MATH REVIEWER series of experiments on some controlled and

experimental variables. This is commonly used

Statistics – is the branch of mathematics or a in scientific inquiries.
science and an art of collection, organization,
presentation, analysis and interpretation of RRL method – gathering data using the review
data. of related literature that can provide data to the
researcher.
DATA GATHERING: different methods used are
1. Direct or interview method DATA PRESENTATION
2. Indirect or questionnaire (survey) Textual form – makes use of words, sentences
method and paragraphs in presentation. It is commonly
3. Registration method used when there are only few numerical data to
4. Observation method be enumerated or to be compared with other
5. Experimental method data. Narrative and descriptions.
6. RRL method
Tabular form – is a systematic presentation of
data in rows and columns. It is used when
Interview method – is a person-to-person
related numerical facts need to be classified in
encounter between the source of information,
arrays.
the interviewee and the one who gathers
information, the interviewer. Interview can be
Graphical form - shows numerical values or
done personal, through phone or internet
relationships in a pictorial form. It makes use of
access. It has a target sample, uses interview
graphs, symbols or visual aids. The use of kind
guide questions.
of graph depends to the data.
Survey method – is the technique in which a
questionnaire is used to elicit the information or
data needed. Uses a survey or a research
instrument.

Registration method – obtains data from the

records of government agency authorized by
law to keep such data or information and made
these available to researchers.

Observation method – is the technique in

which data particularly those pertaining to the
bahaviors of individuals or group of individuals
during the given situation are best obtained
through observations. The researcher can be
participatory or non-participatory to the data.
Participatory – Researcher is participatory to
DATA ANALYSIS
the data or research.
1. T-Test - is an inferential statistic used to
Non-participatory – researcher is the observer
determine if there is a significant
of the data.
difference between the means of two
Experimental method – is a system used to groups and how they are related. T-
gather data from the results of performed tests are used when the data sets follow
 a normal distribution and have Ex. Sex, civil status, nationality, postal code, and
unknown variances, like the data set LRN.
recorded from flipping a coin 100 times.
● Ordinal scale – Observations have size
2. Z-Test - is a statistical test used to or magnitude but you cannot determine
determine whether two population differences.
- Accounts for order; no indication of
means are different when the variances
distance between positions.
are known and the sample size is large.
It can also be used to compare one
Ex. Curriculum, level, socio-economic status,
mean to a hypothesized value.
military ranks, and Latin honors.
3. F-Test - is any statistical test used to
compare the variances of two samples ● Interval scale – We can now determine
or the ratio of variances between differences but zero is not absolute.
multiple samples. The test statistic, - Equal intervals; no absolute zero.
random variable F, is used to determine - Ex. Temperature and test scores.
if the tested data has an F-distribution
under the true null hypothesis, and true ● Ratio scale – Zero is now absolute.
customary assumptions about the error Has all the following properties:
term (ε). a. The numbers in the system are used to
classify a person/object into distinct,
TWO KINDS OF DATA non-overlapping and exhaustive
● Qualitative data – Data representing categories;
information and concepts that are not b. The system arranges the categories
represented by numbers. Refers to the according to magnitude;
qualities, characteristics, attributes, and c. The system has a fixed unit of
description of the sample.
measurement representing a set size
Ex. Sex, eye color, and occupation.
throughout the scale and
● Quantitative data – Are measures and d. The system has an absolute zero.
values or counts and are expressed as Ex. Money, gas, work hours worked by an
numbers. Numerical information. employee.
Ex. Height, weight, duration, and age.

Discrete data – Includes non-divisible figures

and statistics you can count. Use of whole
numbers. SAMPLING TECHNIQUES/PROCEDURES
Ex. Votes in election, and Facebook likes. ● Sample - is the group of individuals who
Continuous data – Represents precise will actually participate in the research.
measurements of nearly any numeric value. ● Population - is the entire group that
Ex. Weight, speed, and temperature. you want to draw conclusions about.

SCALES/LEVELS OF MEASUREMENT A. PROBABILITY SAMPLING

● Nominal scale – observations are B. NON-PROBABILITY SAMPLING
labelled so that they fall into 2 or more
categories.
- Numbers or symbols used to classify.
Probability sampling - involves random Note: after dividing into different strata the list
selection, allowing you to make strong is then used for either lottery method (simple
statistical inferences about the whole group. random sampling) or kth (systematic sampling)
also known as Multistage sampling.
Non-probability sampling involves non-random
selection based on convenience or other
criteria, allowing you to easily collect data.
● Cluster sampling (Area sampling)
A. PROBABILITY SAMPLING/ RANDOM Cluster sampling also involves dividing the
SAMPLING population into subgroups, but each subgroup
● Simple random sampling - In a simple should have similar characteristics to the whole
random sample, every member of the sample. Instead of sampling individuals from
population has an equal chance of each subgroup, you randomly select entire
being selected. Your sampling frame subgroups.
should include the whole population.
- Uses Lottery method or fish bowl Can also use the multistage sampling.
technique. Ex. URS campus in division 1
● Systematic sampling - The population is URS CAINTA, URS TAYTAY URS ANGONO, and
the entire group that you want to draw URS BINANGONAN
conclusions about.
- List of names or document Use the lottery method to select two Campus at
(alphabetical). “Sampling frame” or random. URS BINANGONAN AND URS TAYTAY,
“frame” the students of the two Campus are now the
sample of the study; Or use the PROBABILITY
Kth = N/n PROPORTION TO SIZE (PPS).
N= population n= no. samples needed USING PROBABILITY PROPORTION TO SIZE: for
Can also be used with a random start by Binangonan Campus
selecting a random number and then using the COLLEGE FREQUEN % NO.
kth from there. CY (PPS SAMPLE
) S

● Stratified sampling - involves dividing ACCOUNTANCY 500 12.5 63

the population into subpopulations that %
may differ in important ways. It allows
BUSINESS 2000 50% 1000
you to draw more precise conclusions
by ensuring that every subgroup is COMP. SCIENCE 1500 37.5 563
properly represented in the sample. %

To use this sampling method, you divide the TOTAL 4000 100 1626
population into subgroups (called strata) based %
on the relevant characteristic (e.g., gender
identity, age range, income bracket, job role).
Then you can apply the systematic sampling
method
 a. 500/63 = 8th criteria and beware of observer bias affecting
b. 2000/1000=2th your arguments.
c. 1500/563 = 3th
Ex. Convenience store example but only the
In Probability sampling or random sampling mothers who enter the store AND go to the milk
you are then allowed to make a hypothesis or formula aisle are asked to be samples.
generalization since the sample reflects or
mirrors the population.
● Quota sampling - Quota sampling relies
B. NON-PROBABILTY SAMPLING/NON-
on the non-random selection of a
RANDOM SAMPLING
predetermined number or proportion
● Convenience sampling - A convenience of units. This is called a quota.
sample simply includes the individuals
You first divide the population into mutually
who happen to be most accessible to
exclusive subgroups (called strata) and then
the researcher.
recruit sample units until you reach your quota.
Ex. The researcher is in a hurry and in the room These units share specific characteristics,
there are only a few students present, the determined by you prior to forming your strata.
researcher conducted the survey only to the The aim of quota sampling is to control what or
student who are present instead of waiting for who makes up your sample.
the others since it was much more convenient
Ex. The researcher only needs 50 samples, once
for them.
they reach their quota they have successfully
Ex. The researcher was gathering samples at a gathered their samples. The researcher set the
convenience store, all the mothers who enter specific time of 1:00pm to 4:00pm to gather
the store were asked to be samples for the samples, at 4:00pm the researcher has
study. Which is more convenient than gathering successfully gathered samples.
all the mothers inside the convenience store.
● Snowball sampling - If the population is
hard to access, snowball sampling can
be used to recruit participants via other
● Purposive sampling - This type of
participants. The number of people you
sampling, also known as judgement
have access to “snowballs” as you get in
sampling, involves the researcher using
contact with more people. The
their expertise to select a sample that is
downside here is also
most useful to the purposes of the
representativeness, as you have no way
research.
of knowing how representative your
It is often used in qualitative research, where sample is due to the reliance on
the researcher wants to gain detailed participants recruiting others. This can
knowledge about a specific phenomenon rather lead to sampling bias.
than make statistical inferences, or where the
Ex. The Researchers pool of samples are the
population is very small and specific. An
Scholars. The researcher will approach one
effective purposive sample must have clear
scholar and then use them to gather more
criteria and rationale for inclusion. Always make
samples. This will continue until the researcher
sure to describe your inclusion and exclusion
is satisfied with the number of samples or x = midpoint
gathered all the samples.
n = sum of frequency
● Voluntary response sampling - Similar
Median (x̃) – is the middle score for a set of
to a convenience sample, a voluntary
data arranged in order of magnitude. Median is
response sample is mainly based on
best used when data has several entries
ease of access. Instead of the
researcher choosing participants and - Is defined as the middle value when a
directly contacting them, people set is observed values have been
volunteer themselves (e.g. by arranged in either ascending (from
responding to a public online survey). lowest to highest value) or descending
(from highest to lowest value) order of
In NON-PROBABILITY SAMPLING OR NON-
magnitude.
RANDOM SAMPLING you can only make
- Is the value that cuts the distribution
assumptions about the samples since they do
into halves.
not represent the population due to not all the
population being given the chance.

Mode (x̂) – is the most frequent score in the

data set. It is sometimes considered as the most
MEASURES OF CENTRAL TENDENCY
popular option.
- Is a typical or representative value of a
- Is the value that appears most
particular set of data.
frequently in the distribution.
Are measures indicating the center of a set of
EXAMPLES:
data which are arranged in order of magnitude.
1. Find the mean, median, and mode of
Mean or Arithmetic mean (or average)
the data (height)
x̄ - x bar
Basketball players: 180, 181, 182, 179, 175, 178,
- Is the most popular and well known 177, 180, 182, 180, 179, 182, 183, 179, 175.
measure of central tendency. It can be
Mean = x̄ = Σx/n
used with both discrete or continuous
data. (often used with continuous) Σx= 180+ 181+ 182+ 179+ 175+ 178+ 177+ 180+
- Is the summation of all observations 182+ 180+ 179+ 182+ 183+ 179+ 175= 2692
divided by the number of observations.
n=15
Formula:
x̄ = 2692/15
x̄ = Σx/n (or ) x̄ = Σfx / n.
x̄ = 179.47
For grouped data:
Median:
x̄ = sum of value/number of values
In ascending order: 175, 175, 177, 178, 179,
For ungrouped data: 179, 179, 180, 180, 180, 181, 182, 182, 182,
183.
F = frequency
Find the middle: 15/2 = 7.5, count to 7.5
x̃ = 180 cf = start at the lowest value (5) and add till the
highest amount.
Mode: find the value that is most frequent. 179,
180, 182 x̄ = Σfx / n

x̂ = 179.5 and 182 x̄ = 278/40

RULES IN DETERMINING THE MODE x̄ = 6.95

1. If two values having the same Median:

frequencies are adjacent, then get their
Add up the cf, now find the middle point
midpoint.
2. If two values having the same f = 5+14+6+8+7/2
frequencies are non-adjacent the values
are the mode. x̃ = 20 , in the table the x that is at 20 is the 7
3. If the frequencies are all equal there x̃ = 7
will be no mode.
Mode
Mode is the weakest measure of tendency,
since a distribution can have no mode 6 has the highest frequency 14

Unimodal – the distribution has one mode. x̂ = 6

Bimodal – the distribution has two modes 3. The ages of 7 people who went on a
field trip were 17, 18, 18, 19, 19, 20, 50
Trimodal – the distribution has three modes. find there mean:
Multimodal - the distribution has more than Mean = 161/7
three modes.
x̄ = 23
2. Calculate the mean, median and mode
in the ff. this is a bad value, since there are no individual
whose age is 23 in the distribution. It does not
x f fx cf represent the distribution. These is due to the
extreme points of the data (the lowest value
9 7 63 40
and the highest value having a huge gap). Mean
8 8 64 33 is affected by extreme values.

7 6 42 25 Median:

6 14 84 19 Median= 7/2 = 3.5

5 5 25 5 x̃ = 19

TOTAL 40 278
Mode:

Mean: Highest frequency= 18,19

fx = x multiplied by f x̃ = 18.5
 4. Fine the modes of the given distribution
2, 2, 3, 3, 4, 4, 5, 5 x̃ = none
2, 3, 3, 4, 4, 5, 6, 7, 8 x̃ = 3.5
2, 3, 3, 4, 5, 5, 6, 7, 8 x̃ = 3 and 5
2, 2, 3, 4, 4, 5, 5, 6, 7, 8, 8 x̃ = 2, 4.5, 8