Estimation error on apparent arbitrage, Applied Statistics

This question explores the effect of estimation error on apparent arbitrage opportunities in a controlled simulation setting. We simulate returns for N = 10 assets over T = 30 years. We will use the first 20 years for estimation and the selection of the hedge portfolio ("in-sample"), and the remaining 10 years as "out-of-sample" performance evaluation period. Start out with a market return RM that is normally distributed with mean μM = 0:05 and standard deviation σM = 0:15, and assume a risk-free rate Rf = 0. All assets follow the factor model Rn,t = αn + βnRM,t + εn,t, where we assume n = 1 for all n.

We will consider three sets of parameters for the return generating process.

1428_Estimation error on apparent arbitrage.png

For each parameterization, perform 100 simulations (data table) for returns on market-neutral zero-investment portfolios and report the average holding period mean return and how often you investment loses money over the performance evaluation period assuming that

i) You know the parameters of the return generating process and invest equal amounts in every stock with positive alpha and short equal amounts of every stock with negative alpha

ii) You estimate the parameters and invest $1 in the stock with the highest alpha (if there is one), and short $1 of the stock with the most negative alpha (if there is one)

iii) You estimate the parameters and invest equal amounts in every stock with positive alphas (if there are) and short equal amounts of every stock with negative alphas (if there are)

iv) You estimate the parameters and come up with a more sophisticated investment strategy. Compare and explain your findings.

Notes

  • Start out with fewer simulations in your data table until you are con dent everything works
  • Your investment should hedge out all market risk (using your best estimates)
  • Take great care programming the portfolio weights in (ii)-(iv). If everything is done right, changing parameters and running the simulations should not take much time.
Posted Date: 2/25/2013 12:22:20 AM | Location : United States







Related Discussions:- Estimation error on apparent arbitrage, Assignment Help, Ask Question on Estimation error on apparent arbitrage, Get Answer, Expert's Help, Estimation error on apparent arbitrage Discussions

Write discussion on Estimation error on apparent arbitrage
Your posts are moderated
Related Questions
for this proportion, use the +-2 rule of thumb to determine the 95 percent confidence interval. when asked if they are satisfied with their financial situation, .29 said "very sat

(1) What values can the response variable Y take in logistic regression, and hence what statistical distribution does Y follow? The response variable can take the value of either

Given a certain population there are various ways in which a sample may be drawn from it. The chart below illustrates this point: Figure 1 In  Judgem

(a) The Horton's initial infiltration capacity for a catchment is 204 mm/h and the constant infiltration value at saturation is 60 mm/h. For a rainfall in excess of 204 mm/h mainta

Make a decision about the given claim. Use only the rare event rule, and make subjective estimates to determine whether events are likely. For example, if the claim is that a coi

2.1 Modern hotels and certain establishments make use of an electronic door lock system. To open a door an electronic card is inserted into a slot. A green light indicates that the

Ask queFrom these studies, which of the following may be considered a variable that can have a probability distribution? [I] Percentage of Sub-Saharan Africans that smoke [II] Perc

discuss the mathematical test of adequacy of index number of formulae. prove algebraically that the laspeyre, paasche and fisher price index formulae satisfies this test. What is

Grouped data  For grouped data, the formula applied is  σ = Where f = frequency of the variable, μ= population mea

Q. Find relative maxima and minima? When finding relative maxima and minima in the Chapters absolute extrema problem, don't forget to use the first or second derivative test to