GBT 441 - BIOSTATISTICS (2024/2025 SESSION)

INTRODUCTION TO STATISTICS AND BIOSTATISTICS

Statistics is a science that involves collecting, organizing, summarizing, analyzing, and presenting numerical data.

Biostatistics is a branch of statistics that focuses on the application of statistical methods and techniques – which

include procedures for collecting data, presenting and summarizing data, and drawing inferences from sample data

to a population – to the biological and life sciences. Biostatistics thus plays fundamental roles in medical research,

public health, clinical trials, epidemiology, agriculture, etc.

COURSE OUTCOMES

The overall goal of this course is to give you the knowledge and skills that you will need to design scientific studies,

critically evaluate statistical claims, perform statistical analyses, and present the results of your own research.

Outcomes related to experimental design

 To understand the role that experimentation, hypothesis testing, and data analysis play in the biological and
life sciences.

 To understand the appropriate design of scientific experiments incorporating treatments, controls, replication,
randomization, experimental units, and blocking.

 To help students become aware of common pitfalls in experimental design including lack of power, poor
controls, confounded effects, and pseudoreplication

Outcomes related to statistical analysis

 To equip students with the background needed to select appropriate methods of statistical analysis commonly
used in biological and life sciences, including parametric and nonparametric tests

 To understand the correct analysis of experimental data and determination of statistical significance of
research results considering the calculated statistics.

 To learn the use of common statistical packages to enter data, graph and analyze data, test hypotheses, and
interpret results from experiments.

Outcomes related to presentation

 To understand how scientific data are summarized graphically and in tables

 To show how statistical results are presented in the scientific literature and to give students experience in
interpreting and evaluating scientific graphs

Some of the key concepts and applications of biostatistics include:

(i) Study Design: Biostatistics helps in the design of studies and experiments to address specific research
questions. It assists in determining sample sizes, defining appropriate study populations, and selecting
appropriate data collection methods.

(ii) Data Collection: Biostatisticians guide the process of data collection, ensuring that data is collected in a
standardized and reliable manner. They help develop data collection instruments, design surveys, and
establish protocols for data collection.

(iii) Descriptive Statistics: Descriptive statistics involve summarizing and presenting data in a meaningful way.
This includes measures of central tendency (e.g., mean, median), measures of variability (e.g., standard
deviation, range), and graphical representations (e.g., histograms, box plots) to describe and visualize data
characteristics.

(iv) Probability: Probability theory forms the foundation of biostatistics. It deals with the likelihood of events
occurring and helps in quantifying uncertainty. Biostatisticians use probability distributions to model random
variables, such as the normal distribution for continuous data or the binomial distribution for categorical data.

(v) Statistical Inference: This involves drawing conclusions or making inferences about a population based on
sample data. It includes estimation and hypothesis testing. Estimation aims to determine population
parameters based on sample statistics, while hypothesis testing involves making decisions or testing
hypotheses about population characteristics.

(vi) Study Analysis: Biostatisticians analyze data using appropriate statistical methods to address research
objectives. They select and apply statistical tests, regression models, survival analysis, and other techniques
to identify relationships, assess treatment effects, examine associations, and explore patterns in the data.

(vii) Clinical Trials: Biostatistics plays a crucial role in the design and analysis of clinical trials, which are
rigorous studies conducted to evaluate the safety and effectiveness of medical interventions. It helps in
determining sample sizes, randomization procedures, blinding methods, and statistical analysis plans for
clinical trials.
(viii) Data Interpretation and Reporting: Biostatisticians assist in interpreting study findings, assessing the
statistical significance of results, and communicating results effectively to researchers, clinicians,
policymakers, and the public. They contribute to scientific publications, research reports, and presentations.

(ix) Statistical Software: Biostatistical analysis is often facilitated by the use of specialized statistical software
packages such as R, SAS, SPSS, or Stata. These software tools provide a wide range of statistical methods
and data manipulation capabilities to assist in data analysis.

