I start explaining some concepts I have learned. After finishing with Coursera course "The Data Scientist’s Toolbox".
I learned the basics of data analysis. An interesting topic was the "6 Types of Data Science Questions". These are described below:
1. Descriptive Data Analysis:
It's the first kind of data analysis performed when you just describe/visualize a set of data.
2. Exploratory Data Analysis
When you find relations you didn't know about, exploratory models are used for discovering new connections. Exploratory analyses alone should not be used for generalizing/predicting because correlation does not imply causation.
3. Inferential Analysis
When you use a relatively small sample of data to say something about a bigger population. Using inference, you estimate both the quantity you care about and your uncertainty about your estimate. An example could be an analysis of the "Effect of Air Pollution on Life Expectancy".
4. Predictive Analysis
When you use the data on some objects to predict values for another object. Also prediction does not imply causation.
5. Causal Analysis
When you need to find out what happens to one variable when you make another variable change. Usually randomized studies are required to identify causation. Causal relationships may not apply to every individual. Causal models are said to be the "gold standard" for data analysis.
6. Mechanistic Analysis
When you need to understand the exact changes in variables that lead to changes in other variables for individual objects. It's hard to infer and usually modeled by a deterministic set of equations (physical/engineering).