IAI Actuarial Core Principles · Economic Modelling · Stochastic models for security prices
In a discrete-time model for a share price, the log-return over each year is assumed to be independent and normally distributed with the same mean and variance. Which statement about the share price process is correct?
The price is lognormally distributed. The log of the price is a sum of independent normal log-returns, so it is normal, and exponentiating gives a lognormal price that cannot be negative.
- AThe price at each future time is normally distributed
- BThe price at each future time is lognormally distributedCorrect
- CThe price at each future time is exponentially distributed
- DThe price can become negative with positive probability
- The price has a Poisson distribution at each future time
Explanation
If log-returns are independent normal, the log of the price is a sum of normal variables and so is normal. The price is the exponential of a normal variable, hence lognormal and always positive. Normality of the price itself would allow negative values, which this model does not.
Did you get it right without looking?
One question tells you little. A timed set on Stochastic models for security prices shows your real accuracy, how long you take and where you lose marks.
More Stochastic models for security prices questions
- A stock follows dS = μS dt + σS dW with μ = 0.12 and σ = 0.20. Using Ito's lemma, what is the drift per year of ln S(t)?
- In the Ito multiplication rules used with Ito's lemma, which set of results is correct for small dt?
- A security price follows geometric Brownian motion dS = μS dt + σS dW under the real-world measure. Which statement about the distribution o…
- A non-dividend-paying share trades at Rs 100. Under Black-Scholes, for a European call with strike Rs 100, maturity 1 year, risk-free force …
- A non-dividend-paying share trades at Rs 100. A European call with strike Rs 100 and one year to expiry is priced under Black-Scholes with a…
- A share price follows GBM with μ = 8% and σ = 25% p.a. For a 1-year horizon, which pair gives the variance of ln(S_1/S_0) and the probabilit…