Introduction to

Biostatistics
Melanie Joy A. Arellano, RMT
 Learning Outcomes
At the end of this topic, you are expected to:
 Define biostatistics
 Explain the uses of biostatistics in the field of medical and
allied medical sciences
 Appreciate the importance of statistics in the field of
medical and allied medical sciences
 Discuss various types of variables
 Explain the different classification of data
 Identify various sources of data
 Explain various sources of data
 Biostatistics
 Etymology: “bio” = life; “statistics” =
science that deals with the collection,
organization, summarization,
presentation, and analysis of data
 Biostatistics is the application to a wide
range of topics in biology.
Biostatisticians

 Apply their skills in health-related fields and

collaborate with other researchers to answer
specific questions
 Guides on data collection, selection, and
implementation of appropriate methodologies,
and in the interpretation of results
 Develops new statistical methods
 Why Study Biostatistics?
 Health Administration – statistics helps administrators in the
recognition and projection of health manpower of a
community/country or estimates the health services needed.
 Clinical Medicine – for comparison of repeated observations
for the average estimate of certain physiological or
anatomical features of human beings as baseline data for
classification of individuals
 Clinical Investigation – statistics is involve in the continuous
search for more effective, non-toxic, and inexpensive
medicines for various ailments/diseases
Branches of Statistics
DESCRIPTIVE STATISTICS

 Descriptive statistics are used to summarize a set of data.

 Example:
Suppose you were teaching a class of 25 students, and you
wanted to know what the average score was for the test
that you just gave.

LIMITATION: do not allow us to make any inferences about

the population at large. This type of statistics simply
describes the data set that has been collected.
INFERENTIAL STATISTICS

 is statistics that are used to draw conclusions

(or infer) about a population based on a
sample of data that was collected from the
population.
 Inferential statistics allow us to make
inferences beyond the data set that was
collected from a sample, assuming that the
sample is representative of the population.
EXAMPLE:

 Suppose you were studying which of two diets

were most effective for weight loss in people
between 40 and 60 years old. You might have
300 people in your study: 100 doing Diet Plan
A, 100 doing Diet Plan B, and 100 doing no
particular diet (the control group). After a
certain amount of time, you could calculate
the results in terms of weight loss for each
group to see which (if any) was more effective.
Classification of Statistics
PARAMETRIC TEST

 If the information about the population is

completely known by means of its
parameters then statistical test is called
parametric test.
 Examples: t-test, f-test, z-test, ANOVA
Parametric: Normal Distribution, uses
mean, >/= 30 samples
 One-Sample: z-test/t-test
 Two Dependent Samples: t-test
 Two Independent Samples: z-test
 >2 Independent Samples: One-way ANOVA
 >2 Dependent Samples: Two-way ANOVA
 Parametric Statistics
Example:
A 99% CI for the true men calorie intake of
adults in a samples of 45 patients with a mean
of 15 grams and a SD of 7.5 grams ranging from
13.45 to 17.45 g

Can a researcher who interviewed 70 out of 100

conclude that more than 60% have completed
polio vaccine?
NON-PARAMETRIC TEST

 If there is no knowledge about the

population or parameters, but still is required
to test the hypothesis of the population. Then
it is called non-parametric test.
 Examples: mann- Whitney, rank sum test,
Kruskal-Wallis test.
Non parametric Statistics:

 One-Sample: Sign Test

 Two Dependent Samples: Wilcoxon Sign-Rank
 Two Independent Samples: Mann-Whitney
 >2 Independent Samples: Kruskal-Wallis
 >2 Dependent Samples: Friedman
 Non Parametric Statistics

Example:

Can we conclude that in a sample of 15

patients there is a median of 112.1mmHg?
Difference between parametric and non-
parametric
PARAMETRIC NON-PARAMETRIC

Information about population is No information about the population is

completely known available

Specific assumptions are made No assumptions are made regarding

regarding the population the population

Null hypothesis is made on parameters The null hypothesis is free from

of the population parameters
Difference between parametric and non-
parametric
PARAMETRIC NON-PARAMETRIC

Test statistics is based on the Test statistic is arbitrary

distribution

Parametric tests are applicable only for It is applied both variable and
variable attributes

Parametric test is powerful, if it exist It is not so powerful like parametric test

 Measurements
Definition: refers to the process of assigning
meaningful numbers (or labels) to individual
persons based on the degree to which they
posses a particular characteristic.
 Levels of Measurement
 Nominal scale: consists of a finite set of possible
values or categories that have unordered scales.
No natural order of categories
 Examples:
 Cause of death
 Gender
 Blood type
 Civil status
 Levels of Measurement
 Ordinal scale: consists of a finite set of
possible values of categories which have
ordered scales
 Example:
 Pain(mild, moderate, severe)
 Attitude towards abortion
 Cancer stages
 Examination marks
 Levels of Measurement
 Interval scale: generally measured on a
continuum and differences between any
two numbers on the scale that are of known
size. No true zero point.
 Examples:
 Temperature in Celsius and Fahrenheit
 Levels of Measurement
 Ratio scale: generally measured on a
continuum and the ratio scale has a
meaningful zero point
Examples:
 Height
 Mass
 Volumes
Levels of Measurement

