Fundamentals of

Statistics
What is Statistics?
The science of conducting studies to collect, organize,
summarize, analyze, and draw conclusions from data
is called statistics. It is used in almost all fields of
human endeavor such as sports, education, health,
research, and among others. Statistical analysis are
used to manipulate, summarize, and investigate data
for a useful decision – making.
Example:
 number of Covid-19cases
 poverty rate
 number of drop outs in a year
2
What is Statistics?
Sir Ronald Aylmer Fisher (February 17,
1890 – July 29, 1962), British
statistician and geneticist who
pioneered the application of
statistical procedures to the design of
scientific experiments. He is consider
as the Father of Modern Statistics.
3
Population vs. Sample

Population - entire collection of entities that

we want information about, on which
inferences aremade.

Sample - subset of the population we

actually examine to gather information.

4
Parameter vs. Statistic

Parameter - summary measures obtained

from apopulation.

Statistic - summary measures obtained

from asample.

Example:

5
Variable, Observation, Data

Variable - characteristic/attributemeasured for the unit

under consideration.
Observation - realized value of a variable
measured foreach unit.
Data - collection of observations on one or more variables.

6
Classification of Variables

Continuous
Quantitative
Variable Discrete
Qualitative

7
Classification of Variables
Qualitative - measures a characteristic that can be
classified into one of a group of categories and
cannot be measured on a natural numerical scale.

Examples:
 Sex (Male, Female)
 Employment status of parents (Employed,
Unemployed)
 Reason(s) for not attending school

8
Classification of Variables

 Quantitative - measures a
characteristicthat
is recorded on a naturally
occurring numerical scale Discrete -
can only take a finite or countable
number of values
 Continuous - takes infinitely many
values at any
 point on agiven interval
9
Level of Measurement

Nominal - qualitative variables without a

sense of order.

Examples:
 Sex (Male, Female)
 Employment status of parents(Employed,
Unemployed)
 Reason(s) for not attending school

10
Level of Measurement
Ordinal - qualitative variables with an inherent
ordering.

Examples:
 Highest educational attainment of parents
(elementary graduate, high school graduate,
college graduate,etc.)
 Conduciveness of household for studying (1 –
lowest to 10 –highest)

11
Level of Measurement

Interval - quantitative variables with no

absolute zeropoint.

Examples:
 Daily maximum temperature (in Celsius)
 Intelligent quotient score

12
1. One can measure time during the day using a 12-hour clock, this is a good example of interval
data. Time in a 12-hour format is a rotational measure that keeps restarting from zero at set
periodicity. These numbers are on an interval scale as the distance between them is measurable and
comparable. For example, the difference between 5 minutes and 10 minutes is the same as 15
minutes and 20 minutes in a 12-hour clock.

2. The temperature measured in Fahrenheit and Celsius but not in Kelvin. If you measure temperature
in Fahrenheit and Celsius then it will be considered interval data as 0 is arbitrary. But in Kelvin, 0 is
absolute. There can’t be a temperature below zero degrees in Kelvin.

3. When you calculate intelligence score in an IQ test. There is no zero point for IQ. According to
psychological studies, a person cannot have zero intelligence, therefore in this example, zero is
arbitrary. IQ is numeric data expressed in intervals using a fixed measurement scale.

4. Test scores of examination like SAT. Scores in SAT test are in the range of 200-800. The numbers from
0 to 200 are not used when they scale the raw score (number of questions answered correctly) to the
section score. The reference point is not an absolute zero, thus, it qualifies to become interval data.

5. Age is also a variable that can be measured on an interval scale. For example if A is 15 years old
and B is 20 years old, it not only clear than B is older than A, but B is elder to A by 5 years.
Level of Measurement

Ratio - quantitative variables with an

absolute zeropoint.

Examples:
 Household size
 Household monthly net income (in pesos)
 Distance from house to school (in km)

14
Broad Categories of Statistics

Descriptive Statistics - refers to the tools used to describe a

mass of data in a clear, concise, and informative way
through the methods of organizing, summarizing, and
presenting data.

Examples:
 Construction of graphs, charts and tables
 Frequency count
 Percentage
 Measures of central tendency (mean, median, mode)
 Measures of variability (Variance, standard deviation,
etc.)
 Measures ofposition 15
Broad Categories of Statistics
16

Inferential Statistics - refers to the tools used to analyze the information

from the sample to make generalizations or predictions about the
population.

Examples:
 Parametric
 Z-tests
 T-tests
 F-tests (such as ANOVA-Analysis of Variance)
 Pearson correlation (Pearsonr)
 Non-parametric
 Wilcoxon Rank sum Test
 Mann-WhitneyU Test
 Spearman Correlation
 Kruskal Wallis Test
 Friedman Test
Data Collection and Sampling Techniques
17

Developed to mathematically determine the most

effective way to acquire a sample that would
accurately reflect the population of the study.

