Instructor: Dr. Alan T. Arnholt
Office: Walker Hall 237
Office Hours: 3-4:30 pm MWF; and by apppointment
Make an appointment to see me by clicking https://arnholtat.youcanbook.me/.
Course Description:
A continuation of STT 3820. Topics commonly covered include experimental design; intermediate topics in least-squares regression modeling, such as multiple regression, residual analysis, transformations, higher order model terms and interactions, categorical predictors, diagnostic statistics for assessment of model fit, and model selection; one-way and two-way analysis of variance, including blocking and factorial designs. Emphasis is on a non-theoretical development of statistical techniques and on the interpretation of statistical results. Statistical software will be utilized in the analysis of data.
Course Objectives:
Course Text:
Supplemental Material:
Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani (2013). An Introduction to Statistical Learning with Applications in R
Chester Ismay and Albert Y. Kim (2018). ModernDive: An Introduction to Statistical and Data Sciences via R.
Course Grading & Assessment:
The only way to learn statistics is to DO statistics, which includes using statistical software. Reading the textbook, learning the language, and practicing exercises using real data are critical to your learning and success. Class activities and assessments have been structured with these principles in mind.
You should read assigned textbook content and read/watch supplemental materials prior to coming to class. It will be easier to participate if you acquire some familiarity with the vocabulary and methods before we start to discuss and use them. You must “speak the language” (both statistics and R) to demonstrate your knowledge effectively.
Appalachian students are expected to make intensive engagement with courses their first priority. Practically speaking, students should spend approximately 2-3 hours on coursework outside of class for every hour they spend in class. For this three-hour course, you you should anticipate 6-9 hours per week of outside work.
24% of the course grade will come from DataCamp assignments (4 assignments)
24% of the course grade will come from reproducing three DataCamp assignments with bookdown
30% of the course grade will come from two projects. The final project includes an oral presentation where you discuss your final model used in the predictive modeling competition — oral presentations will take place during the final exam period — December 9, 2019, WA 303, 11-1:30pm
22% of the course grade will come from two labs
How To Get Unstuck
Well constructed questions will elicit answers more rapidly than poorly constructed questions. This video provides some background on asking questions. This stackoverflow thread details how to create a minimal R reproducible example. Please read How To Ask Questions The Smart Way by Eric Raymond and Rick Moen and heed their advice.
University Policies
This course conforms with all Appalachian State University policies with respect to academic integrity, disability services, and class attendance. The details of the policies may be found at http://academicaffairs.appstate.edu/resources/syllabi.
Computers and Software
This course will use the RStudio server (https://mathr.math.appstate.edu/) that has the programs listed below and more installed.
You must have an active internet connection and be registered in the course to access the server. To access the server, point any web browser to https://mathr.math.appstate.edu/. Use your Appstate Username and Password to access the server. A screen shot of the RStudio server is shown below.
If you have problems with your Appstate Username or Password visit IT Support Services or call 262-6266.
Required Technology
Note: All technology used in the class is either open source (free) or will be accessible to students enrolled in the course for no cost.
Assignments
The CoursePacing guide has all course assignments and due dates.