Introduction to

Biostatistics: Collection
and Presentation of Data

Course: Introduction to Biostatistics and Epidemiology

Laboratory
Presented by: Enoch Taclan BSBIOL, MSBIOL
Why Study Statistics?
Because numbers are
everywhere
Statistics allows us to 3
things:
•Understand a phenomenon
•Derive conclusions and inferences
•Make reasonable (and intelligent)
decisions
STATISTICS

• It is a discipline of study concerned with collection, organization and

presentation, analysis, and interpretation of data.
• Collection of Data – it is the most important aspect
• Organization or presentation of data – edit, classify, tabulate or
present your data into graphs
• Analysis – once data is collected, organized and presented it is
important to analyze it to get a better understanding of the subject
• Interpretation – draw conclusions and inferences from it
BIOSTATISTICS

• A broad discipline involving the application of

statistical principles to the problems in medicine
and public health
• The best example for this is how we use and
gather data during this pandemic.
POPULATION vs SAMPLE

POPULATION SAMPLE
- Entire collection of A subset or small portion
individuals or objects of a population that is
about which information is selected for study → “n”
desired → “N”
− Ex. 50 ER patients in
− Ex. All patients in AMCM AMCM participated in a
participated in a survey to survey to determine
determine blood pressure. blood pressure.
PARAMETER vs STATISTIC

PARAMETER STATISTIC
- It is any characteristic of a An estimate of a parameter.
population. − Any value or measurement
obtained from the sample.
− Ex. The average diastolic
blood pressure of all − Ex. The average diastolic
patients in AMCM is 78 blood pressure of 50 ER
mmHg. patients in AMCM is 75
mmHg.
 DESCRIPTIVE VS INFERENTIAL

DESCRIPTIVE STATISTICS INFERENTIAL STATISTICS

- Describes the characteristics and properties of a - Uses data gathered from a small portion of a
particular group of people, places, or things. larger group (sample) to make an inference or draw
conclusion about the characteristics or attributes of
Ex. According to a survey of 100 a larger group (population) from which the sample
MT students, 25% are coffee drinkers was drawn.
and their average exam − Ex. Coffee consumption
score is 90. the remaining 75%
significantly improves test scores
are non-coffee-drinkers and of college students.
their average exam score is 85.
DATA

• Any value that represent an observation or measurement of a certain

characteristic about people, processes, and condition.
TWO CLASSIFICATIONS OF DATA

Primary Data Secondary Data

• Obtained through • Published or

observation, unpublished data
survey, interview, taken from an
experiments agency or person
who have already
used the data for
their own needs
VARIABLE

• A characteristic that can take on different values

for different members of a group or set
Ex. MLS3 students enrolled in Bio-Epi subject
• Hair color
• Height
• No. of siblings
CONSTANT

• A characteristic that does not vary (does

not change) and assumes only one value.
Example:
• Pi (π) = 3.14159
• Speed of light = 299792458 m/s
CLASSIFICATION ACCORDING
TO FUNCTIONAL RELATIONSHIP
a. Independent Variable “manipulated variable”
- Its value is independent of other variables in
your study.
- It is not affected nor changed by any other
variable because only the researcher can
manipulate or change it.
b. Dependent Variable “responding variable”
-It is the outcome the researcher studies and
measures.
- It changes depending on the changes to the
independent variable.
INDEPENDENT VS DEPENDENT

Example:
• Drinking coffee in the morning (IV) increases test
scores (DV).
• A study was conducted to determine whether social
media
use (IV) affects productivity level (DV).
CLASSIFICATION ACCORDING TO
THE TYPE OF DATA PROVIDED
a. Qualitative Variable “categorical variable”
- Yield observations that can be categorized according to
some characteristic or quality.
− Answer the questions: “What type?” or “Which category?”
Ex. Hair colors, Nationality
b. Quantitative Variable “numerical variable”
-Yield observations that can be counted or measured in the
usual sense. They represent quantities.
- Answer the questions: “How many?” or “How much?”
ex. No. of siblings, Height
CLASSIFICATION OF QUANTITATIVE VARIABLES
ACCORDING TO CONTINUITY OF VALUES:

