MA 382: Introduction to Statistics

Have you had an introductory course in probability? Are you interested in hands-on data analysis? Then, this is the course for you. In MA382, we dive into basic theory surrounding the field of statistics while motivating all of the topics with real data analyses. You may count the course credit toward any of Pre-req: MA 381 (Introduction to Probability)
Note: Students may only receive credit for one of MA223 or MA382.
Example Syllabus: Fall 2020 Syllabus
Example Schedule: Fall 2020 Schedule


Statistical skills are extremely desirable.

The Bureau of Labor Statistics cites statistics as one of the fastest-growing fields in the U.S., with a projected growth rate of 31% between 2018 and 2028. So, individuals with strong statistical analysis skills are in high-demand. Beyond this, statistical jobs are cited as having relatively low stress and great pay. Statistician positions top multiple job lists online, including


If you take MA382, you will have experience

This course covers basic statistical ideas: data visualization, estimation, confidence intervals, and hypothesis testing. We specifically cover inference for a single population mean, parameters in simple linear regression, and several population means through ANOVA. Both parametric (normal, t-, or F- distribution) and nonparametric (bootstrap) approaches are included in analysis.


Beyond Basics: Data Challenge

Although you have many chances to analyze data in class assignments and lectures, the data challenge takes you beyond the typical classroom experience. Students will work in teams to analyze a large, complicated dataset throughout the term. Teams are able to complete a data analysis from start to finish: obtaining the dataset, visualizing and summarizing its contents, formulating interesting questions, performing a statistical analysis, and summarizing the results. The challenge in the project comes with the size of the data and the intricate relationships within each dataset. Students are able to see limitations of the basic statistical methodology while still creating a model with real utility in applications.

This year, student teams will have the opportunity to select their dataset for analysis. The sources available include


FAQ:

How are MA382 and MA223 different?

MA223 (Engineering Statistics) and MA382 technically cover the same statistical methods. However, the student experience in these courses is widely different. MA223 focuses on engineering applications with little formal theory presented (due to no MA381 pre-req). Instructors in MA223 focus very little on coding, and most data analyses utilize small datasets. MA382 relies on the prior exposure to probability to dive a bit deeper into the statistical theory. For example, we consider questions such as,

"Why do we use a sample mean to estimate the population mean?"
"How does the Central Limit Theorem work?"
"Why might a standardized mean come from a t-distribution instead of a normal distribution?"

These types of questions are answered without proof in MA223, but formalized in MA382. Students in MA382 solely use the R programming language for statistical computing, are expected to program on their own within R, and tend to analyze larger datasets.


If I have taken MA223 already, may I take MA382 for credit?

No, students may only take one of these introductory statistics courses for credit. They both cover the same topics, but MA382 just give a deeper understanding of theory and relies more heavily on programming and computing for analyses. If you liked your MA223 class, then you should consider taking an upper-level statistics course such as MA386 or MA480 in the fall and look into obtaining a statistics minor.


I already took MA381. How does MA382 differ? (Both courses have "probability" and "statistics" in the title.)

Although the titles may imply that these courses are very similar, the approaches are quite different. Probability is a traditional area of mathematics, and courses in probability have a similar feel to courses like calculus. In probability analyses, certain population distributions and parameter values are assumed to be known. Subsequently, that information is utilized to perform calculations (e.g. summing, integrating) to yield a single, correct numerical answer.

In statistics, the population distributions and parameter values are unknown. Sample data is utilized in order to estimate parameters associated with the population. Using reasonable methodology, we are able to obtain estimates, but not able to say that we have found the answer with 100% certainty. This difference leads to a strong emphasis on communication of results and writing. Many students have not experienced a course like statistics, where the mathematical and rhetorical emphases are nearly equal.