Professional Documents
Culture Documents
is computed as
For population values, x1, x2, , xN, the population mean is computed as
For multiperiod returns R1, R2, , Rn, the geometric mean return GR is computed as
where n is the number of multiperiod returns.
For growth rates g1, g2, , gn, the average growth rate Gg is computed as:
where n is the number of multiperiod growth rates.
For observations x1, x2, , xn, the average growth rate Gg is computed as:
where n 1 is the number of distinct growth rates. Note that only the first and last observations are
needed in the time series due to cancellations in the formula.
Measures if dispersion
Mean absolute deviation
The mean absolute deviation (MAD) is an average of the absolute differences between the
observations and the mean
For sample values, x1, x2, , xn, the sample MAD is computed as
For population values, x1, x2, , xn, the population MAD is computed as
For population values, x1, x2, , xN, the population variance 2 and thepopulation standard
deviation are computed as
The Sharpe ratio measures the extra reward per unit of risk. The Sharpe ratio for an investment I is
computed as:
where I is the mean return for the investment, f is the mean return for a risk-free asset such as a
Treasury bill (T-bill), and sI is the standard deviation for the investment.
CHEBYSHEV'S THEOREM
For any data set, the proportion of observations that lie within k standard deviations from the mean is at
least 1 1/k2, where k is any number greater than 1.
Grouped data
CALCULATING THE MEAN AND THE VARIANCE FOR A FREQUENCY DISTRIBUTION
where mi and fi are the midpoint and the frequency of the ith class, respectively. The standard deviation is
the positive square root of the variance.
THE WEIGHTED MEAN
Let w1, w2, , wn denote the weights of the sample observations x1, x2, , xn such that w1 + w2 +
+ wn = 1. The weighted mean for the sample is computed as
= wixi.
The weighted mean for the population is computed similarly.
THE COVARIANCE
For values (x1, y1), (x2, y2), , (xn, yn), the sample covariance sxy is computed as
For values (x1, y1), (x2, y2), , (xN, yN), the population covariance xyis computed as
Note: As in the case of the sample variance, the sample covariance uses n 1 rather than n in the
denominator.
The complement rule states that the probability of the complement of an event, P(A ), is equal to one
c
BAYES' THEOREM
Given a set of prior probabilities for an event of interest, upon the arrival of new information, the rule for
updating the probability of the event is Bayes' theorem. Here P(B) is the prior probability and P(B|A) is
the posterior probability:
or equivalently,
The number of ways to choose x objects from a total of n objects, where the order in which the x objects
are listed does not matter, is calculated using the combination formula:
Given two random variables X and Y, the expected value of their sum, E(X + Y), is equal to the sum of
their individual expected values, E(X) andE(Y), or
Using algebra, it can be shown that the variance of the sum of two random variables, Var(X + Y), yields
where Cov is the covariance between the random variables X and Y.
For given constants a and b, the above results are extended as:
Given a portfolio with two assets, Asset A and Asset B, the expected return of the portfolio E(Rp) is
computed as
where wA and wB are the portfolio weights wA + wB = 1 and E(RA) andE(RB) are the expected returns on
assets A and B, respectively.
PORTFOLIO VARIANCE
The portfolio variance,
, is calculated as
or, equivalently,
where 2A and 2B are the variances of the returns for Asset A and Asset B, respectively, AB is the
covariance between the returns for Asset A and Asset B, and AB is the correlation coefficient between the
returns for Asset A and Asset B.
binomial random variable X is defined as the number of successes achieved in the n trials of a
Bernoulli process. A binomial probability distribution shows the probabilities associated with the
possible values of the binomial random variable.
THE BINOMIAL PROBABILITY DISTRIBUTION
For a binomial random variable X, the probability of x successes in n Bernoulli trials is
for x = 0, 1, 2, , n. By definition,
EXPECTED VALUE, VARIANCE, AND STANDARD DEVIATION OF A BINOMIAL RANDOM VARIABLE
If X is a binomial random variable, then
for x = 0, 1, 2, , where is the mean number of successes and e 2.718 is the base of the natural
logarithm.
EXPECTED VALUE, VARIANCE, AND STANDARD DEVIATION OF A POISSON RANDOM VARIABLE
If X is a Poisson random variable, then
where a and b represent the lower and upper limits of values, respectively, that the random variable
assumes.
The expected value and the standard deviation of X are computed as
Z=(X-MU )/ Sigma
where equals approximately 3.14159 and exp(x) = ex is the exponential function where e 2.718 is the
base of the natural logarithm.
STANDARD NORMAL DISTRIBUTION
A standard normal random variable Z is a normal random variable withE(Z) = 0 and SD(Z) = 1.
The z table provides cumulative probabilities P(Z z) for positive and for negative values of z.
equals
the population standard deviation divided by the square root of the sample size, or
is normal we can transform it into the standard normal random variable as:
on
For any population X with expected value and standard deviation , the sampling distribution of will
be approximately normal if the sample size n is sufficiently large. As a general guideline, the normal
distribution approximation is justified when n 30.
As before, if
equals
on
The transformation of
. The resulting
to Z is made accordingly.
THE T DISTRIBUTION
If repeated samples of size n are taken from a normal population with a finite variance, then the
statistic
, where