BIOSTATISTICS

PHARMACY RESEARCH AND THESIS WRITING

STATISTICS

 Scienceof conducting studies that

COLLECT, ORGANIZE, SUMMARIZE,
ANALYZE and CONCLUDE from data.

“Datum” – fact or information

BIOSTATISTICS

Application
of statistical methods
to medicine and biological
problems.
Statistical Tools

 Descriptive Statistics
 Inferential Statistics
Descriptive Statistics

 Collection, organization and presentation of data

 Data are simply being described
 Ranking, computation of percentages, mean,
median and mode.

Examples:
- Fifty percent of the elderly patients are hypertensive.
- Four out of ten adult Filipino males are at risk of
developing prostate cancer
Inferential Statistics

 Generalizing characteristics obtained from samples,

performing hypothesis testing, determining relationships
among variables and making predictions.
 Significant difference (T-test, Z-test, ANOVA)
 Significant relationship – Pearson Correlation ( r )

Examples:
- Smoking increases the risk of lung cancer.
- Several studies showed that consumption of Vitamin A
prevents cancer.
POPULATION Versus SAMPLE

 Population
- groups / aggregates of people, objects, materials,
events or thing of any form.
- measures of a population is known as PARAMETERS.

 Sample
- sub-group of a population
- measures of the sample – ESTIMATES or STATISTICS
 POPULATION SAMPLE
Scores of entire students in the Scores of students in a class
secondary level
All children of ay age who have The 40 children who actually
older or younger siblings participated in one specific study
about siblings.

Board rating of Pharmacy Board rating of Pharmacy

graduates in Baguio City graduates in PCC.
VARIABLES and DATA

 DATA
- Raw materials (sets of numbers) obtained from counting
or measuring things.

* Surveys
* Experiments
* Numerical records
* Questionnaires
 VARIABLES and DATA

 VARIABLES
- Characteristic which may vary from one individual/object
in a sample.

* Age
* Sex / Gender
* Personality
* Religious affiliation
* Civil status
Types of Variable

➢ Qualitative Variables – represent differences in

quality, character or kind
Eg. Sex / gender, nationality, eye color

➢ Quantitative Variables – numerical in nature, can be

ordered or ranked.
Eg. Age, height, weight, score
 Classification of Quantitative Variables

➢ Discrete – values can be counted using integral values

Eg. Number of patients in a ward
Number of deaths in a year
Number of enrolled subjects

 Continuous – variable that can assume a numerical value over an

interval/s.
Eg. Weight, Serum cholesterol
Height, Hemoglobin level
RBC count
Independent and Dependent Variables

 Independent Variable – stimulus variable that is

manipulated; predictor; remains constant.

 DependentVariables – response variable which is

observed & measured to determine the effect of
the independent variable; it changes when the
independent variable varies.
 Examples:

 Effect of sunlight on the growth of plants

- Independent V. (sunlight); Dependent V. (growth of plant)

 Effect of study habits of students to their academic

performance.
- Indept. V. (study habits); Dept. V. (academic performance)
SCALES OF MEASUREMENT OF DATA

 Nominal Data – use numbers in identifying name

or membership in a group/category
 Ordinal Data – connote ranking or inequalities.
 Interval Data – indicate an actual amount with
equal unit of measurement separating each
score.
 Ratio Data – has an absolute zero and multiples
are meaningful
 EXAMPLES
NOMINAL DATA ORDINAL DATA
Sex / Gender Birth Order
1. Female First Third Fifth
2. Male Second Fourth Sixth
Civil Status Size
1. Single 3. Widowed Small, Medium, Large
2. Married 4. Separated
Nationality Income
1. Filipino 3. Chinese High, Medium, Low
2. Sudanese 4. British
Profession Stages of Cancer
1. Pharmacist 3. Nurse Grade 1, Grade II, Grade III
2. Medical Technologist 4. MD
 EXAMPLES

INTERVAL DATA RATIO DATA

Temperature Length, weight, area, volume, density,

velocity

Aptitude test scores Money, salaries, wages

Scores on tests Speed, election votes

 Important Personalities

 Adolf Quetelet - Father of Modern Statistics; a Belgian who

considered statistics as the queen of science.
 Francis Galton & Karl Pearson – theory of regression and
correlation
 Carl Gauss – derivation from study of errors from repeated
measurements - GAUSSIAN DISTRIBUTION
 William Gosset – small sample theory
 John Graunt – percentages of deaths from suicides, accidents
and various diseases remained constant.
 Abraham de Moivre – equation of normal distribution.
Sample Size

Formula: (Slovin’s formula )

N
n = ---------------
1 + Ne2

Where:
n = sample size
N = size of the population
e = margin of error (NMT 5%)
 Examples:

Use Slovin’s formula to find out what sample of a population of 1,000 people you need to
take for a survey on their soft drinks’ preferences.