The most common mathematical formula to

determine the number of sample in reference to
population is the Slovin’s Formula which is
introduced by Slovin in 1960. To this day, it is still
unknown who really Solvin is, many names
associated either Mark Slovin, Michael Slovin, or
Kulkol Slovin.
Data Collection and Sampling Techniques
18

Sampling
 It is the process of selecting a number of
individuals for a study in such a way that they
represent the larger group from which they were
selected.
 The process which involves taking a part of the
population, making observations on this
representative groups, and then generalizing the
findings to the bigger population.
Data Collection and Sampling Techniques
19

 Population refers to a group that has one or more

characteristics in common.
 Target population consists of all the people with a
common characteristic to whom investigators
plan to generalize their results. Example: 15-year-
olds living in rural areas, all fourth graders in the
Philippines.
▫ The group of interest to the researcher, the group
to which she or he would like the results of the
study tobe generalizable.
Data Collection and Sampling Techniques
20

 Accessible population is a population where

researchers delineate within the target population
to which they have access, example 15-year-olds
living in a particular district/municipality, fourth
graders in a public school district.
 A sample comprises of the individuals, items, or
events selected from a larger group referred to as
a population.
 Sampling frame is the actual list of sampling units
from which the sample, or some stage of the
sampling, is selected.
Data Collection and Sampling Techniques
21

 Categorical sampling- when samples are

taken proportionally from
groups/categories.
 Temporal sampling- when a sample is
taken in terms of time, e.g., pulse or blood
pressure of patient taken every hour.
Data Collection and Sampling Techniques
22

Why sample?
 Makes possible the study of large,
heterogeneous population
 Saves time, money, and effort
 More effective
 Faster and cheaper
 More accurate
 Gives more
 Comprehensive information
Data Collection and Sampling Techniques
23

▫ Slovin’s Formula
𝑁
▫ 𝑛=
1+𝑁𝑒 2
▫
▫ where:
▫ 𝑛 is the samplesize
▫ 𝑁 is the population size
▫ 𝑒is the margin of error (e.g. 0.01, 0.05, 0.1, etc)
Data Collection and Sampling Techniques
24

Use Slovin’s formula if you have no idea about the

population’s behavior. Slovin’s formula determines
sample in proportion to the population. Slovin’s
formula is applicable only when estimating a
population proportion and when the confidence
coefficient is 95%. There are other sampling
formula that could be used to determine samples
in relation to the characteristics of the variables.
Data Collection and Sampling Techniques
25

▫ In most educational and scientific researches,

0.05 margin of error (level of significance is used
most ofthe times.
▫
▫ Margin of error tells how many times percentage
points your results will differ from the real
population. For example, 0.05 (5%)level of
significance which implies 0.95 (95%)confidence
level to the real population value.
Data Collection and Sampling Techniques
26

Example:
Assuming a certain is to be conducted to a
certain community with 6,518 residents.
Determine the number of respondents of the
study with 5% level of significance using
Slovin’s formula.
Data Collection and Sampling Techniques
27

Solution: From the assumption, 6,518 is the

population size, and 0.05 (5%)is the margin of error.
Therefore:

𝑁
𝑛=
1 + 𝑁𝑒 2
6,518
𝑛=
1 + 6,518 0.05 2
6,518
𝑛=
1 + 6,518 0.0025
Data Collection and Sampling Techniques
28

6,518
𝑛=
1 +16.295
6,518
𝑛=
17.295
𝑛 = 376.87 ≈ 377
This implies that using Slovin’s formula, the
given’s sample size is 377(respondents).
Data Collection and Sampling Techniques
29

Sampling Techniques
Sampling techniques are methods of
identifying who will be the respondents of
the study (sample). For instance, in the
previous example, how to identify the 377
respondents? Here comes the sampling
techniques.
Data Collection and Sampling Techniques

Types of Sampling Techniques

1. Probability/ Random SamplingTechniques
All members of the population have an equal chance of
being selected to be part of the sample.

1.a. Simple Random Sampling Technique (e.g. fishbowl

method or lottery method, table of random numbers, or
computer)
In this method, names will be placed inside a bowl or
box, then the target respondents will be picked by one
by one until the target number of respondents is
obtained. 33
Data Collection and Sampling Techniques
Example: If we are going to select 5 of

10 using simple random sampling,

names or code of the 10 members of
population will be placed inside the
bowl and box. Then, 5 names or codes
will be pick one by one. Then the
selected 5 will be the respondents.
31
Data Collection and Sampling Techniques

Simple Random Sampling Technique with

Replacement
In here, each of them can be selected or pick up more
than once because their names will be put back after
they arepicked.

Simple Random Sampling Technique without

Replacement
Here, if their names or codes are picked it will not be
placed again in the bowl or box.

