REVIEWER IN STATS (4th GRADING EXAM) 2.

Purposive Sampling - this sampling is done

with a purpose in mind. This technique, also
called judgment or selective sampling,
1. Random Sampling focuses on samples which are taken based
2. Introduction to sampling distribution (parameter on judgment of the researcher. The goal of
and statistic) this sampling is to carefully choose the
3. Sampling Distribution of the Sample Mean members of the population which are best
4. Mean, Variance and Standard Deviation of the fitted to answer the research questions
Sampling Distribution of the Sample Mean 3. Snowball Sampling - is sometimes called
chain-referral sampling. In this technique,
SAMPLING TECHNIQUE the researcher chooses a possible respondent
• Sampling technique is the name or other identification for the study at hand. Then each respondent
of the specific process by which the entities of the is asked to give recommendations or
sample have been selected. referrals to other possible respondents. This
is very effective sampling technique,
RANDOM SAMPLING especially when the suitable participants of
– Method wherein each element of the population the study are hard to find
has an equal chance of being chosen to represent 4. Volunteer Sampling – sample units are
the population. volunteers in studies wherein the measuring
POPULATION - consists of all members of process or troublesome to a respondent
the group about which you want to draw a 5. Quota Sampling – sample units are picked
conclusion. for convenience but certain quotas are given
SAMPLE - is a portion, or part (subset) of to interviewers. This design is specially used
in market research. Researchers choose
the population of interest selected for analysis
these individuals according to specific traits
or qualities
TYPES OF RANDOM SAMPLING
PROBABILITY SAMPLING - sampling techniques PARAMETER – measurement or quantities that describes the
that involve random selection population.
1. Simple Random Sampling – is the most
commonly used sampling technique wherein STATISTIC - measurement or quantities that describes the
each element in the population has an equal sample.
probability of being selected. EXAMPLE
2. Systematic Random Sampling – this can
be done by listing all the elements in the 1. Below are the scores in Statistics and Probability of
population and selecting every nth/kth GRADE 11 HUMSS knowledge during the prelim.
element in your population list. This is Compute the population mean, population variance,
equally precise as the simple random and population standard deviation.
sampling. It is often used on long population
lists. To determine the interval to be used in 24 29 18 25 30
identifying the samples to who will 12 28 20 23 21
participate the study, use the formula K=N/n
(population/sample size). POPULATION MEAN:
3. Stratified Random Sampling – is a random
sampling wherein the population is divided μ=
∑x
into different strata or homogenous N
partitions or division. The number will be
24 +29+18+25+30+ 12+ 28+20+23+21
proportionately picked in each stratum that μ=
is why all strata are presented in the 10
samples. 230
1. Cluster Sampling – is a random sampling μ=
10
wherein population is divided into a clusters
or groups and then the clusters are randomly μ=23
selected. All elements of the clusters
randomly selected are considered the POPULATION VARIANCE
x (x- μ) (x- μ)2
samples of the study. σ =∑ ¿ ¿ ¿
2
24 1 1
29 6 36
NON-PROBABILITY SAMPLING - the sampling 2 274 18 -5 25
σ =
techniques that not involve random selection of 10 25 2 4
data 2
30 7 49
1. Convenience Sampling – wherein the σ =27.4 12 -11 121
researcher gathers data from nearby sources 28 5 25
of information exerting minimal effort. 20 -3 9
Convenience is being used by persons 23 0 0
giving questionnaires on the streets to ask 21 -2 4
the passersby
POPULATION STANDARD DEVIATION Example: A population consist of the numbers
2,4,9,10 and 5. Construct a sampling
σ =√ ∑ ¿ ¿ ¿ ¿ distribution. If the sample size is 3.
σ =√ 27.4
Step 1: NCn (N = 5 ; n = 3)
σ =¿5.23 N Cn = 5C3 = 10
EXAMPLE
Step 2:
2: Form the previous data of the population, suppose Sampl
that we randomly select only 5 data out of 10 in the Sample Mean
e
total data in the sample. Compute the sample mean, 2,4,9 5
sample variance, and sample standard deviation. 2,4,10 5.33
24 29 18 25 30 2,4,5 3.67
2,9,10 7
12 28 20 23 21 2,9,5 5.33
2,10,5 5.67
SAMPLE MEAN
4,9,10 7.67

