STATISTICS AND PROBABILITY

❖​ Qualitative Variables
Statistics (Categorical Variable)
- A branch of applied mathematics - classified according to
which deals with the collection, some attributes or
organization, presentation, categories e.g. Marital
analysis and interpretation of status and Gender ❖​ Interval
data ❖​ Quantitative Variable ➢​ The Difference
❖​ Descriptive Statistics - (Numerical) between measurement
Summarizes or describes - variables that are is a meaningful quantity
the important classified according to but does not involve a
characteristics of a known numerical true zero point
set of data characteristics e.g. ➢​ Example:
❖​ Inferential Statistics - Number of Child and
Consist of generalizing Age
from samples to ➢​ Continuous Variable -
populations, performing assume any if an
hypothesis testing, infinite numbers of
determining relationship values and can be
among variables, and associated with points ❖​ Ratio
making predictions on a continuous line ➢​ Differs from interval
Population interval (ex: Height & measurement only in
- consist of al member of a Weight) one aspect; it has true
group being studied ➢​ Discrete Variable zero point
Sample -consist of either a finite ➢​ Example: Money,
- a portion or part of the number of values or Weight, Distance, Age
population of interest selected countable number of Interval Vs. Ratio
for analysis values (ex: Population ➢​ Interval Data can
Parameter of a City) include numerical data
- a numerical index describing Level of Measurement that does not use zero
a characteristics of a ❖​ Nominal sa reference, such as
population ➢​ classifies data into age ranges income
Statistic various distinct range, data range and
- a numerical index describing categories in which no more
a characteristic of a sample ranking is implied. It ➢​ Ratio Data includes
Source of Data indicates distinction variables like income,
❖​ Primary Data - data that ➢​ Example: weight, annual sales,
comes from an original unemployment rate and
source, and intended to more
answer specific questions. PROBABILITY
It can be taken by DISTRIBUTION OF
interview, mail-in DISCRETE RANDOM
questionnaires, survey, or VARIABLES
❖​ Ordinal
experimentation
➢​ classifies data into Property of discrete random
❖​ Secondary Data - Data
distinct categories in variables
that are taken from
which ranking is implied 1.​ The sum of all
previously recorded data.
➢​ Example: probabilities should be
Experimental Classification
- A research may classify variables 1 𝑃(𝑥) = 1
according to purpose whether
experimental or mathematical
 2.​ Probabilities should be Measures of Dispersion 4.The width of the curve is
confined between zero - Measures that describe the determined by the standard
and 1 0 ≤ 𝑃(𝑥) ≤ 1 spread of the data deviation of the distribution.
Discrete Random Variables - Mean (average), Median, 5.The tail of the curve is
- consist of the values a Mode always approaching the
random variable can assume horizontal axis but never
and the corresponding Variance touching it. “The curve is
probabilities - The expected value of the asymptotic” to the baseline.
squared variation of a 6.The area under the curve is
random variable from its 1
mean value
Formula for the Variance and Empirical Rule
Standard Deviation: - A statistical rule which
2 2
σ = Σ(χ − µ) · 𝑃(𝑥) states that for a normal
distribution, almost al
Discrete Probability observed data will fall within
Distribution: three standard deviation of
2 2 the mean
σ = Σ(χ − µ) · 𝑃(𝑥) - it is often used in statistics
for forecasting outcome
Normal Random - this can be used as a
Mean and variance of
DIstribution rough estimate of the
discrete random variable
outcome of the impending
Mean of Probability Normal Distribution data to be collected and
distribution - also known as Gaussian analyzed
➢​ The mean in considered Distribution
as the measure of the - A probability distribution that ❖​ One standard deviation
central location if a random is symmetric about the mean of the mean is
variable - If a distribution consists of a approximately 0.68
➢​ The expected value or very large number of cases (68%). “𝜇 − 𝜎 < 𝑥 < 𝜇 +
mean value of a discrete and the three measures of 𝜎”
random variable x can be averages (mean, median, ❖​ Two standard
computed by multiplying mode) are equal, then the deviations of the mean
the probability of observing distribution is symmetrical is approximately 0.95
that value and then adding and the skewness is zero. (95%). “𝜇 −2 𝜎 < 𝑥 < 𝜇
the resulting quantities - The shape and position of the
+ 2𝜎”
normal distribution curve
µ = Σ𝑥 · 𝑝(𝑥) ❖​ Three standard
depend on two parameters, the
µ = Mean of the probability deviations of the mean
mean and the standard
is approximately 0.997
distribution deviation.
( 99.7%). “𝜇 −3 𝜎 < 𝑥 <
X = values of random variable
P(x) = corresponding PROPERTIES OF A NORMAL
𝜇 + 3𝜎”
probabilities DISTRIBUTION
Σ = Summation 1.The distribution curve is
Measures of Central bell-shaped.
Tendencies 2.The curve is symmetrical
- Measures that indicate the about its center.
approximate center of 3.The mean median and mode
distribution coincide at the center.