Lab 5 | My Projects

Lab 5

Normalizing population growth rates can be useful when you want to compare the growth rates of different regions or countries with widely varying population sizes. By normalizing the data, you eliminate the influence of population size, allowing for a more meaningful comparison. Similar to the population growth rate, normalizing the dependency ratio can be useful when comparing the age distribution and economic disadvantage of different populations.
Population and LandArea
LandArea
The data is heavily left-skewed as most values are towards the higher end of the histogram. The range is 0.68, and the mean is 0.84. The data is not normally distributed as most data points on the larger side of the histogram. For left-skewed data, most outliers lie on the left side of the data set, which in our case was the class of 0.3158 – 0.5354 and has a count of 2.
The intervals at the extremes of the distribution are wider because the quantile classification method tries to get an equal count between all classes. For example, the class 0.3158- 0.8152 has a count of 212, and the class 0.8153-0.8384 has a count of 209. There are no empty classes or classes with too few values. The quantile classification method is mostly used to highlight changes in the middle values of the distribution. Quantile classification is well suited to evenly distributed data, which in our case is not.
Several classification methods could potentially create classes that contain no DAs. The equal interval classification method, when there are a lot of classes, creates classes that have no values. The equal interval classification method divides the range of values into equal-sized classes. Doing this, we see that if we have too many classes, there are going to be some classes that don’t have any values inside of them. An easy way to fix this problem would be to decrease the amount of classes made. Another classification method that could have classes with zero values is the manual interval. This classification method uses user input, which can cause problems if you were to include a class that doesn’t have any values. A way to solve this problem is to create classes that have values inside of them.
The diverging/dichromatic color scheme is good for a standard deviation classification scheme because each class represents a different standard deviation value. A diverging color scheme is usually used to create emphasis on quantitative data from the midpoint of the data. In our case, we can use a diverging color scheme for our standard deviation classification method because each color represents a different standard deviation class. It is not appropriate for other classification schemes because the other schemes usually have qualitative values, which would not work for diverging/dichromatic color schemes.
A Go Global Exchange Program finding homes that would host students that speak French with homes that speak English and French.
EN_FR as the field and the normalization as POP.
Yes, I normalized the variable. I used population because I was finding the percentage of the population from each dissemination area that spoke English and French.
I used a manual interval classification scheme because I wanted the percentage of the population to be a nice number. Also, the manual interval classification scheme allows you to make your own classes with examples from other classification schemes. For example, I first set the classification scheme to be Jenks, and then I modified the classes, turning the classification scheme into a manual classification scheme.
Lab 5