LESSON 1- INTRODUCTION TO DESCRIPTIVE • it is the complete collection of all elements (e.g.

,
ANALYTICS scorers, people, measurements, etc.) tobe
studied.
Descriptive Analytics • overall numbers
• classification: finite (countable); infinite (we do
• the transformation of raw data into a form that not have control of)
will make them easy to understand and interpret;
rearranging, ordering, and manipulating data to Sample
generate descriptive information
• it will give a single value that will represent the • a portion of a population
set of values • represents the population
• concerned largely with summary calculations and
graphical displays, or simply summarizing or Types of Samples:
describing important features of a set of data
• the root cause of an event 1. Purposive: direct relations and drawn from the
population deliberately
Descriptive Techniques 2. Probability: random and drawn from the
population by following set of rules wherein each
• a matter of getting all the data together unit in the population has an equal chance to be
• include constructing tables of means and chosen as a sample
quantiles, measures of dispersion such as
variance or standard deviation, and cross- Sampling Techniques
tabulations or “crosstabs" that can be used to
examine many disparate hypotheses 1. Simple Random Sampling
• the data which have been collected, organized
and presented need to be given meaning and • random
interpreted properly • commonly used
• interpretation of data using descriptive statistics • population are selected in such a way that each
depends on the purpose or purposes intended by unit in the population has an equal chance of
the investigator being selected

Population Illustration: You want to select a simple random sample

of 100 employees of Company X. You assign a number
to every employee in the company database from 1 to
1000, and use a random number generator to select 4. Cluster Sampling
100 numbers.
• population area was first subdivided into sections
2. Stratified Sampling (or clusters), then randomly select a few of those
sections, and then choose all the members from
• divided into two categories (e.g., gender) those selected sections
• population was divided into at least two different
subpopulations (strata) that share the same Illustration: The company has offices in 10 cities across
characteristics (such as IQ, gender, educational the country (all with roughly the same number of
attainment, etc.) and the samples are drawn employees in similar roles). You don’t have the capacity
from each stratum to travel to every office to collect your data, so you use
random sampling to select 3 offices – these are your
Illustration: The company has 800 female employees clusters.
and 200 male employees. You want to ensure that the
sample reflects the gender balance of the company, so Reasons for Sampling
you sort the population into two strata based on gender.
Then you use random sampling on each group, • Necessity
selecting 80 women and 20 men, which gives you a • Practicality
representative • Cost-effectiveness
sample of 100 people. • Manageability

3. Systematic Sampling Scales of Measurement

• used for specific reason • the data we gathered from research/survey

• select a starting point (random start) then select observations on the different individuals may
every kth (such as every 10th) element in the classified according to the scale of measurement
population that we used
• measurement is defined as the assignment of
Illustration: All employees of the company are listed in numbers or labels to the observation
alphabetical order. From the first 10 numbers, you
randomly select a starting point: number 6. From Four Levels of Measurement
number 6 onwards, every 10th person on the list is
selected (6, 16, 26, 36, and so on), and you end up with 1. Nominal (classificatory) Scale
a sample of 100 people.
 • assigns names and labels to classify respondents • provides the most detailed information as
researchers and statisticians can calculate the
Examples: demographics of a survey; gender central tendency using statistical techniques

2. Ordinal (ranking) Scale Examples: SWOT; TURF; Cross-tabulation; Conjoint

• assigns numbers or labels to observations with

implied ordering
• numbers or labels are used to order the
respondents or objects without giving how much
of the attribute they possess
• not only assigns values to the variables but also
measures the rank or order of the variables LESSON 2- DATA COLLECTION AND
• rank and level PRESENTATION

Examples: Likert scale; rating survey Data Collecting

3. Interval Scale • the process of gathering the information that

you need
• assigns real numbers to observations to reflect
distance between rank position of the Data
respondents or objects in equal units
• can be manipulated algebraically by addition or • displays can relate a qualitative variable and a
subtraction but not division or multiplication quantitative measure such as a count or percent
• raw materials for further analysis
Examples: mean, median and mode (central tendency);
income; Net Promoter Scale (NPS); Bipolar Matrix Table Types of Data

4. Ratio Scale 1. Numerical (quantitative) Data

• assigns numbers to observations to reflect the • more on measurements

existence of true absolute zero points as its origin • particular numerical values

Categories:
 a) Discrete Numerical: represented by whole 1. Interview
numbers (e.g., 1,2,3) • a person-to-person encounter between the
b) Continuous Numerical: can take any value in a interviewer and interviewee.
range (such as heights, weights and • e.g., personal, telephone, or through an Internet
temperatures) access interview

2. Category (qualitative) Data 2. Questionnaire

• utilized a pre-arrangement question to gather
• more on labels information
• measured by nominal scale • e.g., mailed/hand carried, newspaper,
magazines, radio, TV, Internet access, to
Sources of Data intended respondent