a. Discrete
- Whole Numbers or
Integer, obtained by
counting
Ex. No. of siblings,
No. of textbooks
purchased, No. of
patients admitted in
AMCM
CLASSIFICATION OF QUANTITATIVE VARIABLES
ACCORDING TO CONTINUITY OF VALUES:

b. Continuous
- Fractions or
decimals ,
Measurable
quantities not
restricted to a
whole number
Ex. Height, Weight,
Temperature
SCALES OF MEASUREMENT
a. Nominal Scale - Values of data are categories or labels
that do not have a regular order or ranking . “naming” or
classifying data.
Ex. Hair color – black, brown, blonde, red
Marital Status – single, married, separated, widowed
b. Ordinal Scale - The term “ordinal” refers to “order” or
“rank”
- Relative position can be determined but not
the
magnitude of difference between them.
Ex. Academic Ranking – top 1, 2, 3 etc
Performance Rating Scale – poor, fair, very good,
excellent
BOTH Ordinal and Nominal scales have descriptive qualities.
Key Difference : there is relative position of labels in
SCALES OF MEASUREMENT
a. Interval Scale - Values or
observations that can be ordered and
measured on an evenly distributed
scale beginning at appoint other
than true zero. “Zero is arbitrary
and ratios are meaningless” “NO TRUE
ZERO”

Ex. Temperature in Celsius and

Fahrenheit

b. Ratio Scale - Values or observations

can be ordered and measured on an evenly
distributed scale “interval scale with
true zero”
- Highest level of
measurement

Ex. Age — 25 y/o, 50 y/o, 75 y/o, 100

y/o,
Height — 5 meters, 10 meters
(twice as long as 5m)
DATA PRESENTATION

To communicate
Organization of
results clearly and
data effectively
PRESENTED IN THREE WAYS:

• Textual Form
• Tabular Form
• Graphical Form
TEXTUAL PRESENTATION
• Data are written and read as they are presented in
paragraphs or sentences
• An expository form describing an information
• Can be used to enumerate important characteristics,
emphasize significant figures, and identifying key
features of data

• If quantitative information to be conveyed

consist only of one or two numbers, then you can
use text than tables or graphs.
TEXTUAL PRESENTATION
• EXAMPLES: 40 item BIO-EPI Exam
TEXTUAL PRESENTATION
• In textual format, it
can be presented as
“In a class of 40
students, the highest
score is 39 while the
lowest is 10. Overall,
the students performed
fairly in the exam
with 23 or 58% getting
a passing score of 26
and above.”
TABULAR PRESENTATION

• Tables convey information that has been

converted into words or numbers in rows and
columns.
• An expository form describing an information
STRENGTHS:
Can accurately present numerical data
Different units can be organized
together
All data are given equal importance
 FREQUENCY DISTRIBUTION
TABLE
• a tabular arrangement of
data together with the
corresponding
frequencies.

• Frequency - the
number of times a
particular data point
occurs in a set of
data.
• Ungrouped data – is
data given as
individual data
points
• Grouped data - is
given in classes or
intervals
ANATOMY OF A FREQUENCY
DISTRIBUTION TABLE
ELEMENTS OF A FQT
 Frequency – number of values that will fall within interval
- number of times that a particular score or value
appears in data set
 Class Intervals – the number defining classes
 Class Limits – the end number of each class
 Upper Limit - highest values that can belong to a class
 Lower Limit - lowest value that can belong to a class
 Class Size – difference between 2 consecutive lower-class limits
 Class Mark or Midpoint - respective average of each class (Upper limit +
Lower limit /2)
 Class Boundary – defined as the “true class limits”
 Lower CB – value halfway between Lower Limit of the class and Upper Limit
if the previous class
 Upper CB – value halfway between LL of the class and UL of the next class
GUIDELINES IN CONSTRUCTING
FREQUENCY
DISTRIBUTION TABLE
• Uses 5 to 15 classes
• Classes must be continuous
• Each observation goes only into one entry of
a class
• So, if there are 40 values in a data set,
40 frequencies must be reflected on your
table, no more no less.
• Equal sizes/width for all classes
• It is recommended that the class size is an
odd number
HOW DO WE MAKE A FREQUENCY
DISTRIBUTION TABLE
STEPS IN CONSTRUCTING FREQUENCY
DISTRIBUTION
TABLE:

