Working as a Data Scientist at one of the biggest consultancies of the world I can just give my two cents which one is useful for a job like mine. All courses are cool and have applications both in research, development as well as consulting. However some courses might be more important for practical application. Disclaimer: This does not reflect the opinion of my employer and I have also only seen several departments in Germany.
THE MOST USEFUL COURSES:
- Introduction to Time Series
If you are working as a Data Scientist you will definitely make forecast occasionally. It is important that you understand patterns such as trends, unit roots, seasonalities, etc.
In practice you will be facing data with different frequencies such as monthly or quartely data.
Read Forecasting principle and practice in order to get an understanding of the applications of forecasting.
- Modern Statistical Prediction and Machine Learning
This course will raise your chances of getting a highly paid job. Machine Learning is correlated with higher salaries than classical statistics. It is definitely worth knowing things such as training and test data. You will always built a model and test it.
It is also due to the importance of Machine Learning that this page is called CrossValidated. hahahaha
- Linear Modeling: Theory and Applications
- Introduction to Econometric Analysis (Cross-enrollment between Stats & Econ)
These courses seem pretty similar to me. I presume both are mainly dealing with Longitudinal Data and Pannel Data. However Most regression problems you will face as a Data Scientist deal with Time Series. I just had one project with Heckman selection modell/ Tobit regression and some small stuff where I faced Count Data and Survival Analysis. Overall classification tasks are more widespread at my company than regression tasks.
You are most likely to work in a team with Mathematicians, Statisticians and Computer Scientists. They will not stick to econometric modells. Nonetheless a solid understanding of linear models and econometric analysis will help you to deal with time series and forecasting issues.
It also depends on the programming language you prefer. R (and even more particularly Stata) are very handy for regression models. Python is rather useful for other tasks.
As Michael Chernick already stated Microeconometric issues are widely used at insurances. If you work for in a life insurance department survival analysis will be crucial. However most data scientist do not face such tasks.
You can go through this applied econometric foundation course by UCLA and reflect in how far you will face such questions in your future job.
- Stochastic Processes (Random walks, discrete time Markov chains, Poisson processes)
This will be hardly useful as a Data Scientist. Maybe you can face such models if you are working in a Quantitative Finance department of a bank.
Game theory is a theoretical concept which is barely directly applied in practice. In economic and psychological research it might be helpful, however it is not in the classical scope of a data scientist.
Please don't hesitate to ask if I should be more specific about some courses.