STATS 3rd QTR

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 6

STATISTICS & PROBABILITY: NORMAL DISTRIBUTION

STANDARD NORMAL DISTRIBUTION | STANDARDIZING NORMAL DISTRIBUTION | SAMPLING THEORY


SHS | STEM | SECOND SEMESTER | 2023
NORMAL DISTRIBUTION standard deviation corresponds to a wider
Normal Random  a type of curve.
Variable continuous 8. In general, the graph of a normal
variable distribution is a bell-shaped curve with
 values are two inflection points, one on the left and
distributed another on the right.
normally o Inflection Point – points that
 majority of the mark the change in the curve’s
values are concavity
close to the 9. Each inflection point of the normal curve
mean or is one standard deviation away from the
expected mean.
value with 10. The standard deviation precisely
only few describes the spread of the normal curve.
values that
are extremely Three Types of Kurtosis
smaller and 1) Leptokurtic  a distribution where values are
extremely clustered heavily or pile up in
larger the center.
2) Mesokurtic  an intermediate distribution
which are neither too peaked
Normal Curve  bell-shaped curve nor too flat
of the graph for 3) Platykurtic  a flat distribution with values
normal more evenly distributed about
the center with broad humps
distribution.
and shot tails.

STANDARD NORMAL DISTRIBUTION


 The normal variable is standardized wherein
the mean is set at 0 and the standard
deviation as 1.
 Has a specific value for the mean
 its equation can be determined by simply
substituting 𝜇 = 0 and 𝜎 = 1 in the normal
graph of a normal distribution density function.

PROPERTIES OF A NORMAL DISTRIBUTION Z-TABLE


1. The graph is a bell-shaped (continuous)  The table used to summarize the
curve with the domain −∞ < 𝑥 < ∞. approximate areas under the standard
2. The graph is asymptotic to the x-axis normal curve, given in four decimal places.
(close but will never equal to zero).  the values given in the table represents the
3. The maximum point on the curve occurs area under the standard normal curve from 0
at 𝑥 = 𝜇 (mean). (the mean).
4. The graph is symmetrical about the line  In symbols, this is written as:
𝑥 = 𝜇. 𝝓(𝒛) = 𝑷(𝟎 ≤ 𝒁 ≤ 𝒛)
5. The median and mode of the distribution
are also located at the center of the CASES
graph. In a normal distribution mean, Basic Case: 0 to z 𝑷(𝟎 ≤ 𝒁 ≤ 𝒛) = 𝝓(𝒛)
mode, and median are equal.
6. The total area under the curve above the
horizontal/x-axis is equal to 1.
7. The standard deviation affects both the
width and the height of the curve. A larger
STATISTICS & PROBABILITY: NORMAL DISTRIBUTION
STANDARD NORMAL DISTRIBUTION | STANDARDIZING NORMAL DISTRIBUTION | SAMPLING THEORY
SHS | STEM | SECOND SEMESTER | 2023
Examples: 1. Find the area
1. Find the area under the curve
under the and between
standard normal 𝑧 = −1.25
curve between 0 and 𝑧 = 0.74.
to 1.85
Case 1:
Basic Case:
𝑃(−𝑧1 ≤ 𝑍 ≤ 𝑧2 )
𝑃(0 ≤ 𝑍 ≤ 𝑧) = 𝜙(𝑧)
= 𝜙(𝑧1 ) + 𝜙(𝑧2 )
𝑃(0 ≤ 𝑍 ≤ 1.85) = 𝜙(1.85)
= 0.4678
= 𝟒𝟔. 𝟕𝟖% 𝑃(−1.25 ≤ 𝑍 ≤ .74)
= 𝜙(1.25) + 𝜙(. 74)
= 0.3944 + 0.2704
2. Find the area
= 0.6648
under the normal = 𝟔𝟔. 𝟒𝟖%
distribution
between -2.33 2. Find the area
and 0. Draw the under the curve
region and between
corresponding to 𝑧 = −0.48 and
the given 𝑧 = 3.09.
standard normal
score. Case 1:
𝑃(−𝑧1 ≤ 𝑍 ≤ 𝑧2 )
Basic Case: = 𝜙(𝑧1 ) + 𝜙(𝑧2 )
𝑃(𝑧 ≤ 𝑍 ≤ 0) = 𝜙(𝑧)
𝑃(−0.48 ≤ 𝑍 ≤ 3.09)
𝑃(−2.33 ≤ 𝑍 ≤ 0) = 𝜙(2.33) = 𝜙(0.48) + 𝜙(3.09)
= 0.4901 = 0.1844 + 0.4990
= 𝟒𝟗. 𝟎𝟏% = 0.6848
= 𝟔𝟖. 𝟒𝟖%
Case 1: Two Values  When the two
on Opposite Sides of endpoints are Case 2: Two Values  When the two
𝑧=0 located on on the Same Side of endpoints are
opposite sides of 𝑧=0 located on same
the mean the sides of the mean
individual the individual
probabilities from probabilities from
0 are added. 0 are subtracted.
𝑷(−𝒛𝟏 ≤ 𝒁 ≤ 𝒛𝟐 )
2.1 Both Due Right
= 𝝓(𝒛𝟏 ) + 𝝓(𝒛𝟐 )
𝑷(𝒛𝟏 ≤ 𝒁 ≤ 𝒛𝟐 )
= 𝝓(𝒛𝟐 ) − 𝝓(𝒛𝟏 )

