Archiving Research Data

Brian Lavoie discusses the effort needed to preserve raw research data .

-DD

Data Analysis Project Failures

Mary Branscombe explains the causes of common failures in data analysis projects :

1. Assuming your data is ready to use — and all you need
2. Not exploring your data set before starting work
3. Expecting too much
4. Not using a control group to test your new data model in action
5. Starting with targets rather than hypotheses
6. Letting your data model go stale
7. Automating without monitoring the final outcome
8. Forgetting the business experts
9. Picking too complex a tool
10. Reusing implementations that don’t fit your problem
11. Misunderstanding fundamentals like causation and cross validation
12. Underestimating what users can understand

Note: A free registration is required to read this article.

-DD

Data Scientists' Role

Katherine Noyes suggests that data scientists spend too much time cleaning and organizing when they should be developing new algorithms.

-DD

Care of Flash Memory Devices

Kingston has a very good guide on "Caring for Your Flash Memory." One tip that is not mentioned, but that I discovered on my own: If your computer offers to correct possible file corruption on your drive, do a backup of your data before running any "repair" utility. I discovered that after I ran the Windows utility, the drive was unusable.

-DD