1. Documentary Sources 3. Observation

• pertaining to the behaviors of the individuals or
• contained in published and unpublished group of individuals during the given situation
documents, reports, statistics, manuscripts, are best obtained through observations.
letters, diaries, etc. • e.g., service station, fast food chain, supervisors
• Primary: first information relevant to the given doing rounds
problem or the firsthand information
• Secondary: data that have been transcribed or 4. Experimental
compiled from the original sources • designed for collection data through
experimentation
2. Field Sources • chemist and medical fields
• for scientific inquires
• living person who have fund of knowledge or • e.g., experiment in class
have an intimate contact with the social
condition and changes over a considerable 5. Used of Existing Documents
period of time • those that are published for public use
• those who are in the field to get the information
(e.g., newscaster) Data Presentation

Methods of Data Collection 1. Textual

• data are presented into a paragraph of text
 2. Tabular 6. Pareto Chart
• systematic presentation of data in rows and • 80%-20% principle by Vilfredo Pareto
columns • combination of bar graph and line graph
• recommended for correlation
3. Graphical • identifies the problem areas or tasks that will
• device for showing numerical values or have the biggest payoff
relationships in a pictorial form • used to know the defect

Types of Graph 7. Fishbone Diagram

• shows the causes of an event and is often used
1. Line Graph in manufacturing and product development
• usually of the purpose of monitoring progress • for qualitative data
• effective device for showing trends over a period • 6M’s (manpower, machinery, methods,
of time materials, measurement, and mother nature)
• Horizontal Lines for issues/ cause and Vertical
2. Pie Graph Lines for root cause
• Percentage
• shows the components of a whole 8. Scatter Diagram
• two-dimensional graphical representation of a
3. Bar Graph set of data
• important to know the difference of variables • usually used to know the relationships between
• for numerical and qualitative data variables (correlation)
• represents quantity or frequency for each • pairs numerical data with one variable on each
category axis to look for a relationship between them

4. Statistical Map 9. Histogram

• for census, statistics, and classification per area • used to represent the frequency distribution of a
• describe or classify geographical areas few data points of one variable
• used to know the data from past to present
5. Pictograph • e.g., distribution of salary
• corresponding image • bar graph represents qualitative and
• uses picture or symbols to represent definite and quantitative, histogram represents both
uniform value quantitative
 MIDTERMS REVIEWER True - nominal scale uses frequency table proportion to
two categories/ Used to categorize data into mutually
Variables - something measurable or observable that exclusive categories or groups
is expected to change over time or between individual
observations True - it is more efficient to collect data from a sample

Discrete - data that can only be particular numerical True – ratio scale is effective in SWOT analysis
values
False - a bar graph is an effective device for showing
Continuous - data that can take any value in a range trends over a period of time

Measurement - defined as the assignment of numbers False – ordinal scale is the highest measurement of
or labels to the observation scale

Ratio - highest scale False – histogram uses picture or symbols to represent

definite and uniform value
Nominal - lowest scale
False - researchers and statisticians uses interval scale
Ratio Scale - a scale that assigns numbers to to calculate the central tendency using statistical
observations to reflect the existence of true absolute techniques such as mean, median, mode, and methods
zero points as its origin such as geometric mean, the coefficient of variation, or
harmonic mean can also be used on this scale
Interview - a person-to-person encounter between the
interviewer and interviewee False – (may unang term pa dito nakalimutan ko)
mean, median, or mode can be used to calculate the
Textual - data are presented into a paragraph of text central tendency

Graphical - device for showing numerical values or True - beauty pageant is an example of ordinal scale
relationships in a pictorial form
True – gender is an example of nominal scale
Descriptive Analytics - transformation of raw data
into a form that will make them easy to understand and Secondary – magazine
interpret
Primary – love letter
Primary – journals <CF= top to bottom

Secondary – news >CF= bottom to top

Primary – diaries

Primary - thesis

Lesson 3- Frequency Distribution Table

R= 𝒉𝒊𝒈𝒉𝒆𝒔𝒕 𝒗𝒂𝒍𝒖𝒆 − 𝒍𝒐𝒘𝒆𝒔𝒕 𝒗𝒂𝒍𝒖𝒆

K= 𝟏 + 𝟑. 𝟑𝟐𝟐 𝐥𝐨𝐠 𝑵

C= 𝑹⁄𝑲

Class interval= C (the number of rows is equal to K)

Frequency= the number of times the value occurs in

the data

(𝒉𝒊𝒈𝒉𝒆𝒔𝒕 𝒗𝒂𝒍𝒖𝒆+𝒍𝒐𝒘𝒆𝒔𝒕 𝒗𝒂𝒍𝒖𝒆)

Class Mark=
𝟐

Class Boundaries=

𝒍𝒐𝒘𝒆𝒔𝒕 𝒗𝒂𝒍𝒖𝒆− . 𝟎𝟓, 𝒉𝒊𝒈𝒉𝒆𝒔𝒕 𝒗𝒂𝒍𝒖𝒆+ . 𝟎𝟓

𝑭
Relative Frequency= x 100 (f: frequency, n:
𝑵
population)