 Is used if the
given values are  Is used when the
negative and given values are
positive. both positive.

Examples:
STATISTICS & PROBABILITY: NORMAL DISTRIBUTION
STANDARD NORMAL DISTRIBUTION | STANDARDIZING NORMAL DISTRIBUTION | SAMPLING THEORY
SHS | STEM | SECOND SEMESTER | 2023
2.2 Both Due Left 3.1 Opposite Sides
𝑷(−𝒛𝟏 ≤ 𝒁 ≤ −𝒛𝟐 ) 𝑷(−∞ < 𝒁 ≤ 𝒛)
= 𝝓(𝒛𝟏 ) − 𝝓(𝒛𝟐 ) = 𝟎. 𝟓 + 𝝓(𝒛)

 Is used if the
 Is used when the given value is
given values are positive and we
both negative. are looking for the
probability of
Examples: numbers less than
1. A standard the given value
normal score is being chosen
selected at which includes
random. What is negative values
the probability
that It falls 𝑷(−𝒛 ≤ 𝒁 < ∞)
between 1.15 = 𝟎. 𝟓 + 𝝓(𝒛)
and 2.49?
Case 2.1:
𝑃(𝑧1 ≤ 𝑍 ≤ 𝑧2 )
= 𝜙(𝑧2 ) − 𝜙(𝑧1 )

𝑃(1.15 ≤ 𝑍 ≤ 2.49)
= 𝜙(2.49) − 𝜙(1.15)
= 0.4936 − 0.3749
= 0.1187
= 𝟏𝟏. 𝟖𝟕% 3.2 Same Side
2. Find the area 𝑷(∞ < 𝒁 ≤ 𝒛)
under the curve = 𝟎. 𝟓 − 𝝓(𝒛)
and between
𝑧 = −2.21 and 𝑷(−𝒛 ≤ 𝒁 < −∞)
𝑧 = −0.50. = 𝟎. 𝟓 − 𝝓(𝒛)
Case 2.2:
𝑃(−𝑧1 ≤ 𝑍 ≤ −𝑧2 )  Is used if the
= 𝜙(𝑧1 ) − 𝜙(𝑧2 ) given value is
𝑃(−2.21 ≤ 𝑍 ≤ −0.50) positive and the
= 𝜙(2.21) + 𝜙(0.50) area we are
= 0.4864 + 0.1915 looking for
= 0.2949 includes numbers
= 𝟐𝟗. 𝟒𝟗% greater than 2.09

Case 3: Normal  You either add or Examples:


