Download as pdf or txt
Download as pdf or txt
You are on page 1of 10

Introduction to Biometrics

Statistics applied to biological problems is called biometry, which is the study of biological
measurement using statistical methods or techniques.

Biometry is linked with the theory, method and application of the mathematical sciences
(Mathematical statistics and computer science) in the studies of agriculture, biology and the
environment.

It originated from the Greek word "bios" meaning life and metron meaning, "measure". Then,
we can say that "Biometry" refers to "measurement of life”. Biometric then clearly refers to the
application of statistical techniques to biological problems.

Biometrics is also the application of statistical methods to the analysis of data derived from the
biological science and medicine.
Data
Data are observations of random variables made on the elements of a population or sample.
Data are the quantities (numbers) or qualities (attributes) measured or observed that are to
be collected and /or analyzed.
The word ‘’data” is plural, “datum” is singular while a collection of data is called a data set
(singular)
Spam num _char format
1 No 21705 html
2 Yes 631 text

Table 1: 2 rows from email50 data matrix

Table 1 displays rows 1 and 2 of a data set, a random sample of a larger data set, containing
emails received in 2012. Each row in the table represents a single email or case. The columns
represent characteristics, called variables, for each of the emails.
An observation can refer to the value of a single variable for a particular subject, but more
commonly refers to the observed values of all variables measured on a particular subject.
Variable
This is defined as characteristics of interest that is either measured or counted e.g. the weight
of an animal.
Types of variables
o Quantitative variables have values that are intrinsically numeric.
-discrete variables have a set of values that are either finite or countably infinite. They
usually take integer values i.e. counts (e.g. number of pregnancies, shoe size, number of
missing teeth)
- continuous variables have a set of possible values including all values in an interval of the
real line. There are no gaps between possible values (e.g. duration of a seizure, body mass
index, height)
o Qualitative variables have values that are intrinsically nonnumeric (categorical).
- nominal variables with no ordering (e. g. gender, marital status)
- ordinal variables with a natural ordering (e. g. level of satisfaction, stage of disease)
Note: In practice, some discrete quantitative variables are treated as continuous if their
distribution can be “well approximated” by a continuous distribution
Note that distinction between interval and ratio scales can be ignored in statistical analyses
but the distinction between nominal and ordinal is very important.
Sources of Data
-Experimental Study: In an experimental study, the researcher deliberately imposes a
treatment on one or more subjects or experimental units (not necessarily human). The
experimenter then measures or observes the subjects’ response to the treatment.
- intervention group is a crucial element of experimental studies
- Observational Study: In an observational study, data are collected on existing system. There
is no intervention. Also the study is:
- less expensive
- easier logistically
- more often ethically practical
- interventions are not often possible
Biological Data
Biological experiments deal with living things and are characterized by the fact that no
individuals are exactly alike. These variations between individuals are the bases of the
variation of new forms of life.
Sources of Biological Data
-Laboratory Experiment.
-Control Experiment.
-Agricultural Farm.
-Research Institutions.
-Existing Records.
Problems associated with Collection of Biological Data
-Some diseases may not be found in the available register despite the fact that they are in
existence.
- Causes of illness are not always recorded.
- The general practitioner’s record, which is a source of medical data, is not kept up to date.
- Variation in climatic condition e.g. rainfall, relative humidity, temperature e.t.c., these may
affect the yield of crop under investigation.
- Diseases and pests make the results of the experiment inadequate for analysis purpose.
Basic Terms in Biometrics
1.Sample: It is a collection of individual observation selected by a specified procedure e.g.
sample of individuals with HIV/AIDS. It is also defined in general form as the representative or
fractional part of a population.
2. Observation: It refers to the count of individual object or measurement taken on the
smallest sampling unit in a sample, such that the observation can be expressed numerically.
3. Population: It is the total number of individual observations about which inferences are
made, existing anywhere in the world or at least within a definitely specified sampling area,
limited in space or time e.g. population of infants in a Local Government Area, population of
lions in western region of Africa. A population may be of finite size or infinite size. It is the
entire collection of all persons/objects concerning a specific area of investigation or study.
4. Variable: (A Biological Variable) defines a property with respect to which individual in the
sample differs in some ascertainable way. If the property does not differ among the sample
case, it cannot be of statistical interest and therefore cannot be referred to as a variable. It can
also be defined as characteristics of interest that is either measured or counted e.g. the
weight of animal can be measured.
Basic Terms in Biometrics (Cont’d)
5. Accuracy: It is the closeness of the measurement of a computed value to its true value. It is a
measure of variation of the estimates from the actual value.
i.e. Accuracy = Actual Value - Estimated Value.

6. Precision: It is the closeness of repeated measurement to its true value. It is the closeness of
an estimate to the expected value. It is the difference between the expected value and the
estimated value.
i.e. Precision = Expected value -Estimated value.

7. Unit of Analysis: This is the unit for which we wish to obtain statistical data. These may be
animals, living matter, human beings etc.
References
• STA 6200 – Introduction to Biostatistics (Lecture notes): Online Resource
• Obisesan, K. O. (2008). STA 351 Biometric Methods. Ibadan Distance Learning Centre Series,
Egbokhare, F. and Adeyemo, O.I. (eds). Distance Learning Centre, University of Ibadan.

You might also like