433 reputation
212
bio website
location
age
visits member for 1 year, 2 months
seen Apr 13 at 17:16

Mar
18
accepted Normally Distributed Returns Become Leptokurtic Due to Compounding
Mar
13
comment Normally Distributed Returns Become Leptokurtic Due to Compounding
Hi Richard, no I simply multiply 1 with (1+norm.inv(rand(),0,1)*......*(1+norm.inv(rand(),0,1). From the graph that shows compounded returns, you can easily tell that distributions doesn't look "bell-shaped" anymore. The values are more clumped in the middle. The range of extreme values is much larger. To Josh's response, yea I am trying to model the returns as they compounded in real markets. $100, up 2%, down 1.6 -->100(1+.02)(1+.016).
Mar
12
comment Why was NASDAQ(or other index) not fluctuating in 70s and 80s?
You need to log the chart. Your not going to see the price if it's either not inflation adjusted or logged.
Mar
12
asked Normally Distributed Returns Become Leptokurtic Due to Compounding
Mar
7
asked Wiener process proof
Feb
27
awarded  Benefactor
Feb
21
awarded  Promoter
Feb
20
asked Directional View of Volatility
Feb
3
awarded  Yearling
Jan
15
awarded  Popular Question
Jan
1
comment Random Brownian Simulation Startling Results
Thx peter. I gussed it had nothing to do with the random generation. This game is based on the nfl office pool I played. Thought it would be interesting to run the simulation.
Dec
15
asked Random Brownian Simulation Startling Results
Dec
13
comment Scaling Intervals in Diffusion Process
If I have an annual mean of $μ=10%$ and vol of $σ$=20% and I am trying to simulate potential asset paths over a 6 future month period in 2 months steps, so 3 steps total, $dt$ would be 1/3 but that would erroneously scaling an annual figure to quarterly returns and vol.
Dec
13
comment Scaling Intervals in Diffusion Process
Hi Hardy, I appreciate your patience and time in helping answer my question. I edited my post. I total forgot about the random component in $$dW_t=σN(0,1)dt^{1/2}$$ drawn from a normal distribution. In regards to the second part of your answer, so essentially what your doing is scaling the daily mean/vol to annual so they can be inputted into the model. Am I correct? If so, what is the relationship between $μ$,$σ$, and $dt$..
Dec
13
revised Scaling Intervals in Diffusion Process
added 6 characters in body
Dec
13
awarded  Notable Question
Dec
13
asked Scaling Intervals in Diffusion Process
Dec
13
accepted Valuation of a Sinking Bond Fund
Nov
22
awarded  Tumbleweed
Nov
21
awarded  Popular Question