Professional Documents
Culture Documents
)
Actual odds in favor of event A happening P(A)/(P( A
Pay-off odd against A = not profit : amount bet
Addition Rule Mutually Exclusive P(A or B) = P(A)+P(B)
Not Mutually Exclusive P(A or B) = P(A)-P(B)
Multiplication Rule Independent Event (Two events are independent if when A occurs, the prob B
occurs is not affected)
If the sample size is no more than 5% of the population, treat the selections as independent events
P(A and B) = P(A)*P(B)
Dependent Event: P(A and B) = P(A)*P(B\A)
(P(B\A) Conditional Probability is the probability that B occurs given A has occurred P(B\A)=P(A and
B)/P(A))
Complements P(at least x) = 1-P(at most x-1)
Permutation (order matters) 1. There are n different items available 2. Select r of the n items r<n 3.
Rearrangement of the same items to be different sequences
nPr=
n!
( nr ) !
Combination (order doesnt matter) 1. There are n different items available 2. Select r of the n items
r<n 3. Rearrangement of the same items to be same sequences
nCr=
hh
n!
( nr ) ! r !
Probability Distribution
(requirements: 1) P(x) = 1 and 2) 0 x 1)
Unusually high # if: P(x or more) 0.05 or +2
Unusually low # if: P(x or less) 0.05 or
+2
Binomial Prob Distribution
(requirements: 1) Procedure has a fixed # of trials n; 2) Trials are independent [sampling with
replacement or sample 5% of pop.); 3) Each trial must have two categories; and 4) The prob of
success remains the same)
P(exactly x=__) = binomPdf();
P(at least x=__) = 1-P(at most x-1) = 1-binomCdf();
P(at most x=__) = binomCdf();
Density Curve Continuous Random Variable (requirements: 1) The area under the curve equals 1;
2) Density curve sits on or above x-axis. Vertical height of zero or above.)
Uniform Distribution Probability Graph is a rectangle
Standart Normal Distribution Graph is bell-shaped
1. Sketch the normal curve, and label and ; 2. Label x values and shade the area desired; 3. Use the
calculator to find area (probability)
The functions used in the calculator is normalCdf() and invNorm()
The Central Limit Theorem:
x =
and
x = / n
1) If the original population is normally distributed, then for any sample size, the sample means are
normally distributed
2) If the original population is not normally distributed, then for a sample n>30, the sample means are
normally distributed
Normal as Approximation to Binomial (requirement: 1) Sample is a SRS; 2) np 5; 3) nq 5)
If r is left point of an interval x = r-0.5
>>> P(r __ ) = P(x __-0.5) = normalCdf()
If r is right point of an interval x = r+0.5 >>> P(r __ ) = P(x __+0.5) = normalCdf()
Ex) 1000 tickets are sold at $2 each for a prize valued at $650. What is the expected value of gain if a
person purchases one ticket?
GAIN
P(x)