A trader cannot deploy the statement that a chart looks predictable. The desk needs a rule specifying what is known, what is forecast, what gets traded and what evidence would justify stopping. This lesson converts an investment idea into that research contract. It extends the quantitative investment process by making the discovery stage auditable before a performance curve exists.
Learning objectives. By the end of this note you should be able to:
- distinguish an economic mechanism, a statistical prediction and a trading rule;
- specify decision time, universe, target, horizon and falsification criteria;
- construct a baseline and a mechanism-specific negative control;
- calculate the difference between predictive success and economic success;
- record a hypothesis revision without disguising it as independent confirmation.
In this lesson
- Begin with a claim that can fail
- Three objects, three questions
- Write the research contract
- Falsification and useful controls
- Keep discovery separate from confirmation
Before you start
The full lesson, with worked examples and exercise solutions, is for members.
Read the full lessonNew to SelfMadeQuant.com? See membership options or browse the Quantitative Research, Data and Backtesting syllabus.