coefficients because it is considered as an
outlier, which does not correlate with the other data.

**Family Income v. Cumulative AIDS Rate**

My first approach to the correlations was thinking about how others
would stereotype or perceive the Brooklyn neighborhood. I remember meeting a
few new friends that were from out-of-state. When I informed them that I was
from Brooklyn, their faces froze and ask me, “Is it dangerous there? Aren’t
there shootings everyday?” These questions provoked me in concluding that
Brooklyn is an unpleasant neighborhood, and I immediately thought of the link
between high crime rates and poverty rates, therefore this provoked me to
analyze my first correlation, the family incomes of Brooklyn. In contrasting
the correlation between the family income and the cumulative AIDS rate, I used
two distinctive incomes: family income of less than $10,000 and family income of
$100,000 to $124,999. According to National Council of Churches USA, the poverty
line for a family of four people in 2002 is $18,100 (Cooper, 2002). According
to Table 1, the correlation coefficient of income of less than $10,000 is
0.585262399, and a coefficient of
-0.357228157 for the family income of $100,000 to $124,999. These results are
highly significant, this means that when family income tends to be lower, the
higher the AIDS rate would most likely be. Conversely, there is a negative
correlation when the family income is higher, meaning that when the income is
higher, the AIDS rate tends to be lower. When the family is in financially
challenged, the family cannot afford to pay for the expensive HIV and AIDS
testing and medicine. This correlation can be further demonstrated in Graphs 8
and 9, where it shows the general trend and correlation of AIDS rate and
percentage of income.

**Public Assistance v. Cumulative AIDS Rate**

Similarly to the nature of the family income, I thought the
relationship between public assistance and AIDS rate would be significantly
correlated. I obtained statistics of public assistance from the U.S. Census,
and found the correlation of the AIDS rate and the percentage of households with
no public assistance to have a coefficient of -0.6783 (Table 1). This negative
correlation shows households that do not need or receive public assistance tend
to have lower cumulative AIDS rate. The correlation coefficient of percentage of
households who receive public assistance is 0.6686, which is highly significant.
The households that do not receive public assistance are not below the poverty
level, thus are able to obtain reasonable HIV and AIDS testing. Contrastingly,
those who do receive assistance are poor, and often are not able to afford to
pay for many things, in this case study, AIDS medication and testing. These
correlations can be clearly shown in Graphs 6 and 7.

**Education v. Cumulative AIDS Rate**

In accompany to the financial aspects that contribute to the AIDS
rate, general education correlates with the AIDS rates as well. In gathering my
statistics, I found that the percentage of female who are high school graduates
have a negative correlation in relations to the AIDS rates. The coefficient is
-0.4581, which is significant (Table 1, Graph 1). In other words, females who
have graduated from high school demonstrate to have a lower cumulative AIDS
rate. Education allows people to obtain correct information on preventing HIV
and be educated about safe sex, thus it would ultimately lower the cumulative
AIDS rate. Surprisingly, the males’ education correlations are not significant,
and the females’ education correlations did not show significance except for
females who are high school graduates.

**Races v. Cumulative AIDS Rate**

Subsequently, the correlation coefficient of cumulative AIDS rate
varies in the Black Hispanic and White population in Brooklyn. In the Black
population, the correlation coefficient is 0.5829, which means that as the
percentage of the Black population increases, the AIDS rate increases as well
(Graph 10). This trend is also shown in the Hispanic population of having a
correlation coefficient of 0.3726 (Table 1, Graph 11). However, contrastingly,
the white population has a negative correlation coefficient of -0.6441(Table 1,
Graph 12). This shows that as the percentages of white population decreases, the
AIDS rate decreases as well. The white population resides in neighborhoods such
as, Bensonhurst (11209), Bay Ridge (11204), East Flatbush (11230) and Sheepshead
Bay (11235) have the least AIDS rate. These neighborhoods are in the AIDS rate
range of 64-1601 per 100,000 people. However, there are exceptions such as
Greenpoint (11201) and Park Slope (11217 and 11231) because of the high male
population in those areas, thus the rate of men having sex with men is very
high. The Black population is predominant in the areas of East Flatbush (11203),
Williamsburg (11206), East New York (11207), Bedford-Stuyvesant (11212 and
11213), Crown Heights (11216, 11233 and 11238), Bushwick (11221), and Flatbush
(11226). These areas are all high in AIDS rate, from the range of 868 to 4054
per 100,000.

**Family v. Cumulative AIDS Rate**

There is a significant correlation between family status and the
cumulative AIDS rate. I found out that the martial status of people influences
the AIDS rate. In the percentage of married-couple family versus the cumulative
AIDS rate, the correlation coefficient is -0.5872, which means that as the
percentage of the married-couple family increases, the AIDS rate decreases.
Commitment within a marriage keeps the couples from being sexually active with
anyone else, except for their spouse. Therefore this explains the negative
correlation and the low AIDS rates among married couples in Brooklyn (Graph 2).
As the percentage of husband engage in the labor force increase, the lower the
AIDS rate (Graph 3) and its correlation coefficient is -0.4558. As the husbands
work, they bring back money to support the family and enable the family to be
more financially stable. Furthermore, the percentage of the wife not being
present is correlated to the cumulative AIDS rate, where there is a 0.5969
correlation (Graph 4). Since there are no wives in the family, men tend to be
more sexually liberal, and may have more sex partners, therefore increasing the
chances of contracting the disease. This is also similar to the percentage of
the husband not being present, in which it has a highly significant correlation
of 0.5628 (Table 1). The women would be more sexually active and may have more
sex partners, increasing the rate of transmission of AIDS (Graph 5).

**
Conclusion
**There were many interesting correlations that I did not expect
to have a correlation in and I am surprised about the education correlations.
Education was the trend that I expected to show relationship between the more
education that one receives, the AIDS rate would be lowered. However, the
correlations calculated in males did not show any significance, while in the
female only the high school graduates show the significance in correlation to
the lower AIDS rate. The family income and the AIDS rate correlated the best,
and as I predicted prior to calculation that it would be significant. The AIDS
rate has correlated with the percentage of Black, Hispanic and White population,
female high school graduates, marital status, and financial status. However,
these are perhaps only a few correlations that demonstrated to have a
significant relationship, a further research may pose more questions on what to
focus on to the correlation of an area where AIDS epidemic is quickly and
destructively damaging the general well being of the society in a very subtle
act.

**
References**

Cooper, Mary Anderson (2002, October 3). Poverty Increases in the United States,
U.S. Census

Bureau Reports. Retrieved July 17, 2008, from
http://www.ncccusa.org/publicwitness/povertyincreases.html.

US Census
Bureau. Retrieved July 18, 2008, from
http://factfinder.census.gov/home/saff/main.html?_lang=en.

Zip Code Definitions of New York City Neighborhoods. Retrieved July 18, 2008,
from

http://www.health.state.ny.us/statistics/cancer/registry/appendix/neighborhoods.htm