In statistics week 4 The topic was the Association between two variables — Review of course, Association between two categorical variables — Introduction, Association between two categorical variables — Relative frequencies, Association between two numerical variables — Scatterplot, Association between two numerical variables — Describing association, Association between two numerical variables — Covariance, Association between two numerical variables — Correlation, Association between two numerical variables — Fitting a line, Association between categorical and numerical variables.
I learned that categorical variables contain different categories or groups, such as gender, blood group, or type of transportation. Studying the association between two categorical variables helps us understand whether one category is related to another. For example, we can study whether students’ preferred study method is related to their academic performance. After that, I learned about relative frequencies. I understood that relative frequency shows the proportion or percentage of observations in each category instead of just the actual count. Relative frequencies make it easier to compare categories, especially when datasets are of different sizes. They provide a better understanding of how data is distributed.
The course then introduced the association between two numerical variables using scatterplots. A scatterplot is a graph where each point represents one pair of values. By looking at the pattern of points, I learned that we can understand whether two numerical variables are related. Scatterplots are useful because they allow us to see trends, clusters, and unusual observations in the data.
Another important topic was describing association between numerical variables. I learned that two variables may have a positive association, a negative association, or no association at all. If one variable increases and the other also increases, the association is positive. If one variable increases while the other decreases, the association is negative. If there is no clear pattern, then there is little or no association between the variables.
Get Umarua’s stories in your inbox
Join Medium for free to get updates from this writer.
Next, I studied covariance. I learned that covariance is a statistical measure that tells us whether two numerical variables move in the same direction or in opposite directions. A positive covariance means both variables generally increase together, while a negative covariance means one variable increases as the other decreases. Covariance gives an idea about the direction of the relationship, but it does not clearly show how strong the relationship is.
The course also introduced correlation. I learned that correlation measures both the direction and the strength of the relationship between two numerical variables. A correlation value close to +1 shows a strong positive relationship, a value close to -1 shows a strong negative relationship, and a value close to 0 indicates little or no relationship. Correlation is one of the most useful tools in statistics because it helps us understand how closely two variables are connected.
Another interesting topic was fitting a line to the data. I learned that when two variables have a relationship, we can draw a line that best represents the overall trend of the data. This line is called the best-fit line or regression line. It helps us understand the relationship more clearly and can also be used to make predictions about future values.
Finally, I learned about the association between categorical and numerical variables. In this topic, I understood that one variable contains categories while the other contains numerical values. For example, we can compare the marks scored by students from different sections or compare the average salaries of employees working in different departments. Statistical methods and graphs help us compare these groups and understand whether meaningful differences exist.
Overall, these topics gave me a strong understanding of how different variables are related to one another. I learned how to identify relationships using tables, graphs, scatterplots, covariance, correlation, and regression lines. These concepts are very important in data science because they help us analyze real-world data, discover patterns, and make informed decisions.