GENERAL REQUIREMENTS IN BIOLOGICAL AND LIFE SCIENCE EXPERIMENTATION

(i) Experimental variables

A variable is any factor, trait, or condition that can differ. An experiment usually has three kinds of variables:

independent, dependent, and controlled. The independent (or experimental, predictor) variable is the variable that is

varied or manipulated by the researcher. The dependent (or outcome) variable is the response that is measured. The

controlled variables are conditions which must be kept controlled and constant throughout the experiment so that

they do not interfere with the dependent variable. When the experiment is repeated, the controlled variables must be

exactly the same. One way to think about it is that the dependent variable depends on the change in the independent

variable. For example, in a study to understand how different doses of a feed supplement affect the growth rate of

birds, the independent variable is the dose of supplement, and the dependent variable is the growth rate. An easy way

to think of independent and dependent variables is, while conducting the experiment, the independent variable is always

the one that we change, and the dependent variable is that which changes because of that. Also, we can think of the

independent variable as the cause and the dependent variable as the effect.

(ii) Factor

A factor of an experiment is a controlled independent variable; a variable whose levels are set by the experimenter.

A factor is a general type or category of treatments. Different treatments constitute different levels of a factor. For

example, three different groups of animals are subjected to three different feed supplements. The animals are the

experimental units, the feed supplements, the treatments, where the three types of feed supplements constitute three

levels of the factor 'type of feed supplement'.

(iii) Treatments

In biological experiments, treatment is what (or something) researchers administer to experimental units (factors) to

analyse its effect on the dependent variable. For example a medical doctor can prescribe three different types of

drugs to three different groups of patients respectively to see the effectiveness of each drug. Each of this drug

applied to particular group of patient is called treatment. Also, a farmer can apply various kinds of fertilizer to a corn

field divided into different parts to see which produces the most corn. Each of the fertilizer applied is a treatment.

(iv) Experimental Units

An experimental unit is an item (or physical entity) that receives the treatment. For example, in an experiment where

three different groups of animals are subjected to three different feed supplements. The animals are the experimental

units.

(v) Controls

These are the standards to which comparisons are made in an experiment or scientific study. The control and

experimental groups are usually identical in every way except that the experimental groups are subjected to

treatments being evaluated in the study, while the control groups are not. Inclusion of a control group strengthens

researchers’ ability to draw conclusions from a study as it is only in the presence of a control group that a researcher

can truly determine whether a treatment under investigation has a significant effect on an experimental group. This

helps to reduce the possibility of making an erroneous conclusion. As such, when conducting experiments, it is

crucial to have controls to reduce bias and accurately measure the dependent variables. Controls also makes the

results more reliable.

(vi) Randomization

This is an experimental technique in which individuals, groups of individuals and study participants are randomly

assigned to the treatment (experimental) and control groups based on their probability of being equally assigned.

This technique helps in the elimination of selection bias and help balance known and unknown confounding factors

so that the control group and treatment groups are similar as much as possible. Appropriate sample sizes are also

important.

(vii) Replications
This is the repetition of an experiment or the application of an experimental unit more than once in an experiment.

This helps to reduce variability in experimental results and increase their significance as well as the confidence level

with which a researcher can draw conclusions about an experimental factor. Replicates can be used to assess and

isolate sources of variation in measurements and limit the effect of spurious variation on hypothesis testing and

parameter estimation. If a treatment is truly effective, the averaging effect of replication will reflect its experimental

worth. If it is not effective, then the few members of the experimental population who may have reacted to the

treatment will be negated by the large numbers of subjects who were unaffected by it. Biological replicates are

parallel measurements of biologically distinct samples that capture random biological variation, which may itself be

a subject of study or a noise source. Technical replicates are repeated measurements of the same sample that

represent independent measures of the random noise associated with protocols or equipment.

RESEARCH INVOLVING ANIMAL TESTING: ETHICAL GUIDANCE

In 1959, William Russell and Rex Burch published the principles of 3Rs that guide humane/ethical experimental

technique in research and testing involving animal research. The 3Rs are in the order: replacement, reduction, and

refinement.

(i) Replacement

This involves the substituting conscious living higher animals with insentient alternatives where available. An

animal research and testing experiment should only be approved if no suitable alternative such as computer

simulations or cell culture experiments, exist.

(ii) Reduction

Where sentient animals must be used, they must be reduced such that only the minimum number necessary for

achieving the objectives of the research are used. A smart, well-designed study can still provide a statistically useful

result with a minimum number of animals.

(iii) Refinement
This involves conscious reduction in the severity of inhumane procedures applied to the animals where they must be

used. This includes always choosing the most animal-friendly experimental method, promoting non-invasive

procedures, and treating any pain the animal may be in. Housing and experimental conditions should be constantly

optimized in order to subject laboratory animals to as little pain as possible.