Introduction

Data science is to deal with data, from all apspects. Data science combines math and statistics, mathematics, computation, data analytics and artificial intelligence (AI) to unfold insightful information and knowledge from data.

Motivation

As a statistican, we always think about the data. Often times, we think the data is there, being cleaned and with good format. Data science is important because it combines methods and technqies to generate meaningful things from data.

Towards Data Science

It is somehow a funny question to ask: to be or not to be. Data Science is truly interdisciplinary and challenging.

• Towards Data Science: Be a statistician

  • A perspective of data generation mechanism.

  • A probabilistic framework for modeling and inference.

• Towards Data Science: Not Just be a statistician

  • A perspective of system thinking.

  • A close loop of data-modeling-decision.

Summary

Form a statistical perspective, a key of doing research in data science is to understand the data generation mechanism. It will enable model inference, model prediction, and data-driven decision making (optimization).