 Nominal- categories only

 Ordinal- categories with some order
 Interval- differences but no natural
starting point
 Ratio- differences and a natural point
starting
 Variables

 Definition: refer to the characteristic of

persons or objects which can take on
different values or labels for different
persons or objects under consideration.
Example:
 College major
 Faculty rank
 Variables
Types:
1. Response variable: affected by the value of some other
variables
2. Explanatory variable: affects the value of the response
variable

Classification of Variables
1. Qualitative: is one whose categories are simply used as
labels to distinguish one group from the other
2. Quantitative: can be measured and ordered according to
quantity
Qualitative Variables

 Many characteristics are not capable of being

measured. Some of them can be ordered or
ranked.
 Examples:
1.Classification of people int socio-economic
groups
2.Social classes based on income, education and
etc.
Quantitative Variables

 It can be measured in the usual sense.

 Examples:
1.Heights of adult males
2.Weights of preschool children
3.The ages of patients seen in dental
clinic
 Variables
 Types of Quantitative variable

1. Discrete: refers to each element of set of possible

values that is either finite or countably infinite that can
appear only as whole numbers

2. Continuous: refers to each element of a set of possible

values including all values in an interval of the real line that
can be expressed with fractions or digits after a
decimal point
Discrete Variable

 Characterized by gaps or interruptions in the values

that it can assume.

 Examples:
1. The number of daily admissions to a general hospital
2. The number of decayed, missing or filled teeth per
child in an elem school
Continuous Variable

 Can assume any value within a specified relevant

interval of values assumed by the variable.

 Example;
1. Height
2. Weight
3. Skull circumference
 Data

 The raw material of Statistics is data.

 data= figures
 Figures result from the process of counting or taking a measurement.

 Examples:
1. When a hospital administrator counts the number of patients (counting)
2. When a nurse weighs a patient (measurement)
Classification of Data

 Internal Data refers to those data that relates

to the activities within the organization
collecting the data

 External Data refers to the data that relates to

the activities outside the organization
collecting the data.
Statistical vs Nonstatistical Data

 1. Statistical Data are those published data

of the government institutions, companies,
and associations which involves figures,
tables, graphs

 2. Nonstatistical Data are those information

which do not involve figure, tables and graphs
 Sources of Data
 1.Primary source: refers to the data that comes from the
original sources and is collected especially for the task at
hand.
Advantages:
 Precise retrieval of information
 Monitor and record the extraneous influences on the
data
Disadvantage
 Very expensive
 Time consuming
 Sources of Data
 Secondary source: refers to the data collected by others for another
purpose (paper-based or electronic sources)
Advantages:
 Can be obtained easily
 Good source of research on past events
 Appropriate to find data on distant places
Disadvantage
 Units of measurement are different since different time periods may
be involved
 Difficult to assess the accuracy of the data
 Data is usually out of date
 Methods of Data Collection
 Mailed questionnaire: most popular
Advantages:
 Less expensive
 Less time needed
 No prior arrangements are needed
 Respondent can answer at their convenient time
 Respondent can hide their true personality
 No dangers of interviewer bias
 Wide geographic coverage
 Methods of Data Collection
Disadvantages:
 Less percentage of returns are expected
 Longer time to wait for the responses of the respondents
 Produce more blanks, no ideas, or no comments
 Answers cannot be verified
 No means of knowing the respondents
 Assumes no literacy problems
 Methods of Data Collection
 Interview
Classification
 Structured
 Semi-structured
 Unstructured
Advantages:
 Higher percentage of returns
 Complete and immediate
 Minimal incidence of blanks, don’t know, or no comment
 Unclear questions could be corrected for better
 Answer can be verified Identity of the respondent can be ascertained
 Possible in-depth questions
 Disadvantages:
 Very expensive
 Time consuming
 More trained personnel
 Respondent in under pressure to answer at
once
 Respondent is left no choice regarding his
personality
 Respondent bias
 Geographical limitations
 Methods of Data Collection
 Observation Classification:
 Direct observation
 Indirect observation
Advantages:
 Most appropriate for data on attitudes and behavior
 Reduce the potential bias caused by interview method
Disadvantages
 Data on awareness beliefs, feelings, and preferences
cannot be observed
 Behavior patterns are rare and unpredictable
 Methods of Data Collection
 Telephone Interview
Advantages:
 Relatively less expensive
 Higher response rate
 Target respondents can usually be contacted faster
 Can cover large geographical area
 Help can be given to the respondents
 Results can be available after completing the last interview
Disadvantages:
 Telephone number required
 Reluctance to answer
 Problems with 8 to 5 people
 Straightforward questions needed
 Can be irritating
 Little time to think
THANK YOU!