Checkpoint: Market Data and Statistics
Quiz
- Which set lists the three inputs every testable quantitative strategy needs?
- Data, rules, and costs
- Costs, forecasts, and news headlines
- Rules, leverage, and luck
- Data, opinions, and intuition
- A rule says: "Buy at today's open if today's close is higher than today's open." What is the main problem with this rule?
- It uses lookahead bias, because at the open you do not yet know the close
- It ignores commission but nothing else
- It is an opinion rather than a rule
- It has no position sizing rule
- In yfinance, which setting returns prices already adjusted for splits and dividends?
- progress=False
- auto_adjust=True
- tz_localize(None)
- keep="last"
- Your cleaned price series has 6 isolated single-day holes and one 40-day stretch of missing closes. What is the correct handling?
- Forward fill the 6 isolated days with a limit, and leave the 40-day stretch unfilled and flagged
- Replace every missing close with zero
- Drop all rows with missing values without counting them
- Forward fill everything, including the 40-day stretch
- A price goes from 100 to 105 on day one, then from 105 to 110 on day two. What is true about the returns?
- The two daily simple returns are equal and sum to the total simple return
- Simple returns add across time, so the total is 10%
- Log returns must be multiplied to get the total
- The two daily log returns are equal and sum to ln(110/100)
- To annualize a daily volatility, you multiply it by the square root of ____, which is about 15.87.
- The gap between the price a backtest assumed and the price an order actually fills at is called ____.
- Describe in your own words how you would take one ticker from a raw download to a return column and a volatility number you can defend. Mention the cleaning steps, the return type you chose, and how you annualized volatility.
Sign in to submit answers.