x̄ =
∑x 4,9,5 6
n 4,10,5 6.33
9,10,5 8
24+18+25+ 28+20 Step 3:
x̄ =
5
Sample Mean Frequency P(mean)
115 3.67 1 1/10 = 0.10 = 10%
x̄ =
5 5 2 2/10 = 0.20 = 20%
x̄ = 23 5.33 1 1/10 = 0.10 = 10%
5.67 1 1/10 = 0.10 = 10%
SAMPLE VARIANCE 6 1 1/10 = 0.10 = 10%
6.33 1 1/10 = 0.10 = 10%
2
s=
∑ (x− x̄)
2
7 1 1/10 = 0.10 = 10%
n−1 7.67 1 1/10 = 0.10 = 10%
2 64 8 1 1/10 = 0.10 = 10%
s= Total N=10 1=1=100%
5−1
2 64
s=
4 MEAN, VARIANCE & STANDARD DEVIATION OF THE
SAMPLING DISTRIBUTION OF THE SAMPLE MEAN
2
s =¿ 16
 The mean of the population is also the mean of the
sample taken from the population.
x (x- μ) (x- μ)2
24 1 1 Example: Find the mean of the sampling
18 -5 25 distribution of the sample means of the scores
25 2 4 1,2,3,4,5 and 6 using n=2 without replacement.
28 5 25 =
20 -3 9 Solution:

SAMPLE STANDARD DEVIATION Sample Mean P(Sample Mean) (x)P(x)

1/15 1.5/15

√ ∑ ( x− x̄)2 1.5
s= 2 1/15 2/15
n−1
2.5 2/15 5/15
s= √ 16 3 2/15 6 /15
s=4 3.5 3/15 10.5/15
4 2/15 8 /15
4.5 2/15 9 /15
Sampling Distribution of the Sample Mean –
A frequency distribution using the means 5 1/15 5/15
computed from all possible random samples of 5.5 1/15 5.5/15
a specific size taken from a population.

Sampling error – the difference between the MEAN:

sample mean and population.
μ=∑ X P(X )
 √
1.5 2 5 6 1 0.5 8 9 σ N−n
= + +¿ +¿ + + + +¿  σ x̄ = ( ) : for finite population (without
15 15 15 15 15 15 15 √ n N −1
5 5 .5 replacement)
+
15 15 σ
 σ x̄ = : for infinite population (with
μ = 3.5
√n
replacement)

where: σ = standard deviation

VARIANCE
n = sample size
N = population size
σ =∑ ( X −μ ) P( X )
2 2

2 4 2.25 1 0.25 0 0.25 1

σ = + +¿ +¿ + + + +¿
15 15 15 15 15 15 15
2.25 4 CENTRAL LIMIT THEOREM
+
15 15
 The central limit theorem (CLT) states that
2
σ =1.17 the distribution of sample means
approximates a normal distribution as the
sample size gets larger, regardless of the
x P(x) (x-mean)2 (x-mean)2P(x) population's distribution.
2
1.5 1/15 (1.5 -3.5) = 4 4/15
2
2 1/15 (2 -3.5) = 2.25 2.25/15
2
2.5 2/15 (2.5 -3.5) = 1 1/15
3 2/15 (3 -3.5)2 = 0.25 0.25/15
3.5 3/15 (3.5 -3.5)2 = 0 0/15 = 0
4 2/15 (4 -3.5)2 = 0.25 0.25/15
2
4.5 2/15 (4.5 -3.5) = 1 1/15
5 1/15 (5 -3.5)2 = 2.25 2.25/15
5.5 1/15 (5.5 -3.5)2 = 4 4/15

STANDARD DEVIATION
σ =√ Ʃ ( x−μ ) P ( x )
2

σ =√ σ 2
σ =√ 1.17
σ =1.08

NOTE:

(Properties of sampling distribution of the

sample mean)
 The mean of the population is also the mean of the
sample taken from the population.
Formula for the mean of sampling distribution
 μ=∑ X P(X )

 The variance of the sampling distribution of the

sample mean id given by the following:
 σ 2=∑ ( X −μ )2 P( X ) or
2
2 σ N −n
 σ x̄ = ( ) : for finite population (without
√ n N −1
replacement)
2
σ
 σ 2x̄ = : for infinite population (with
n
replacement)
where: σ 2= variance
n = sample size
N = population size

 The variance of the sampling distribution of the

sample mean id given by the following: