STATISTICS QUANTITATIVE VARIABLE - is a measurable

• Statistics is the science of conducting attribute of a subject. This quantity can be

studies to collect, organize, summarize, measured or can be calculated with the use of
analyze, and draw conclusions from mathematical formula.
data. Examples: age, height, pulse rate, blood pressure
• Sir John Sinclair introduced the word Types of Quantitative Variables
statistics into the English language in • Discrete variable - data can be measured
1798. using integers or simply by counting.
• The word statistics was derived from the Example: pulse rate, number of public schools in
Latin word “status” meaning “state”. a particular locality
TWO KINDS OF STATISTICS • Continuous variable - data cannot be
DESCRIPTIVE STATISTICS measured alone by integers but by real
• It can be defined as methods for numbers in general. It is obtained by
organizing, summarizing, and presenting measurements, usually with units.
data in an instructive way. It also consists Example: height, weight
of the collection, organization, • QUALITATIVE VARIABLE - is an
summarization, and presentation of observable attribute of a subject. It is a
data. non-measurable characteristic that
INFERENTIAL STATISTICS cannot assume a numerical value but
• This uses a sample of the population for can be classified into two or more
estimating and drawing conclusions. It categories.
consists of generalizing from samples to Example: color
populations, performing estimations and Types of Qualitative Variables
hypothesis tests, determining • Dichotomous variables – qualitative
relationships among variables, and variables with two values. Example: sex
making predictions. • Trichotomous variables – qualitative
FUNDAMENTAL ELEMENTS OF STATISTICS variables with three values. Example:
• POPULATION - a set of all units (usually “for”, “against” and “undecided”
people, objects, transactions, or events) • Multinomous variables - qualitative
that we are interested in studying. variables with two or more values.
• SAMPLE - a subset of the units of a SCALES OF MEASURING DATA
population. • Nominal Scale – classifies objects or
• CONSTANTS – fundamental quantities peoples’ responses so that all of those in
that do not change in value. a single category are equal with respect
• VARIABLE - is an attribute of a subject to some attributes and then each
that is measurable or observable. It is an category is coded numerically.
observable characteristic or Examples:
phenomenon of a person or object • Eye color (blue, brown, green)
whereby the members of the group or
• Nationality (Filipino, Korean, American)
set vary from one another.
• Personality type (introvert, extrovert,
Types of Variables
ambivert)
 • Employment status (unemployed, part- • Speed in miles per hour (continuous)
time, retired) • Length in centimeters (continuous)
• Political party voted for in the last • Age in years (continuous)
election (party X, party Y, party Z) • Income in dollars (continuous)
• Type of smartphone owned (iPhone, • Sales made in one month (discrete)
Samsung, Google Pixel)
SUMMATION
• Ordinal Scale – classifies objects or
SIGMA NOTATION
individual’s responses according to
• 𝚺 (uppercase sigma) – refers to “total” or
degree or level, and then each level is
“to take the sum”
coded numerically.
• If 𝒙 is a variable, which represents a set
Examples:
of measurements, then ∑ 𝑥 means to get
• Academic grades (1.00, 1.50, 3.00, and
the sum of all the measurements from
so on)
the first to the last.
• Happiness on a scale of 1-10 (this is 𝒏
what’s known as a Likert scale) ∑ 𝒙𝒊 = 𝒙𝟏 + 𝒙𝟐 + 𝒙𝟑 + ⋯ + 𝒙𝒏
• Satisfaction (extremely satisfied, quite 𝒊=𝟏
satisfied, slightly dissatisfied, extremely METHODS OF COLLECTING DATA
dissatisfied) • DIRECT OR INTERVIEW METHOD –
• Level of education completed (high person-to-person interaction between
school, bachelor’s degree, master’s an interviewer and an interviewee. Tape-
degree) recorded or written interviews will help
• Seniority level at work (junior, mid-level, the researcher obtain exact information
senior) from the interviewee.
• Interval Scale – refers to quantitative • INDIRECT OR QUESTIONNAIRE METHOD
measurements in which lower and upper – an alternative to the interview method.
control limits are adapted to classify Written responses are obtained by
relative order and differences of item distributing questionnaires (lists of
numbers or actual scores. questions intended to elicit answers to a
Examples: given problem, which must be given in a
logical order and not too personal) to the
• Temperature in degrees Fahrenheit or
respondents through mail or hand-carry.
Celsius (but not Kelvin)
• REGISTRATION METHOD – is enforced
• IQ score
by private organizations or government
• Income categorized as ranges (P30-39k,
agencies for recording purposes.
P40-49k, P50-59k, and so on)
• OBSERVATION METHOD – is a scientific
• Ratio Scale – takes into account the
method of investigation that makes
interval size and ratio of two related
possible use of all senses to measure or
quantities, which are usually based on
obtain outcomes or responses from the
standard measurement.
object of study.
Examples:
• EXPERIMENTATION – used when the
• Weight in grams (continuous) objective is to determine the cause and
• Number of employees at a company effect of a certain phenomenon under
(discrete) some controlled conditions.
SAMPLING TECHNIQUE conveniently available for the
PROBABILITY SAMPLING researcher.
• The probability sampling method utilizes • The samples are easy to select, and the
some form of random selection. researcher did not choose a sample that
• In this method, all the eligible individuals outlines the entire population.
have a chance of selecting the sample Purposive or Judgmental Sampling
from the whole sample space. • In purposive sampling, the samples are
Types of Probability Sampling Method selected only based on the researcher’s
Simple Random Sampling knowledge.
• In a simple random sampling technique, • As their knowledge is instrumental in
every item in the population has an creating the samples, there are chances
equal and likely chance of being selected of obtaining highly accurate answers
in the sample. with a minimum marginal error.
• Since the item selection entirely • It is also known as judgmental sampling
depends on the chance, this method is or authoritative sampling.
known as the “Method of Chance STEM-AND-LEAF PLOT
Selection”. • A stem-and-leaf plot or stem-and-leaf
• As the sample size is large, and the item diagram is a way to arrange and
is chosen randomly, it is known as represent data so that it is simple to see
“Representative Sampling”. how frequently various data values
Systematic Sampling occur.
• In the systematic sampling method, the • It is a plot that displays ordered
items are selected from the target numerical data.
population by selecting the random • The digits of a data value are divided into
selection point and selecting the other a stem (first few digits) and a leaf
methods after a fixed sample interval. (usually the last digit).
• It is calculated by dividing the total HISTOGRAM
population size by the desired • The histogram is a graph that displays
population size. the data by using contiguous vertical
NON-PROBABILITY SAMPLING bars (unless the frequency of a class is 0)
• The non-probability sampling method is of various heights to represent the
a technique in which the researcher frequencies of the classes.
selects the sample based on subjective FREQUENCY POLYGONS
judgment rather than random selection. • The frequency polygon is a graph that
• In this method, not all the members of displays the data by using lines that
the population have a chance to connect points plotted for the
participate in the study. frequencies at the midpoints of the
Types of Non-Probability Sampling Method classes.
Convenience Sampling • The frequencies are represented by the
heights of the points.
• In a convenience sampling method, the
samples are selected from the OGIVE
population directly because they are
 • The ogive is a graph that represents the the value and dividing the result by the
cumulative frequencies for the classes in standard deviation.
a frequency distribution. PERCENTILE
• This type of graph is also called the 𝒋
𝑷𝒋 = (𝒏 + 𝟏)
cumulative frequency graph. 𝟏𝟎𝟎
BAR GRAPH QUARTILE
• A bar graph represents the data by using 𝟏
𝑸𝟏 = (𝒏 + 𝟏) = 𝟎. 𝟐𝟓(𝒏 + 𝟏)
vertical or horizontal bars whose heights 𝟒
or lengths represent the frequencies of 𝟐
𝑸𝟐 = (𝒏 + 𝟏) = 𝟎. 𝟓𝟎(𝒏 + 𝟏)
the data. 𝟒
𝟑
PARETO CHART 𝑸𝟑 = (𝒏 + 𝟏) = 𝟎. 𝟕𝟓(𝒏 + 𝟏)
𝟒
• A Pareto chart is used to represent a
DECILE
frequency distribution for a categorical
𝒋
variable, and the frequencies are 𝑫𝒋 = (𝒏 + 𝟏)
𝟏𝟎
displayed by the heights of vertical bars,
BOX AND WHISKER PLOT
which are arranged in order from highest
• A box and whisker plot (also called a box
to lowest.
plot) displays the five-number summary
TIME SERIES GRAPH
of a set of data.
• A time series graph represents data that
• The five-number summary is the
occur over a specific period of time.
minimum (𝑳𝑽), first quartile (𝑸𝟏 ),
PIE GRAPH median (𝑴𝒅), third quartile (𝑸𝟑 ), and
• A pie graph is a circle that is divided into maximum (𝑯𝑽).
sections or wedges according to the MEASURES OF DISPERSION
percentage of frequencies in each
• The measure of dispersion (or measure
category of the distribution.
of variation) indicates the scattering of
MEASURES OF CENTRAL TENDENCY data.
•A measure of central tendency is a ABSOLUTE MEASURES OF DISPERSION
summary measure that attempts to
• If the dispersion of data within an
describe a whole set of data with a single
experiment must be determined, then
value that represents the middle or
absolute measures of dispersion should
center of its distribution.
be used.
MEASURES OF LOCATION
RANGE (𝑹)
• It is also known as the measure of
• It is the difference between the highest
position.
value and the lowest value in the data
• These measures include standard scores, set.
percentiles, deciles, and quartiles.
VARIANCE
• They are used to locate the relative
• It is the average of the squares of the
position of a data value in the data set.
distance each value is from the mean.
Z-SCORE
STANDARD DEVIATION
• A z-score or standard score for a value is
• It is the positive square root of variance.
obtained by subtracting the mean from
 • It is the most commonly used measure of
dispersion. It indicates how closely the
values of a given data set are clustered
around the mean.
MEAN ABSOLUTE DEVIATION (𝑴𝑨𝑫)
• The mean deviation gives the average of
the data's absolute deviation about the
central points.
QUARTILE DEVIATION (𝑸𝑫)
• It is also known as semi-interquartile
range.
• It is half of the difference between the
upper and lower quartile.
RELATIVE MEASURES OF DISPERSION
• If the data of separate data sets have
different units and need to be compared,
then relative measures of dispersion are
used.
COEFFICIENT OF RANGE (𝑪𝑹)
• It is the ratio of the difference between
the highest and lowest value in a data set
to the sum of the highest and lowest
value.
COEFFICIENT OF VARIATION (𝑪𝑽)
• It is the ratio of the standard deviation to
the mean of the data set.
COEFFICIENT OF MEAN DEVIATION (𝑪𝑴𝑫)
• This can be defined as the ratio of the
mean deviation to the value of the
central point from which it is calculated.
COEFFICIENT OF QUARTILE DEVIATION (𝑪𝑸)
• It is the ratio of the difference between
the third quartile and the first quartile to
the sum of the third and first quartiles.