STATISTICS AND PROBABILITY Discrete Probability Distribution/Probability Function -

consists of the values a random variable can assume

and the corresponding probabilities of the values.
RANDOM VARIABLES AND PROBABILITY
DISTRIBUTIONS
Mean and Variance
Random Variable
Variance of a Discrete Probability Distribution formula;
- function that associates a real number to each
σ2= Ʃ(x-μ)2 · P(x) or σ2 = Ʃx2 · P(x) – μ2
element sample space.
Standard Deviation of a Discrete Probability Distribution
- values are determined by chance.
formula;
- discrete random variable if it’s a set of possible
σ = Ʃ(x − μ)2 · P(x) or σ = Ʃx2 · P(x) – μ2
outcomes is countable. Mostly represent count data,
such as defective chairs produced in factory. x P(x) x*P(x) (x-µ) (x-µ)2 (x-µ)2*P(x)2
=Variance(σ2)
- continuous random variable of it takes values on
continuous scale. Often represent measured data such
as heights, weights and temperature. [Symbols – Mean(µ), Variance(σ2), Standard
Variance(σ)]
(Cardinality – number of outcomes.)
Mean - is the average of all possible values of X.
Measure of accuracy.
Probability of an Event
Variance – measures the degree to which the values of
Sample space(S) – set of all possible outcomes. Each X depart from the mean. The spread of distribution or
possible outcome/element of set is called point/sample standard variation. Measure of precision.
point.
Standard Variation – measure of variation of all values
Event – is any subset of a sample space. from the mean. Square root of variance.

Solution in finding the values of the random variables; E[X]= (x-µ)2*P(x)2

n(S)= nCr =n!/r!(n-r)!

Properties Probability Distribution

NORMAL DISTRIBUTION
1. Probability of each value of the random variable must
Normal curve
be between or equal to 0 & 1. In symbol, we write it as
0≤P(E)≤1. - bell-shaped shows the probability distribution of a
continuous random variable. It represents a normal
2. The sum of the probabilities of all values of the
distribution. It has a mean μ = 0 and standard deviation
random variables must be equal to 1. In symbol, we
ơ = 1. Its skewness is 0 and its kurtosis is 3. “The
write it as ∑P(E)=1.
skewness of a normal curve is 0 and its kurtosis is 3.”
(Histogram - graphical representation of the distribution
of data.)

Decision-making - this situation requires the use of

random variable and probability distribution.
 The following formula is used when sample is given.

Skewness - talks about the degree of symmetry of a The following formula is used when sample is not given.
curve. It is asymmetry in a statistical distribution, in
which the curve appears distorted or skewed either to
the left or to the right. It can be quantified to define the
extent to which a distribution differs from a normal
distribution.

Kurtosis - on the other hand, talks about the degree of

peakedness of a curve. It refers to the pointedness or
flatness of a peak in the distribution curve.

SAMPLING AND SAMPLING DISTRIBUTION

Sampling - process of getting the sample.

Statistics versus Parameter

Sample Statistic – any quantity computed from a sample

taken from a population with the intention of using this
quantity to estimate same but unknown quantities of
the population. The examples would be sample mean
zero (positive), Leptokurtic. and sample variance.
Zero (negative), Platykurtic. Parameter – a useful component of statistical analysis. It
(normal curve), Mesokurtic. refers to the characteristics that are used to define a
given population.
Learning the Probability Notations Under the
Statistic describes a sample while parameter describes a
Normal Curve - P(a < z < b) denotes the probability that population. In other words, statistic is used to estimate
the z-score is between a and b. a parameter.
P(z >a) denotes the probability that the z-score is
greater than a.
*Examples of a Parameter
P(z < a) denotes the probability that the z-score is less
than a. Population mean (μ)

P(a ≤ z ≤ b) = P(a < a < b) Population standard deviation (σ)

The Central Limit Theorem Population variance (σ2)

- it justifies the use of normal curve methods for a wide

range of problems. This theorem applies automatically
to sampling from infinite population.
*Examples of a Statistic 2. Convenience Sampling - selected from the population
only because they are conveniently available. Easy to
Population mean (μ)
recruit, and the researcher did not consider selecting a
Population standard deviation (σ) sample that represents the entire population.

Population variance (σ2) 3. Purposive Sampling - based purely on the

researcher’s knowledge and credibility. Choose only
those people who they deem fit to participate
Sampling 4. Snowball Sampling - when the sample size is small
Random Sampling - technique in which each member of and not easily available. This sampling system works like
the population is given equal chance from a population the referral program.
is called sample. 5. Judgemental Sampling - also called purposive
sampling, the sample members are chosen only on the
basis of the researcher’s knowledge and judgment.
*Probability Sampling

1. Simple Random Sampling - study from a larger group

(population). Each individual is chosen entirely by Two Types of Statistics
chance and each member of the population. As easy as 1. Descriptive Statistics - concerned with the gathering,
assigning numbers to the individuals (sample). classification and presentation of data and the
- Fishbowl method collection of summarizing values to describe group
characteristics of data.
- Lottery Method
2. Inferential Statistics - pertains to the methods dealing
2. Systematic Sampling - selection of elements from an with making inference, estimates or prediction about a
ordered sampling frame. Progression through the list is large set of data using the information gathered.
treated circularly, with a return to the top once the end
of the list is passed. “nth” individual to be a part of the
sample. Hypothesis
3. Stratified Sampling - divides the population into Hypothesis – when assumption is made using the
separate groups, called strata. Then, a probability sample.
sampling is drawn from each group. Where a larger
population can be divided into smaller groups. 1. Null Hypothesis (H0) – population is equal and it is
assumed equal.
4. Cluster Sampling - mutually homogeneous yet
internally heterogeneous groupings. The total 2. Alternative Hypothesis (Ha) – direct contradiction of
population is divided into groups called clusters a simple null hypothesis. Statement of inequality.
random sample of the group is selected. Random choice
*Test of Hypothesis – to test how true the hypothesis
of subgroup.
types of error:
5. Multistage Sampling - taking of samples in stages
using smaller and smaller sampling units at each stage.
A combination of stratified, cluster and simple random
sampling is used in multistage sampling technique.

*Level of Significance – probability that the null

*Non-probability sampling hypothesis is rejected by using the test statistics. Often
denoted α with values either 1%, 5%, or 10%.
1. Quota Sampling - convenience sample involving
individuals that represent a population.
*Rejection Region – set of region that cause rejection of
null hypothesis and the acceptance of alternative
hypothesis.

*Critical Value – what separates the rejection region

and non-rejection region. Can be obtain from Z or T
table.