• STEP 1 : Establish the number of class and class

size
Sturges’ Formula:

K = 1 + 3.322 log (n)

where K is the approximate number of classes

n is the number of observations
STEPS IN CONSTRUCTING FREQUENCY
DISTRIBUTION
TABLE:
• STEP 2 : Compute for the suggested class size
using Freund and
Simon Formula.

Range - HIGHEST SCORE – LOWEST SCORE

Range - 39 – 10 = 29
Class Size = 29 / 6 = 5 → class intervals will
have a size/width of 5
STEPS IN CONSTRUCTING FREQUENCY
DISTRIBUTION
TABLE:

• STEP 3 : Determine
the lower-class limit

• STEP 4 : - Determine
all the class limits,
by adding the size “c”
− Simply
add the class size (5)
to the limit of the
previous class (both 10
and 14 and so on).
STEPS IN CONSTRUCTING FREQUENCY
DISTRIBUTION
TABLE:

• STEP 5: Tally the

scores and complete
the frequency
distribution table
• Sum the frequencies
and check against
the total number of
observations
VARIATIONS OF FREQUENCY
DISTRIBUTION TABLE

• Relative and Frequency

Percentage
• Shows the proportion
of observations
falling in each
class interval
• Shows the total
proportion of the
total number of
observations
associated with each
value or class
VARIATIONS OF FREQUENCY
DISTRIBUTION TABLE: RF

CLASSES FREQUENCY ( RELATIVE PERCENTAGE

f) FREQUENCY (%)
(rf)
35-39 8

30-34 8

25-29 8

20-24 6

15-19 5

10-14 5

TOTAL 40
VARIATIONS OF FREQUENCY
DISTRIBUTION TABLE
• Cumulative Frequency
• The cumulative frequency is calculated by
adding each frequency from a frequency
distribution table to the sum of its
predecessors.
• This column is prepared by adding in
successive class frequencies starting at
the lowest class interval
VARIATIONS OF FREQUENCY
DISTRIBUTION TABLE: CF
CLASSES FREQUENCY ( CUMULATIVE
f) FREQUENCY
(cf)
35-39 8

30-34 8

25-29 8
20-24 6

15-19 5

10-14 5

TOTAL 40
GRAPHICAL PRESENTATION

• Use of graphs or charts to show numerical

data or relationships of variables
• Effective for simplifying complex
information for easy comprehension by using
images to emphasize data patterns or trends
and are also very useful for summarizing,
explaining, or even exploring quantitative
data.
Qualities of a Good Graph
Appropriate
Easily comprehended
• Graphs, just like tables, should be self-
explanatory
Well labeled
• Descriptive title
• Legend or key
• Units
• Labeled axes
• Both axis should be
labeled with both the
name of the variable
and the units which the
variable was measured
FOUR COMMON TYPES OF GRAPHS OR
CHARTS

 Bar/Column Graph
• A rectangular bars
where the
height/length of the
bar represents the
quantity of
frequency for each
category.
FOUR COMMON TYPES OF GRAPHS OR
CHARTS
 Histogram
• Is a pictorial or
graphical
representation of
the distribution of
data that has been
grouped into classes
• Suitable for
quantitative
continuous data
• No spaces in between
bars
FOUR COMMON TYPES OF GRAPHS OR
CHARTS

 Pie Chart
• Is a simple easily
understood chart,
basically what you
see is what you get.
• A circular graph
showing how a total
quantity is
distributed among a
group of categories.
FOUR COMMON TYPES OF GRAPHS OR
CHARTS

 Line graph
• This illustrates
patterns or trends
of quantitative or
numerical data over
a primary variable
which is time.
• Method of choice for
plotting data over
time