Sei sulla pagina 1di 61

Nguyen

Thi Van Anh, PhD


Department of Pharmacological, Medical,
Agronomical Biotechnology
Contents
•  Random variables

•  Probability distributions of discrete variables:


-  Binominal distribution
-  Poisson distribution
-  Hypergeometric distribution

•  Probability distributions of random variables


-  Continuous probability distributions
-  The normal distribution
1. Random variables
•  Usually written X, is a variable whose possible values are
numerical outcomes of a random phenomenon

•  2 types: discrete and continuous


Discrete random variable
•  The one which may take on only 1 countable number of distinct
values (0, 1, 2…)

•  Usually (but not neccesarily) counts

•  Ex: Number of children, number of pilots/aircrafts


ConCnuous random variable
•  The one which takes an infinitive number of possible values

•  Usually measurements

•  Ex: Height, weight, airspeed....

•  Not defined at a specific values but over an interval of values

•  Represented by area under the curve (integral)


2. Probability distribuCon
2.1. Probability distributions
of discrete variables

Formula:
A table

RelaCve frequency

A graph
Probability distributions of discrete variables

2 essential properties:
Number of P (X = x) a)  What is the probability that a
program (x)
Randomly selected family used
1 0.2088
2 0.1582 three assistance programs?
3 0.1313 P(3) = P(X = 3) = 0.1313
4 0.1313
5 0.1953 b) What is the probability that a
6 0.1246
Randomly selected family used
7 0.0135
Either one or two programs?
8 0.0370
Total 1.0000 P(1U2) = P(1) + P(2)
= 0.2088 + 0.1582
= 0.3670
•  Cumulative Distributions
Cumulative frequency a)  What is the probability that a

Number of P (X ≤ x) randomly selected family used


program (x) ≤ 2 assistance programs?
1 0.2088
2 0.3670 P(X ≤ 2) = 0.3670
3 0.4983
4 0.6296 b) What is the probability that a
5 0.8249 randomly selected family used
6 0.9495 fewer than 4 programs?
7 0.9670
P(X < 4) = P(X ≤ 3) = 0.4983
8 1.0000
Cumulative frequency c) What is the probability that a

Number of P (X ≤ x) randomly selected family used


program (x) 5 or more assistance programs?
1 0.2088
2 0.3670 P(X ≥ 5) = 1 - P(X ≤ 4)
= 1- 0.6296 = 0.3704
3 0.4983
4 0.6296 b) What is the probability that a
5 0.8249 randomly selected family used
6 0.9495
between 3 and 5 programs?
7 0.9670
8 1.0000 P(3 ≤ X ≤ 5) = P(X ≤ 5) – P(X ≤ 2)
= 0.8249 – 0.3670
= 0.4579
•  Mean and Variance of Discrete Probability
Distributions

p(x): relaCve frequency

Standard deviation: SD = σ
2.2. Some special discrete probability
distribuCon

•  Binominal distribuCon

•  Poisson distribuCon

•  Hypergeometric distribuCon
2.2.1 The binomial distribution
The Bernoulli Process
Binomial Probability DistribuCon
n  A fixed number of observations (trials), n
n  e.g., 15 tosses of a coin; 20 patients; 1000 people surveyed
n  A binary outcome
n  e.g., head or tail in each toss of a coin; disease or no disease
n  Generally called “success” and “failure”
n  Probability of success is p, probability of failure is 1 – p
n  Constant probability for each observation
E.g.,Probability of getting a tail is the same each time tossing the coin
Example:

If we examine all birth records from the North Carolina State Center
for Health Statistics for the calendar year 2001, we find that 85.8%
of pregnancies had delivery in week 37 or later. We will refer to this
as a full-term birth. With that percentage, we can interpret the
probability of a recorded birth in week 37 or later as .858. If we
randomly select five birth records from this population, what is the
probability that exactly three of the records will be for full-term birth?
a full-term birth (F) as a “success”
a premature birth (P) as a “failure”
Code: 1 = Full-term birth, 0 = premature birth
•  Sample Procedure: Use of Combinations

Number of combinations:

x!: x factorial
Sample Procedure: Use of
Combinations

Example:
The data North Carolina State Center for Health Statistics show that
14% of mothers admitted to smoking 1 or more cigarettes per day
during pregnancy. If a random sample of size 10 is selected from this
population, what is the probability that it will contain exactly 4 mothers
Who admitted to smoking during pregnancy?
Binomial probability distribuCon
If you have only two possible outcomes (call them 1/0 or yes/no or
success/failure) in n independent trials, then the probability of exactly X
“successes”=
n = number of trials

⎛n⎞ X n− X
⎜ ⎟ p (1 − p )
X=# ⎝X⎠ 1-p = probability
successes
p= of failure
out of n
probability of
trials
success
Example

•  If I toss a coin 20 times, what’s the probability of


getting exactly 10 heads?

⎛ 20 ⎞ 10 10
⎜ ⎟(.5) (.5) = .176
⎝ 10 ⎠
•  The Binomial Parameters

2 parameters of binominal distributions: n, p

Mean and variance of binominal distributions:


Poisson distribu<on
A random variable x is said to have a Poisson distribution if
Poisson distribu<on
•  The poisson distribution is a limiting form of binominal distribution
When n è∞, p è0, np = µ remains constant.

•  Provides a good approximation of binominal distribution when


n > 20, p > 0.05
Hypergeometric distribuCon
Used to solve problems of sampling inspection without replacement
Hypergeometric distribuCon
Hypergeometric distribu<on
Mean:

Variance:
Hypergeometric distribu<on

Characteristics:

-  2 possible outcomes

-  Probability of success is not the same of each trial


without replacement, thus events are not independent

-  Population is finite

-  Trials are dependent


Hypergeometric distribu<on
Hypergeometric distribu<on
2.3. Continuous probability
distributions
•  Between any two values assumed by a continuous variable,
there exist an infinite number of values

•  As the number of observations, n, approaches infinity, and the


width of the class intervals approaches zero, the frequency
polygon approaches a smooth curve

•  Such smooth curves are used to represent graphically the


distribution of continuous random variables
•  Finding Area Under a Smooth Curve
P (a < x < b)
THE NORMAL DISTRIBUTION

•  The most important distribution, frequently


called the Gaussian distribution
Characteristics of the Normal Distribution

v It is symmetrical about its mean.

v The mean, the median, and the mode are all equal.

v The total area under the curve above the x-axis is one
square unit.
Characteristics of the Normal Distribution

The normal distribution is completely determined by the


parameters µ (location parameter) and σ (shape parameter)
The Standard Normal Distribution
•  Mean = 0 and Standard deviation = 1

•  Random variable:

Equation for standard normal distribution


Area under the curve between Z0 and Z1:

Use Table D to find results


Example:
P (z ≥ 2.71) = ?
•  Normal distribution APPLICATIONS

the normal distribution can be used to model the


distribution of many variables that are of interest
Example:

In a study of 529 normally developing children ages 8-15 years,


researchers found that the amount of time children spent in the
upright position followed a normal distribution with a mean of 5.4h
and SD = 1.3h. Find the probability that a child selected at random
spends less than 3h in the upright position?
The probability is .0322 that a randomly selected child will have
uptime of less than 3.0 hours
Example:

Z = (0.9-0)/0.45 = 2

P(x > 0.9) = P (z > 2) = 1 – 0.97725 = 0.02275

Potrebbero piacerti anche