Most of them aren’t worth it. The free equivalent courses on Coursera are just as good.

An alternative to taking courses is to simply download a free dataset online and try to do something with it: summarize it, visualize it, etc. using R, Python, or whatever coding language you’re trying to learn. This will force you to google “How to import data”, “how to do X, Y, Z”, etc. and you’ll learn much quicker this way.

Completely agreed – it’s in high demand right now and the income opportunities reflect that. Very cool to hear from someone who used to be in the field. Thanks for sharing!

I consider basic stats to be the concepts you would learn in an intro to statistics course like confidence intervals, hypothesis testing, regression, ANOVA, and probability.

When I first start working with a dataset, I usually try to visualize the data with histograms, scatterplots, etc.

If I’m just trying to describe a dataset, I’ll use common descriptive stats like mean, median, standard deviation etc.

And if I’m building a model, I’ll commonly use regression or clustering depending on the business question.

In my limited experience as a data scientist over the past ~2 years I would not consider it stressful at all. That said, it probably varies by industry. I have been in healthcare and retail. I’m sure finance/banking or other more demanding industries could present more stressful situations.

Thank you!

Reading this post makes me wonder what kind of statistical tool you use at work to interpret data. For example, maybe TOP 3 concepts that are frequently used to make sense of the data?

I’m not very familiar with the terms, read a little on K Clustering before, and it is interesting. So would like to read about what are some of the common concepts used!

Regards,
Henry