At the beginning of this semester, our instructor, Professor Robert Woodward, informed the class that we would be taking part in a group data collection project that would be due at the end of the semester. This term-length project involved collecting data from bags of Skittles candies that were passed out on the first day of class. With each bag of Skittles, each student was given a set of instructions to follow throughout the semester. The project was designed for students to “pull together concepts you are studying this semester, including organizing data, drawing conclusions using confidence intervals and hypothesis tests, and presenting our work in a well-organized paper”. We began our team project in September, when each classmate was asked to record and share data about our individual Skittles bags.

 

Part 1: Project Data Collection

 

Part one of the assignment was organized as a quiz in Canvas, which allowed each student to input the number of each color of candies present in each of their personal bags of Skittles. My bag of Skittles contained 9 red Skittles, 17 orange Skittles, 12 yellow Skittles, 8 green Skittles, and 11 purple Skittles for a count of 57 Skittles total in my personal bag. A few days later, Professor Woodward used the Skittles data that each student in our class entered into Canvas in Part 1 to create a spreadsheet that reflected the characteristics of each bag. The class data was provided to each student through Canvas in the form of an Excel spreadsheet and a PDF table. Click the button below to view my submission for Part 1.

​

​

 

 

The data from the button above is a screenshot of the PDF file that was shared through Canvas that reflected every class member’s Skittles data. Throughout the rest of the term project, our class used a software called Stat Crunch to analyze, organize, and display our data.

​

Part 2: Organizing and Displaying Categorical Data

 

Part 2 of our project, Organizing and Displaying Categorical Data: Colors, went a bit further in depth than Part 1. In Part 2, we were asked to make predictions about the class Skittles data to help us begin using a statistical view for analyzing data. We were asked to make a prediction about the relative frequency of each bag of Skittles and explain our reasoning. We were then asked to present graphs and tables that visually displayed our predictions. After, we were asked to see how our predictions compared to reality, and to display the comparison in a frequency table. Click the button below to view my submission for Part 2.

​

​

 

 

 

Part 3: Organizing and Displaying Quantitative Data: The Number of Candies Per Bag

 

The next part of our term project involved analyzing, organizing, and displaying the class Skittles data. Using information that we learned in chapters 4-6, we analyzed our data to find the mean and median, minimum and maximum, quartiles, and outliers present in our class Skittles data. We organized and displayed this information in box plots and histograms. Then, we described our data as quantitative or qualitative and elaborated on the best ways to describe, display, and organize the type of data we were analyzing. Click the button below to view my submission for Part 3.

​

​

​

​

Part 4: Confidence Interval Estimates

 

Part 4 of our term project revolved around confidence intervals. A confidence interval is a low point estimate and high point estimate that may contain the true value of a statistic. The t-score, standard deviation, and sample size (n) affect the width of the confidence interval. A larger sample size will make the confidence interval wider. A larger standard deviation will make the width of the confidence interval more narrow. For Part 4, we were asked to construct a 99% confidence interval estimate for the population proportion of yellow candies, construct a 95% confidence interval estimate for the population mean number of candies per bag, and discuss and interpret the results of each of our interval estimates. Click the button below to view my submission for Part 4.

​

​

​

 

Part 5: Compile Term Project, Reflection, and ePortfolio Posting

 

We have finally reached the end of the semester and the end of the term project. Part five asks us to compile each portion of our team project, reflect on our work, and post it to our ePortfolio. 

 

Reflection: 

 

This term project was very helpful way to show students how to apply concepts that we learned throughout the semester in Introduction to Statistics. Each portion of the project was organized and aligned to the concepts we were currently learning and served as a great reinforcement tool that helped better our understanding of concepts before each exam. 

Part one was the easiest part of the assignment, but served the purpose of helping me to understand how data is collected. Chapter one focused on the foundations of statistics, and how to describe data. We also learned the different ways that data can be collected, ways that data can be interpreted, misinterpreted, or biased. This portion of the assignment helped me familiarize myself with what kind of data we were collecting and how it was being collected. 

Parts two and three of our project helped me familiarize myself with the ways that data is displayed. It also helped me to understand how to choose the way in which we display data so that it is interpreted correctly and isn’t misleading. It was extremely helpful to see the different ways that we could display data to determine what ways qualitative data was best visually represented. This was the most influential part of this project for me. I now understand how to identify visual data that is misleading. This helps me in real life situations to avoid simply accepting misleading data at first glance, and instead conduct my own research into what the data really means. 

Part four of this project helped reinforce the topic of confidence intervals. Confidence intervals were very interesting to me this semester. I think it is very important to understand confidence intervals because sample data is often used to make assumptions about a population. By using confidence intervals, we can understand that a study of a sample does not always reflect a population perfectly. I liked confidence intervals because it uses a range of numbers to make predictions about a population, while also including a margin of error. It’s important to consider a margin of error in statistics because it is impossible to predict something to be true about the entirety of a population. However, including outliers in a data set could skew the data, making it hard to analyze or use. It’s important to understand these aspects of statistics in order for data to be significant.

This project was really interesting and fun to analyze. It did a great job with reinforcing topics throughout the semester and showing me how to apply what we were learning to different aspects of my studies and daily life. I was skeptical about how much statistics was going to be helpful as a prospective dental hygiene student, but I am happy to say that I think it is very applicable to my future career. I think statistics will be used often in my future career, especially advising patients about proper preventative dental care through research.