
Mastering Data Analysis in Excel
Duke University · View on Coursera ↗
Or see the score while you browse.
Taught by Jana Schaich Borg, Daniel Egger
BusinessData Science
About the course
This course focuses on essential data analysis using Excel. Learn to design and implement realistic predictive models to reduce uncertainty for informed business decisions. In a hands-on project, you'll act as a business data analyst, building models to assess credit card applications, minimize default risk and maximize bank profits.
Read more
You'll master key uncertainty measures like classification error rates, entropy of information, and confidence intervals for linear regression. Assignments use data provided within the course and basic Excel functions, ensuring fluency for future business applications. No prior knowledge of advanced Excel features (Visual Basic, Pivot Tables) is required. The Excel and data analysis skills you will learn will enable you to apply business data analysis methods based on binary classification, information theory and entropy measures, and linear regression, and prepare you for roles such as a business data analyst.
The dissent
The most-upvoted critical review (90 votes, 1.0★).
“This course has more holes than swiss cheese. The instructor makes major leaps without thoroughly explaining things. A lot of times when I started to do a problem set it felt like I had missed 2 or 3 lectures. But I had not, the instructor just leaves you to figure a lot out on your own. The videos are choppy often containing errors that sometimes have a note stating the accurate information. The excel sheets are posted at the end of the lecture as opposed to the beginning. But they have nothing to do with the lectures other than the calculus behind the formulas. So you have to go through cell by cell to figure out what the hell the instructor did and what calculus was being used. I appreciate how the instructor combined a lot of material here but unless you are fresh of calculus 3 or several statistics class then this is complexly crap course.”
Coursera's 4.2 comes from 3,960 ratings. Of those, 10.6% are 1–2★.
Starisk reads the reviews learners voted most helpful, and weights each by the square root of its votes: a review with 80 upvotes counts about five times one with 2. Unvoted reviews are not skipped out of laziness — by this model they carry no evidence that other students endorsed them.
That measures what the most-endorsed reviews say, not “true quality.” The rating distribution above is the whole population, so you can see the sample next to it.
Reviews read on 9 Nov 2026.Read them on Coursera ↗