1990 V. 2000 Case Study

After looking at Maternal Deaths 1990 v. 2000, it is important to look at the number of maternal deaths in 2011 compared to those in 1990. Just like before, the relationship between the two variables is if the data point is above the regression line then there was more deaths in 2011 than in 1990 and vice versa (Figure 5). This makes sense because higher the y-value the lower the x-value and it is the same the other way around. For this data, the least square regression equation was y=0.37x+75.456. The slope is 0.37 which is inferring that there is .84 change in maternal deaths in 2011 for every number of deaths in 1990. The y-intercept in the equation is 75.456. The y-intercept is saying that when 1990 there are 0 deaths, there there is 75.456 maternal deaths in 2011. For the regression line, this makes absolute sense. In reality, that doesn’t make sense because there can be 75 females dead and .456 of another female. In that case, for the y-intercept to be realistic it would have to be a whole number. …show more content…
in 2011, it will be found in the correlation coefficient, which is represented by “r”. The correlation coefficient for the data is r=0.815. The correlation is telling us the direction, strength, and linearity of the regression line to the data point. Based on the 0.815 is a positive number, the direction is positive and it can be seen in the picture of the graph (Figure 5). The strength of the regression line is really strong, meaning there is a high correlation. The strength is really strong because 0.815 is closer to 1 than to 0 and the closer to 1 the strong the strength is. Plus, it is saying that the data point are really close to the regression line which is true if looking at the graph (Figure 5). As for the linearity, it is okay to say that the data does have a linear correlation as evidenced by the graph showing that as x-values increase so does the y-value (Figure