Which Discipline is More Useful for Quantitative Trading: Statistics or Computer Science?
When it comes to quantitative trading, many practitioners might argue that either statistics or computer science is more useful. In my experience, the answer depends on the perspective of the practitioner. However, a comprehensive understanding of both disciplines is vital for success.
Why Statistics Reigns Supreme
Statistics serves as the backbone of analysis in quantitative trading, providing a fundamental understanding of why certain strategies work. While coding is a valuable tool that helps with 'how' to implement these strategies, statistics offers the 'why' that is essential for effective trading. The utility of statistics in this field cannot be overstated.
The Myth of Coding Dominance
It's a common misconception that computer science is the primary driver in quantitative trading. While it's true that coding is crucial for developing algorithms and managing data infrastructure, statistics is equally important for analyzing financial data and developing sophisticated trading strategies. Both disciplines are indispensable.
Misunderstandings and Definitions
The term 'quantitative trading' is loaded with ambiguity. Its meaning varies significantly depending on the context:
To people with institutional trading experience, 'quantitative trading' refers to the development of systems that rely on statistical inputs and innovative data usage for achieving a competitive edge.
To those with retail trading experience, it's associated with the use of prepackaged 'bots' that make trades based on traditional technical indicators like RSI, DMA, and moving average crossovers. While these tools are not ineffective, they do not capture the full essence of quantitative trading.
To those with no trading experience, quantitative trading is often perceived as trading with complex algorithms and computers. This oversimplification overlooks the strategic and analytical components that are integral to the practice.
The prevailing belief that all trading is done with computers and algorithms is true, but it fails to recognize the multifaceted nature of quantitative trading. The New York Stock Exchange (NYSE) is indeed a collection of computers in a data center in New Jersey, but that doesn't equate to quantitative trading.
Quantitative Trading: A Unique Discipline
Despite the differing definitions and perceptions, it's beneficial to view quantitative trading as its own distinct discipline. While it shares similarities with computer science and data science, it cannot be fully defined by either. Instead, it combines the strengths of both to create a unique set of skills and strategies.
Combining Skills for Success
To excel in quantitative trading, one must understand the nuances of both statistics and computer science. Here are some key areas where these disciplines intersect and complement each other:
Data Analysis: Statistics provides the tools and methods necessary for analyzing large financial datasets. Computer science helps in managing and processing these datasets efficiently.
Algorithm Development: Both disciplines are crucial in developing algorithms that can make informed trading decisions. Statistics ensures that these algorithms are statistically sound, while computer science focuses on their implementation.
Information Advantages: Combining statistical insights with computational power can lead to new and unique ways of obtaining information advantages in the market.
Conclusion
While there may be debates about which discipline is more useful, the reality is that both statistics and computer science are essential for quantitative trading. Success in this field requires a deep understanding of both domains and an ability to apply them in a cohesive manner.
For a more in-depth exploration of quantitative trading, you can check out my Quora profile and other resources that delve into this fascinating intersection of finance, statistics, and computer science.