We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 17
NATURE OF BIOSTATISTICS
ALVIN DUKE R. SY, MSPH, RN
Learning Objectives
At the end of the session, the learners should be able to:
explain the role of biostatistics in public health,
differentiate the different types of data, and
® discuss common terms associated with biostatisticsTDP ea
Data is Everywhere!
Data is utilized and summarized frequently...
...in research literature
OF 156 and 155 participants in usual care and clinical
pathway periods, during their initial care, 60 (38.5%) usual
care participants were hospitalized, and 27 (17.6%) pathway
participants were hospitalized (difference = 20.8
percentage points [PP], 95% confidence interval [Ci] = 10.4
to 31.2 PP). Over 44 days, 70 (44.9%) usual care and 44
(28.8%) pathway participants were hospitalized (difference
16.1 PP, 95% Cl = 4.9 to 27.4 PP).* Data is utilized and summarized frequently...
~» in research literature
=, is populormndig
A report from the CHO HIV/AIDS Core Team showed
that the confirmed cases in the city already increased to
112 as of the end of September, a significant increase
from the 44 detected last year. A total of 27 new
HIV/AIDS cases were reported on July, 23 cases in
August, and 18 in September, with the youngest involving
15-year-old male.
* Data is utilized and summarized frequently...
~»...in research literature
+... popular media
* Data can be analyzed and summarized to provide useful
information.
» BAD data can be analyzed and summarized to provide
incorrect or harmful or non-informative information.
SEE ee |
6Stal'sbicy
isa science dealing with the collection,
organization, analysis, and interpretation of
numerical data.
Public Health Statistiex
refer to quantitative data needed as basis for planning,
monitoring, and evaluation of health services
* Vital statistics
data on vital events (births, deaths, marriage)
* Health statistics
data on morbidity (causes and frequency of illness)
hospital and clinical statistics (no. of admissions and discharges, be
occupancy, length of stay, etc.)
~ service statistics (no. of baby immunized, no. household with sanitary
toilet, no. of women practicing family planning, etc.)Brostalistes
.wis the scientific discipline focused with the application of
statistical principles concerning biological problems
_-specific applications include public health, medical
sciences, agriculture, environmental and ecological sciences
Brostabsbes
__can be useful in cerms of being:
¥ adata processing & analytics technique,
¥ a tool for objective appraisal and evaluation,
¥ a tool for decision-making, or
¥ a tool to design and analyze research well“assessment of the health status in
the community
(risk factors)
= prevention and control of disease
= monitoring and evaluation of
health interventions
® provision of health policy
formulation and health care
planning
Descriptive
+ summarize and present data
~* measures of central tendency
measures of dispersion and
location
~* tabular presentation
~* graphical presentation
—
2
= determination of disease causation ®
Inferential
* predictions, generalizations, and
conclusions
~» estimation of parameters
~~» hypothesis or significance testingDesersptive Statistics
>» ..tabulation of number of probable dengue cases per region
in the Philippines
>» .ause of histogram to present frequency distribution of
newborns based on their birthweight
>> calculation of average length of stay of patients in the
hospital
B
Population population
Sample
Select a sample
from the populationEstimation
woprocess by which a statistic computed from a random
sample is used to approximate or estimate the corresponding
parameter
..generation of point or interval estimates
Hypothesis testing
..Set of procedures that culminates in the rejection or non-
rejection of the null hypothesis based on the probability of
occurrence of the sample results if the null hypothesis were true
=~
Nature Cy Statistical Data21/08/2023
* Statistical data must have the following characteristic:
~ expressed numerically,
~* treated as a mass or group of observations, and
~~» subject to variation
Vaniabilly
«tendency of a measurable characteristic or
behavior to change
.-Statistics is necessary to analyze variabilityVariable
..refers to the measurement or characteristic of
interest
Conta
..a phenomenon whose value remains the same from person to
person, from time to time, or from place to place
*= pull of gravity = 6.674x10-" m&kgr hs?
= speed of light = 299,792,458 meters per secondA study was done among UP Manila students to determine the
proportion of current smokers
School Smoking status
Constant Variable
ony
2
A study was done among universities in Manila to determine the
proportion of students who are current smokers
School Smoking status
Variable Variable
cI er |
2Qualitative
non-quantifiable categories
numerical representation as
labels or codes only
sex
educational level
disease status
eye color
Quantitative
values indicate quantity or
amount
either discrete or continuous
discrete variables assume only
integral values or whole numbers
continuous variables attain any
value including fractions and
decimalsNombenl,
+ ..a classificatory scale used only as labels
* ..represent a set of mutually exclusive and exhaustive classes
~* sex (male or female)
~+ blood groups (i.e., A+, B+, AB+, O+)
~+ medical diagnosis (e.g., HA Pneumonia, CAP, etc.)
25
Gulia,
» shas similar characteristics to nominal variables, but the
categories can be ordered or ranked
-+ disease severity (e.g., Mild, Moderate, Severe)
“+ age groups (e.g., Infant, Child, etc.)
~ rating (e.g., Agree, Disagree, etc.)
26Ledewal
« ..has similar characteristics to ordinal variables, however the
distances between all adjacent classes are equal
* ...these variables do not have a true zero point (arbitrary)
~* temperature in Celsius
» calendar time
* standard IQ test
27
Rufio
avith similar characteristics to variables of interval scale, except it
has a meaningful zero point (that exists)
+ ..the “ratio” of two ratio variables can be meaningfully computed and
interpreted
~+ blood pressure
* number of doctor visits
~» weight and height
28¥ A variable can either be quantitative or qualitative at one
point in time, but not both, at the same time.
¥ A variable can be classified under one scale or level of
measurement only at a single point in time
¥ A variable can be quantitative or qualitative depending on
the objective of the data collection
¥ Likewise, the scale of measurement can vary depending on
how the variable is treated
Se ee
30* ...to make sense of massive amount of information
* .needed to avoid reaching invalid conclusions out of limited data
~» Research has shown that the ability to generalize from a sample to a
population is hardwired into our brains and has been observed in
eight-month-old babies
* ..essential to avoid being fooled by seeing apparent patterns
among random data
: qh, certain
pveTay Celaya
Daniel WW & Cross CL Biestaistics: A Foundation for Analyssin the Health Science, roth ed. New York:
Wiley, 2013.
Gubulani R. Group worved over surge of HIV/AIDS cases in GenSan, Philippine News Agency, Oct 7, 2021
Ittps:{fiww.yma gov.phtarticles/n55859
-MedinaJRC. Lecture Notes on Bistalistis, Department of Epidemiology & Biostatistics, Collegeof Public
Health, UP Manila 2022.
‘Mendoza OM, Borja MP, etal Founuations of Statistical Analysis forthe Health Sciences, UP Manila: DEBS,
‘alan DA, Mower WR, etal Pathway wth single-dose long-acting intravenous antibaticreduees emergency
department hospitalizations of patients with skin infections, Acad Em Med, 20%; 28(0):108-17