In a newspaper, magazine, or on the internet, find an article that contains a data set of 15 or more values. Apply what you are learning about statistics to analyze the data and discuss the data within the context of the article. Follow the steps below, showing how you did all calculations.
1. Include the link to the article, or use a screenshot of the article that shows all of the data values.
2. Based on the data, tell the units of the variable. For example, in an article about a basketball player, the units might be the number of points scored per game, the number of games played per season, or the percentage of scored free throws.
3. Does the article describe the data using any statistics, such as an average or a range? If so, describe what statistic was used and how to calculate it. If the article didn't state any statistics, give one statistic that could have been helpful to include and explain why it would be good to include.
4. Calculate the following statistics from the data. Show all your written work, or include an accessible link to the spreadsheet you used to do the calculations.
- Mean and median
- 5 Number Summary, IQR, and boxplot
- Standard Deviation (tell whether it is population or sample, and calculate it accordingly) and range
5. Ask a question about the data that can be answered using a z-score and probability. You will need to assume the data is normally distributed, which may not be true. An example could be, "What is the probability that this basketball player will score fewer than 15 points in their next game?" Then answer your question using the statistics you calculated, the z-score formula, and the z-score table.
6. Use the statistics you calculated to write a short analysis of the data. Use the context of the article to relate the numbers to the original topic. Ideas include describing the center and spread of the data, relating the mean and median if they are very different, or describing the spread of the data based on the 5 Number Summary. A specific example could be, "Although the player scores an average of 20 points per game, the standard deviation being 8.34 means that the number of points scored is highly variable. This might mean that the player has good games and bad games because the large variation means they are not consistent in the points they score."