λ λ σ μ) σ σ μ π σ σ π π σ μ0 μ π π σ σ π

advertisement

Formulas for Statistics I

The i th

quartile is at position (i

×

(n +1))/4

Bayes’ Theorem:

P(B|A) = [P(A|B)

×

P(B)]

÷

P(A), where P(A) = P(A|B)

×

P(B) + P(A|B’)

×

P(B’)

The binomial probability of x successes in n trials:

P(x) = n

C x

π x

(1 -

π

)

(n-x)

where n

C x

represents combinations of n things taken x at a time; n

C x

=

( n

− n !

x )!

x !

.

The Poisson probability of x successes in an interval of length t:

λ x

P ( x )

=

λ x e

− λ x !

= e

λ x !

where

λ

= r

×

t, r the rate of occurrence and t the length of the interval

The exponential probability that the first success will not occur until after an interval of length t

0

:

P(t

t

0

) = e

-

λ where

λ

= r

×

t

0

and successes follow a Poisson distribution.

For the normal distribution z

=

( x

σ

μ

)

The SamplingDistribution of : The Sampling Distribution of p:

E ( x )

= μ σ x

=

σ n s x

= s n

E(p) =

π σ p

=

π ×

( 1

− n

π

)

Confidence intervals for

μ

: x

± z

C

× σ x

OR x

± t

C

× s x where C is the confidence level, and the t value has n – 1 degrees of freedom

Confidence interval for

π

: p

± z

C

× s p s p

= p

×

( 1

− n p )

To find the minimum necessary sample size: n

=

⎡ ×

⎢⎣ z e

σ ⎤

⎥⎦

2

OR n

= z

2 × π ×

( 1

− e

2

π

)

For hypothesis tests about

μ

: For hypothesis tests about

π

: z

= x

σ x

μ

0

OR t

= x

− s x

μ

0 z

= p

σ

− π p

σ p

=

π

0

×

( 1

− π

0

) n

Download