Correlations
My studies on AIDS epidemic in Buffalo have brought me to analyze the relationships of dependent variable present in correlations. This allows a new perspective into the study of AIDS with the use of correlations coefficients determine the direction and strength of the relationship. The coefficient ranges from -1 to +1.With a negative correlation (-1) the relationship is inverse meaning that as one dependent increases the other decrease. A positive correlation means the relationship is direct since as one increases the other also increases. To find the correlation coefficient a covariance is used to show the degree which the variables diverge together. For my studies my covariance was .29 for my 46 zip codes. The dependent variables I correlated with the rate variables included public assistance, income, race, property ownership, foreign born population and gross rent.
I correlated public assistance and income with the AIDS rates because I wanted to see if there might be a relationship between rates of AIDS. I expected the correlation of public assistance and the AIDS rate to be inverse because I though that the more assistance the better of they were since they had to means to protect themselves. That was not the case since the graph produced a positive correlation 0.76 that shows that the more public assistance received, the more AIDS. (Table 1) This relationship is probably due to the fact the people receiving public assistance in their later stage of the disease are so weak that they need this assistance. Furthermore, those on public assistance for other reasons other than AIDS are not working and left with plenty of free time to acquire or transmit HIV. When I correlated the median income I had similar expectations as the public assistance and this time I was right. The correlation produced a negative relationship of -0.71 that showed that the more income received the less AIDS. (Table 2) With more money the people have the means to protect themselves and find the infection of HIV sooner in order to get treatment. Maps I
To further my study I correlated the AIDS rates with race. I though that it would be interesting to see how the AIDS rate connected with the various relationship. The races I correlated included Whites, Blacks and Hispanics. I expected the relationship to be direct for all cases because I perceive the AIDS epidemic as an equal opportunity killer. That was not the case since the white population showed a negative correlation while the Blacks and Hispanics had positive correlations. The White population’s negative correlation of -0.73 shows that as the population grows, the AIDS rate decrease. Among the Blacks the correlation was positive with 0.66 and among the Hispanics it was 0.52, showing that the AIDS rates increase with the increase in both populations. (Table 3, Table 4, Table 5)The correlations show that the white population is identifying AIDS and tackling it with education, while the Blacks and Hispanics fail face the AIDS epidemic. Most of the white population lives in the suburban areas while the Black and Hispanics are concentrated in the close quarter in the inner city. This explains why the few media coverage of the AIDS epidemic in Buffalo calls upon the Blacks and Hispanics to get tested. Another group I chose to investigate was the Indian population. I was not surprised to learn that they fell in the same category of the Blacks and Hispanics. The group had the positive correlation of 0.30. (Table 6)In their smaller clusters outside of the city the Indians my not be able to reach centers HIV/AIDS testing. Maps II
Other dependent variables I observed were the median gross rent for the white population and the median value for all owner-occupied housing units. I was attracted to these variables because I wanted to see how people with financial stability of home correlated with the AIDS rates. I expected that the higher the gross rent the more valuable the property, which would suggest that the inhabitants had money. Since the higher income produced a negative correlation I expected the gross rent and property value would have the same effect. My hypothesis was correct since inverse relationships were observed in both variables. As the median gross rent increases the AIDS rates decreases, producing a negative correlation of -0.56. (Table 7) The median value for all owner-occupied housing units also held an inverse relationship with the AIDS rates and had a negative correlation of -0.43. (Table 8) The results really show that wealth has a great impact on the AIDS epidemic. People with the means are able to engage in the fight against AIDS while the impoverished people slowly die off.
Moreover I correlated the foreign origins of various people to the AIDS rates. I did so because I am aware that Buffalo, New York is the destination point of may immigrants, I can include myself in that count. I look at the foreigners from Europe, Africa and the Americas. I expected the correlations to produce a direct relationship with Africa because I am aware that it is third world but was a bit uncertain with Europe and the Americas which are more developed. My speculations about foreigners from Africa were correct since a positive relationship with the AIDS rates was produced with a positive correlation of 0.35. (Table 9)The correlation shows that the more African immigrants the increase of AIDS rate, the same can be said of the foreigners from the Americas that produced a correlation of 0.44. (Table 10)I was surprised to learn that the Europeans foreigners had an inverse relationship with the negative correlation of -.61. (Table 11) The graph shows that as more Europeans emerged from Europe the lower the AIDS rates.
In all my studies through correlations have offered a new way to perceive the AIDS epidemic in Buffalo. Through my correlations of races I was able see that Blacks and Hispanics are the greatest risk. This group of people that are either not receiving enough information or unable to access the aid. My correlations also proved that the AIDS rates are the highest among the poor in the projects and ghettos which mainly consist of minorities.
Maps