# descriptive statistics 31

Please answer the following questions:

If you were given a large data set (i.e., sales over the last year of our top 100 customers), what might you be able to do with these data? What might be the benefits of describing the data?

This is an example post the professor posted, just to have an idea what professor wants:

Example Post:

We have to look at the different groups of costumers that buy our products. We can select and divide these groups into categories, for example:

What percentage of this data are males?
What percentage of this data are females?
What percentage are young customers?
What percentage of femalesâ€™ vs males buying certain products?
What is the tendency of young buyers?
What are the ages of the different costumers?
Which locations have the most sales?
What are the buying behaviors the costumers have?
What costumers buy more frequently?
What is the frequency in which costumers buy?
What are the ages of the different costumers?
What is the product that sells the most? What is the frequency of that particular product being bought by each gender?
What are the geographies of the different groups of costumers, by knowing this the company can map potential customers, identifying costumer concentration.

By having the knowledge of a particular scenario one can focus his or her products based on what is being sought after. We can organize and describe this data and make a frequency distribution table in which, the costumerâ€™s age can placed in groups or classes determining the frequency; For example, how many costumers from ages 10 to 20 years do we have? How often they buy a product? What kind of products they buy? What is the age group with more frequency of buying certain products? Therefore, allowing the company to canalize its products to specific ages. Another way to organize and visualize this data is to draw a histogram in which the X- axis, is the different ageâ€™s groups and the Y- axis is the frequency; this will help the company to find the average age in this data (mean). Through this histogram data vary (range) can be determined. All of this information will aid the company in marketing its products more efficiently. By graphical analysis the company can determine the number of classes, estimate the frequency of the class with the least frequency, and estimate the frequency of the class with the greatest frequency. Having all these information will help the company to measure the data and at the same time visualize the future of its market. Also the organization of this data allows the analyzer to see if specific products sell better at certain times of the year. We can focus which items these 100 customers are not buying, this is important and helpful when deciding the par level of these items. Another way is to use a frequency chart divided in 12 classes equivalent to the months of the year. In this case, the frequency is the number of purchases for each month. If I plotted this data into a histogram I can show the highest months for profit. This is a good way to visualize in order to make easier comparisons. I can use a stem-and-leaf plot to look at the amount of money spent in the entire year. For example, if \$411 is the lowest amount spent and \$1250 is the highest amount spent, the stem values could range from 4 to 12. By create the plot, we list these stems to the left of a vertical line (Larson & Farber, 2015). This can show any patterns in the amounts of money my top customers spent. Another way is to select a random sample of my top customers and put together a dot plot for the products they bought, this way to see which products are the top sellers; this will be very helpful to increase my sales.

To decide future inventory selection, it will be important to collect data pertinent to dates of the purchases, which items were purchase and the quantity of each product.