Step 1: Figure out what you want your confidence level to be. For example, you might want
a confidence level of 95% (which will give you a margin of error of 0.05), or you might need
better accuracy at 98% confidence level (which produces a margin of error of 0.02).

Step 2: Plug your data into the formula. In this example, you use a 95 percent confidence
level with a population size of 1,000.
n = N/(1 + N e2) = 1,000/(1 + 1000*0.05 2) = 285.714286

Step 3: Round your answer to a whole number (because you can’t sample a fraction of a
person or thing) 285.714286 = 286
 VITAL STATISTICS

 Anaspect of biostatistics concerned with

measurements and comparisons of data
pertaining to human life.
 Frequency of births, diseases, deaths, etc.
 Events
are expressed in proportions,
percentages or ratios
 RATIOS

Ratio = no. of cases in a particular event in a period of time

no. of cases in a different event in a period of time

Example: For the past 6 months, the number of reported male HIV positive cases in Manila was
20, while that for females were 40. What is the ratio of HIV positive females to that of HIV positive
males in Manila?
Ratio = no. of reported HIV(+) females in Manila for the past 6 months
no. of reported HIV(+) males in Manila for the past 6 months
= 40/20 or 2:1
Interpretation: There are two reported HIV positive females to one HIV positive male in Manila for
the past six months.
 FERTILITY RATES

 Crude Birth Rate (CBR)

CBR = no. of registered live births in a year x 1,000
midyear population

➢ General Fertility Rate (GFR)

GFR = no. of registered live births in a year x 1,000
midyear population of women 15-44 (15-49)
 Crude Birth rate (CBR)

The midyear population of Davao City in 2004 was 5,000,000 while that
in Zamboanga City was 3,500,000. If the number of registered births in
Davao City was 120,000 and that of Zamboanga City was 105,000 in
2004. Which City has a higher Crude Birth Rate?
General Fertility Rate (GFR)

The following table gives age-specific number of women and births in a given
year of a country. The mid-year population of the country was 45,879. There was
no birth after age 44. calculate the following and interpret the results:
a. Crude birth rate (CBR)
b. General Fertility rate (GFR)
 MORTALITY RATES

 Crude Death Rate

CDR = no. of deaths in a calendar year x 1,000
midyear population
 Age-Specific Mortality Rate
Specific MR = no. of deaths in a specified group in a year x 1,000
midyear population of specified group
 Cause-Specific Mortality Rate
Cause-Specific MR = no. of deaths from a certain cause in a year x 1,000
midyear population
 Exercise:

The town in Limay, Bataan with a midyear population of 65,000 had

850 reported deaths for the previous year. Among other items
reported, it was noted that the highest mortality count was among
children 1-5 years of age accounting for 200 cases out of 20,000 in
that age bracket. The leading cause of death was bronchitis with a
death count of 145.
Compute for the: crude death rate, age-specific mortality rate and
cause of death rate.
 MORTALITY RATES

 Infant Mortality Rate

IMR = deaths under 1yr of age in a year x 1,000
no. of live births in the same year
 Swaroop’s Index
Swaroop’s Index = no. of deaths 50yrs old and above x 1,000
total no. of deaths in a year
 Case Fatality Rate
CFR = deaths from a specified cause x 1,000
no. of cases of the same disease
 MORBIDITY RATES

 Incidence Rates = no. of new cases of a disease in a period of time x Factor

total population at risk in a period of time

 Prevalence Rates = no. of existing cases of a specific diseases at a point of time x F

total population at risk at the same point of time

 Factor (F) = 100, 1,000, 10,000, 1,000,000,000, etc.

 Months Incidence rate Prevalence rate
July

August

September

October

November

December

Compute for incidence and prevalence rates of illness in the lives of 12 people
from July to December of 2012. Show all solutions.
In what month was the incidence highest? ___________________________
In what month was the prevalence highest? __________________________
In what month was the prevalence lowest? ___________________________
RELATIVE MEASURES OF DISEASE FREQUENCY

 Relative Risk (RR)

RR = incidence of disease in exposed group
incidence of disease in unexposed group
 Odds Ratio (OR)
OR = odds in favor of disease in exposed group
odds in favor of disease in unexposed group
 Attributable Risk (AR)
AR = (incidence of disease in exposed group) – (incidence of disease in unexposed group) x 100
incidence of disease in unexposed group
It was found in a recent survey that the incidence of lung
cancer among smokers is 50 per 1,000,000 population per
year; and the incidence for non-smokers is 10 per 1,000,000
per year. Compute for the: Relative risk; Odds ratio;
Attributable risk
Assessment 1B:

Answer and submit the following sample exercises in solving vital

statistics. Follow the format:
1. Problem statement / Scenario / Data
2. Formula
3. Equation
4. Solution, Highlight with red ink the final answer.
5. Interpretation of your result
THANK YOU