32
Data Collection and Sampling Techniques

Systematic Random Sampling Technique

Obtained by selecting every 𝑘𝑡ℎmember of
the population where k is a counting
number.

Example: For the sake of illustration let us

limit the population size. Suppose the
population size is 10,and the sample is 5.
How can we obtain the 5samples?
33
Data Collection and Sampling Techniques

34
Data Collection and Sampling Techniques

35
Data Collection and Sampling Techniques

36
Data Collection and Sampling Techniques

1.c. Stratified Random Sampling Technique

Obtained by dividing the population into
subgroups or strata according to some
characteristic relevant to the study. (There
can be several subgroups.) Then subjects
are selected at random from each
subgroup.

37
Data Collection and Sampling Techniques

Example: The town has 250 homeowners of

which 25, 175,and 50 are upper income,
middle income, and low income,
respectively. Explain how we can obtain a
sample of 20 homeowners, using stratified
sampling with proportional allocation,
stratifying by income group.

38
Data Collection and Sampling Techniques

39
Data Collection and Sampling Techniques

40
Data Collection and Sampling Techniques

1.d. Cluster Random SamplingTechnique

Obtained by dividing the population into sections or
clusters and then selecting one or more clusters at
random and using all members in the cluster(s) as
the members of the sample. Groups or cluster could
be by geographic area or schools in large district.
Cluster sampling is used when the population is
large or when it involves subjects residing in a large
geographic area.

41
Data Collection and Sampling Techniques

Example: To save time, the planner

decided to use cluster sampling. The
residential portion of the city was
divided into 947 blocks, each
containing 20 homes. Explain how
the planner used cluster sampling to
obtain a sample of 300 homes.
Data Collection and Sampling Techniques

43
Data Collection and Sampling Techniques

44
Data Collection and Sampling Techniques

2.Nonprobability/ Nonrandom Sampling

Techniques
In these techniques, all members of the
population have no equal chance of being
selected to be part of the sample.

a. Convenience or AccidentalSampling
Technique
The use of most convenient way of determining
the samples.
45
Data Collection and Sampling Techniques

For instance, a survey about Facebook

users, to select respondents using
convenience sampling technique, the
researcher could send private message to
online Facebook friends. Not all Facebook
friends have equal chance to part of the
sample because what if the person is
offline, therefor he/ she has no chance to be
part of the respondents.
49
Data Collection and Sampling Techniques

2.b. Quota SamplingTechnique

Ensures equal or proportionate representation of
the subjects, depending on which trait is considered
as the basis of quota. The usual bases of quota are
age, gender, education, race, religion, & socio-
economic status.

Example: The basis of quota is college level &

research needs equal presentation with 100 as
sample size. Researcher must select 25 from each
year level.
47
Data Collection and Sampling Techniques

2.c. Volunteer or self –selected Sampling Technique

If a person decided to include themselves as part of
the samples.

2.d. Purposive/ Purposeful or Judgmental/

Judgement or Selective or Deliberate Sampling
Technique
Researcher selects samples who fulfil the criteria as
well as inclusion in the population as per knowledge
of the researcher.

48
Data Collection and Sampling Techniques

 For example,a study about experiences of post disaster

depression among people living in earthquakeaffectedareas,
therefore the respondents are the people who are victims of
earthquake and sufferingpostdisasterdepression.

49
Data Collection and Sampling Techniques

2.e. Snowball/ NetworkingSampling Technique

Used to identify potential subjects in studies where
subjects are hard to locate. Works like chain referral.
This is also known as chain referral sampling
technique.

After observing the initial subject, the researcher asks

for assistance from the subject to help in identifying
people with a similar trait of interest. It is like asking
subjects to nominate another with the same trait. The
same process is done until sufficient number of
subjects is obtained. 53
Data Collection and Sampling Techniques

2.f. Expert Sampling Technique

Samples are chosen their expertise.

For example, a study about

volcanoes, then you will consult
volcanologists.

51
References
• Institute of Statistics - UPLB (2021). Software-Assisted Statistical Analysis: Basic
Statistical Methods using R. [PowerPoint Slides]
• Mascariñas, A. (2022). QRM 6 [Selecting a Sample from the Population] [PowerPoint
Slides]
• Peck, R. (2020). Introduction to Statistics and Data Analysis. Cengage Learning, Inc.
• Johnson, R.A. (2019). Statistics: Principles and Methods. Wiley.
• Jabilles, A.B. (2018). Statistics for Thesis Writers. Books Atbp. Publishing Corp.
• Murphy, C. (2018). Statistics and Sampling Theory. Willford Press.
• Blumann, A.G. (2017). Elementary Statistics: A Step-by-Step Approach. McGraw-Hill
Education.
• Navidi, W.C. & Monk, B.J. (2019). Elementary Statistics. McGraw-Hill Education.
• Triola, M.F. (2018). Elementary Statistics. Pearson.

52
THANK YOU!