Curve’s Extremities subtract the 1. Find the
corresponding are probability that a
or possibility of number chosen
the z-score from at random on the
0.5. standard normal
STATISTICS & PROBABILITY: NORMAL DISTRIBUTION
STANDARD NORMAL DISTRIBUTION | STANDARDIZING NORMAL DISTRIBUTION | SAMPLING THEORY
SHS | STEM | SECOND SEMESTER | 2023
scores is less 7−4
=
than 1.73. 2
3
Case 3.1: =
𝑃(−∞ ≤ 𝑍 ≤ 𝑧) 2
= 0.5 + 𝜙(𝑧)
𝒛 = 𝟏. 𝟓
𝑃(−∞ ≤ 𝑍 ≤ 1.73) = 0.5 + 𝜙(1.73)
= 0.5 + 0.4582
= 0.9582 2. A normal distribution has a mean of 10.2
= 𝟗𝟓. 𝟖𝟐% and a standard deviation of 1.8. Find
P(4.8 ≤ 𝑋 ≤ 12).
2. Find the Convert the following raw scores:
probability that a 𝑥1 = 4.8 𝑥2 = 12
standard normal
𝑥−𝜇 𝑥−𝜇
score is less than 𝑧= 𝑧=
𝜎 𝜎
-0.18 4.8 − 10.2 12 − 10.2
Case 3.2: = =
1.8 1.8
𝑃(−∞ ≤ 𝑍 ≤ −𝑧)
= 0.5 − 𝜙(𝑧)
𝒛𝟏 = −𝟑 𝒛𝟐 = 𝟏
𝑃(−∞ ≤ 𝑍 ≤ −0.18) = 0.5 − 𝜙(0.18)
= 0.5 + 0.0714 𝑷(−𝟑 ≤ 𝒁 ≤ 𝟏)
= 0.4246
Case 1: 𝑃(−𝑧1 ≤ 𝑍 ≤ 𝑧2 ) = 𝜙(𝑧1 ) + 𝜙(𝑧2 )
= 𝟒𝟐. 𝟖𝟔%

𝑃(−3 ≤ 𝑍 ≤ 1) = 𝜙(3) + 𝜙(1)


3. Find the area = 0.4987 + 0.3413
under the normal = 0.84
curve from 2.09 = 𝟖𝟒%
and above.
Case 3.2: 3. The average score of a Statistics test for a
𝑃(𝑧 ≤ 𝑍 ≤ ∞) class is 85 and standard deviation is 10.
= 0.5 − 𝜙(𝑧) Find the probability of a random score falling
𝑃(2.09 ≤ 𝑍 ≤ ∞) = 0.5 − 𝜙(2.09) 75 and 95.
= 0.5 + 0.4817 Convert the following raw scores:
= 0.0183 𝑥1 = 75 𝑥2 = 95
= 𝟏. 𝟖𝟑%
𝑥−𝜇 𝑥−𝜇
𝑧= 𝑧=
𝜎 𝜎
Standardizing Normal Distribution 75 − 85 95 − 85
= =
 Given a normal random variable X with mean 𝝁 10 1.8
and standard deviation 𝝈, each value x of the
variable can be transformed into z-scores using 𝒛𝟏 = −𝟏 𝒛𝟐 = 𝟏
the formula:
 𝑥 – raw score 𝑷(−𝟏 ≤ 𝒁 ≤ 𝟏)
𝒙− 𝝁  𝜇 – mean Case 1: 𝑃(−𝑧1 ≤ 𝑍 ≤ 𝑧2 ) = 𝜙(𝑧1 ) + 𝜙(𝑧2 )
𝒛=  𝜎 – standard
𝝈
deviation 𝑃(−1 ≤ 𝑍 ≤ 1) = 𝜙(1) + 𝜙(1)
= 0.3413 + 0.3413
EXAMPLES = 0.6826
1. A random variable X has a mean of 4 and = 𝟔𝟖. 𝟐𝟔%
standard deviation of 2. Find the
corresponding z-score for x = 7. 4. Entry to a certain University is determined by
𝒙− 𝝁 a national test. The scores on this test are
𝒛=
𝝈 normally distributed with a mean of 500 and
STATISTICS & PROBABILITY: NORMAL DISTRIBUTION
STANDARD NORMAL DISTRIBUTION | STANDARDIZING NORMAL DISTRIBUTION | SAMPLING THEORY
SHS | STEM | SECOND SEMESTER | 2023
a standard deviation of 100. Matt wants to SLOVIN’S/YAMANE’S FORMULA
be admitted to this university and he knows  Yamane’s Formula – is used to calculate
that he must score better than at least 70% the sample size (n) given the population size
of the students who took the test. Matt takes (N) and a margin of error (e).
the test and scores 585. Will he be admitted
to the university? Formula:
𝑵
𝑷(−∞ ≤ 𝒁 ≤ 𝟎. 𝟖𝟓)
𝒏=
𝟏 + 𝑵𝒆𝟐
𝑥−𝜇 Case 3: 𝑛- sample size
𝑧=
𝜎 𝑃(−∞ ≤ 𝑍 ≤ 𝑧) = 0.5_𝜙(𝑧) 𝑁 – size of the population
585 − 500 𝑒 – margin of error
= 𝑃(−∞ ≤ 𝑍 ≤ 0.85) = 0.5 + 𝜙(0.85)
100 1% - medical fields
= 0.5 + 0.3023 5% - education and social sciences
= 0.8023 10% - other fields
𝒛𝟏 = 𝟎. 𝟖𝟓
= 𝟖𝟎. 𝟐𝟑%
SAMPLING TECHNIQUES
Probability Sampling Nonprobability Sampling
Matt scored better than 80.23% of the students
 Unbiased  Biased sampling
who took the test and he will be admitted to the sampling
university.  Random selection

SAMPLING THEORY PROBABILITY SAMPLING


 Population – refers to the entire group of 1. Simple Random Sampling
individuals or object known to have similar - also known as “lottery method”
characteristics. - the most commonly used sampling
- the totality of observations or elements technique.
- every element of the population has the
from a set of data
same probability of being selected for the
 Sample – a subset of the entire population
inclusion of the sample.
- refers to one or more elements taken
from the population for a specific Example: A company executive selected 15 participants for
purpose the international business Congress by writing the names of
all employees and then choosing a name one at a time until
the delegation is complete.
PARAMETER AND STATISTIC
Parameter Statistic
2. Systematic Sampling
 a numerical  a numerical - adopts a skipping pattern in the selection of
measure that measure or value sample units.
describes a that describes a - every nth element of the population is
characteristics sample selected until the desired number of
of an entire elements in the sample is obtained.
population.
Formula:
Example: A school principal surveys the mean # of elements in the population
𝑛=
# of elements in the sample
general weighted average (GWA) of the
students in the present school year. From a
Example: From a list containing the names of 500
group of 50 random students, a mean GWA members of the alumni association, a sample of size 50 is
86.75 is determined. obtained by including every 10th person in the list.

Parameter 3. Stratified Sampling


Statistic - used in homogenous partitions/categories
- the population is partitioned into subgroups
called strata, based on some
characteristics such as year, religion,
gender, age, ethnicity, etc.
STATISTICS & PROBABILITY: NORMAL DISTRIBUTION
STANDARD NORMAL DISTRIBUTION | STANDARDIZING NORMAL DISTRIBUTION | SAMPLING THEORY
SHS | STEM | SECOND SEMESTER | 2023
- samples are then randomly selected in Example: The teacher announced that he needs 3
each stratum representatives to represent the school in a regional quiz
show. The teacher decided to choose the top three
students as representatives.
Formula:
size of stratum
# of samples per stratum = × # of samples 3. Snowball Sampling
total population
- sometimes called chain-referral sampling.
- the researcher chooses a possible
Example: A sample of 200 students is to be selected from respondent for the study at hand. Then
a senior high school population of 1000, of which 200 each respondent is asked to give
students are in ABM strand, 150 in GAS strand, 200 in recommendations or referrals to other
HUMSS strand, 300 in STEM strand, and 150 in TVL possible respondents
strand. If the sample size to be taken is 200 and should be
- used when the research is focused on
proportionally distributed, how many samples are to be
participants with very specific
taken per stratum?
characteristics such as being members of a
gang
4. Cluster Sampling
- the total population is divided into groups or
Example: The researcher asks respondents to suggest
clusters other possible respondents who are members of their
- used when “natural” but relatively organization.
heterogeneous groupings are evident in a
statistical population. 4. Quota Sampling
- equivalent of stratified random sampling in
Example: Suppose a researcher wants to study the effect terms of nonprobability sampling.
of blended learning in a particular city/municipality. Since
- The researcher starts by identifying
there are many schools in a city/municipality, it will be very
inefficient and impractical to consider all the schools in the quotas, which are predefined control
study. Instead, the researcher will randomly choose few categories such as age, gender, education,
schools where students will be surveyed. or religion

Stratified Sampling vs. Cluster Sampling

NON-PROBABILITY SAMPLING
1. Convenience Sampling
- known as grab or opportunity sampling
or accidental or haphazard sampling.
- involves the sample being drawn from that
part of the population which is close to
hand. That is, readily available and
convenient

Example: The researcher conducts online poll in social


media in determining the respondent’s choice of TV
program.

2. Purposive Sampling
- done with a purpose in mind
- also called judgmental or selective
sampling, focuses on samples which are
taken based on the judgment of the
researcher.

You might also like