1. as presented on that date, with special formatting removed
What Statistical Knowledge Serves as a Foundation for a Business Analytics Course?
Abstract:  This session examines the statistical principles and techniques that would prepare students to take a business analytics course. Presenters seek, through discussion with attendees, to formulate the required knowledge as a series of review questions that could help students prepare for such a course.
DSI 2016 DASI Session, Saturday, November 19, 2016, 4:30-6 PM,
as presented on that date, with special formatting removed

2. DSI 2016 DASI Session, Saturday, November 19, 2016, 4:30-6 PM
What Statistical Knowledge Serves as a Foundation for a Business Analytics Course?
David Levine,
30+ years teaching business statistics and writing statistics textbooks
David Stephan
20+ years teaching CIS, 40+ years facilitating IT use,
30+ designing instructional tools
Kathy Szabat,
30+ years teaching business statistics,
5 years developing business analytics courses
DSI 2016 DASI Session, Saturday, November 19, 2016, 4:30-6 PM

3. Why That Question? Rise in Business Analytics Writing a book
Developing a course and curriculum

4. Define Business Analytics
Differentiated from Data Science and Data Analytics
Not just advanced OR/MS, but elements of Statistics and Information Systems

5. Define Business Analytics
“Business analytics are the methods that combine advances in statistics, operations research and management science, and information technology to reveal meaningful information from data….Business analytics forms a basis for fact-based management decision-making.”

6. Determining the Foundational Knowledge
What concepts and methods are necessary to knowingly use business analytics?
Which concepts and knowledge from an introductory statistics course would you want students to remember several years later?

7. Issues Discussing the Foundational Knowledge
Range of student preparations
AP Statistics, Business Statistics, some general statistics; one-semester, two- semester
What might an introductory business statistics course omit that is important to understanding business analytics?
Calendar tensions
Must avoid re-teaching introductory statistics

8. Presenting the Foundational Knowledge
How much time to spend?
What needs to be taught as new material?
What should be the method/format of presentation?

9. Presenting the Foundational Knowledge

10. Using a Q&A format to present Foundational Knowledge
Sequencing issue: what question comes first?
What concepts do not lend themselves to questions?

11. Our solution: Three Units, 2 of which are Q&As
Q&A: Basic Statistical Terms, Concepts, and Methods
Q&A: Statistical Inference Basics
Review Chapter: Linear Regression Basics
TBD: The amount of “practical skills” reviewed for these topics.

12. Basic Statistical Terms, Concepts, and Methods
1.1 What’s “statistics” and why should I bother studying statistics?
Statistics is one of the tools of a modern information system. Businesses use information systems to generate useful information for management decision-making. Statistics provides the means to analyze data that may affect decision-making. In an information system, statistics has the unique ability to organize and summarize large volumes of data and to demonstrate relationships among related data.

13. Basic Statistical Terms, Concepts, and Methods
1.2 What is data??
Data are the facts that a business collects or generates as part of its ongoing activities as well as facts that a business may collect from other sources to facilitate decision-making.

14. Basic Statistical Terms, Concepts, and Methods
1.3 What’s the distinction meant by using “business statistics” instead of “statistics?”
Business statistics emphasizes the application of statistics to management decision making. Using business statistics always begins with the statement of an organizational problem or goal that fact-based, rational decision-making can help solve or achieve....Business statistics users need to understand the logic behind the statistical methods they use…(and) need to know the implications and assumptions about the data they use.

15. Basic Statistical Terms, Concepts, and Methods
1.4 What kinds of data do statistical methods use?
Statistical methods use data that are the results of a counting, measuring, or classifying activity. Counting things leads to discrete counts…
Measuring things leads to continuous values that may be any value within an interval…
Classifying activities results in assigning categories to something….

16. Statistical Inference Basics
2.7 What is sampling error? Why is it important?
Sample statistics almost always vary from sample to sample. This expected variation is called the sampling error. The size of the sampling error is primarily based on the variation in the population itself and on the size of the sample selected. Larger samples will have less sampling error….

17. Statistical Inference Basics
2.8 What is a confidence interval?
A confidence interval estimate is a range of numbers, called an interval, constructed around a point estimate, the value that represents the “best guess” of a particular sample statistic. One constructs confidence intervals in a way that ensures that the probability that the interval includes the population parameter will be known….

18. Statistical Inference Basics
2.15 How do you perform hypothesis testing using the p- value approach?
Most modern statistical and spreadsheet software, including the functions found in spreadsheet programs, can calculate the probability value known as the p-value that you can use to determine whether to reject the null hypothesis.

19. Statistical Inference Basics
2.16 More specifically, what is a p-value?
The p-value is the probability of computing a test statistic equal to or more extreme than the sample results, given that the null hypothesis H0 is true. The p-value is the smallest level at which H0 can be rejected for a given set of data. The p-value represents the actual risk of having a Type I error for a given set of data.
(Type I error is defined in an earlier Q&A.)

20. Our solution: Regression Basics Chapter Topics
Simple linear regression models
Evaluating goodness of fit
Nonlinear relationships
Assumptions in regression
Residual analysis
Inferences in regression
Pitfalls in regression
Multiple regression models

21. Mapping the Foundational Knowledge to Business Analytics/Justifying Choices
Foundational knowledge is the knowledge that unlocks understanding.
Prediction/predictive: How can one understand “predictive analytics” if one does not understand what “predict” means in this sense.
With foundational knowledge can answer such insight questions as “Can predictive models be wrong?”

22. Further Considerations
If the Business Analytics course follows as a second course after Business Statistics, what foundational concepts from other disciplines need to be reviewed/discussed?

23. “Other Discipline” Example
A “Data” concepts component?
(Come back tomorrow to further consider this.)

24. Thank You From the Two Davids and Kathy!
Contact us at:
2016 DSI DASI session, Saturday, November 19, 2016, 4:30-6 PM