BL 234

BIOSTATISTICS I

Lecture I

1
 Definition

 Statistics refers to a range of techniques and

procedures for ANALYZING,
INTERPRETING and ORGANIZING data;
and MAKING DECISIONS on the basis of
data.
 Statistics refers to the scientific study of
numerical data based on natural phenomena.

2
 Definition

 Scientific study: Statistics must meet the

commonly accepted criteria of validity of
scientific evidence.
 We must always be objective in presentation
and evaluation of data and adhere to the
general ethical code of scientific method-
ology, or we may find that the old saying that
"figures never lie, only statisticians do"
applies to us. 3
 Definition

 Numerical: Measurements (length, width,

height), or counts (number birds, teeth, trees,
animals etc).
 Natural phenomena: Things that take place
outside the control of human beings, but also
those evoked by scientists and partly under
their control, as in experiments.

4
 Definition

 “Statistic(s)" is also used in another, though

related, way. It can be the plural of the noun
statistic,
 Statistic(s) refers to anyone of many
computed or estimated statistical quantities,
such as the mean, the standard deviation, or
the correlation coefficient.

5
 Definition

 Biostatistics is the application of Statistics

to solve biological problems.
 The science is sometimes also known as
Biometry or Biological statistics.

6
 Scope of Statistics

I. Experimental design, planning, and

collection of data (lab and field)
II. Descriptive statistics = Description,
Classification, and presentation of data
III. Inferential statistics = Analysis and
interpretation of data through Hypothesis
testing. Making decisions.

7
 Variables
 In Biostatistics measurements or counts of some
attribute (quality or quantity) of interest to the
Biologist are taken
 A variable is the entity (or characteristic) that is
being measured.
 E.g: height, colour, growth rate, blood pressure,
lengths, areas, volumes. weights, angles,
concentrations, rates, number of animal, trees etc.
 Entity is something that exists apart from other
things, having its own independent existence.
 Natural variation: in biological material,
measurements differ (vary) between specimens. 8
 Data and Variables
 Data refers to the actual measurements or
observation taken of the variable under study
(singular: data or datum). Qualitative vs
Quantitative data.
 Datum is a single measurement or observation
 Types of Variables:
 1) Numerical variable
(i) Discrete or Discontinuous variables
(ii) Continuous variables
 2) Categorical variable 9
 Data and Variables
Data sources:
 a) Regularly kept records are records
 b) Surveys are detailed studies aimed at collecting data
for answering a particular question.
 c) Experiments
 d) External sources are existing published reports,
databases, or scientific literature
Sometime data is mixed with the word “information”
 Information is a collection of facts or data,
which have been processed, analysed and
communicated. 10
 Data and Variables

 1) Numeric Variables-Numeric variables have

value, which describes a measurable quantity
or number, indicating “how many”, “how
much” or “how often”.
 a) Continuous variables, are the variable
which have an infinite number of values
between any two fixed points. E.g. between
two length 1.5 and 1.6 cm there are an infinite
number of lengths that could be measured.
11
 Data and Variables
 b) Discontinuous (meristic or discrete) variables
are variables that have only certain fixed
numerical values, with no intermediate values
possible in between.e.g. No. of teeth, trees, animals
 2) Categorical Variables are qualitative variables
with values, which describe “quality” or
“characteristic” of a unit of data, such as “what
type” or “which category”. Colour, sex (male,
female), marital status (married, single, widowed).
12
 Data and Variables
 Further, categorical variables may be described
as:-
 A) Nominal-for which observations can assume
a value that cannot be organized in a logical
sequence (e.g., sex)
 B) Ordinal- in which observations can assume a
value that can be logically ordered or ranked.
e.g., juvenile, subadult, adult; strongly agree,
agree, disagree, strongly disagree).
13
 OUTLIERS

 Occasionally, a set of data will have one or more

observations that are so different, relative to the other
data in the sample, that we doubt they should be part
of the sample. Eg., 3.87, 3.90, 39.8, 3.94, 3.96,
3.99,3.99, 4.00, 4.03, 4.04, 4.05, 4.06, 4.09 kilograms
 Outliers or discordant data are data in striking
disagreement with nearly all the other data in a
sample and the occurrence of such observations
generally calls for closer examination.
14
 Population and Sample

 A Statistical Population: Is an entire collection of

measurements of a variable under study.(Or: all
subjects possessing a common characteristic that is
being studied)
 A Statistical Population: is the totality of individual
observations about which inferences are to be made.
 It is often different from the Biological (Ecological)
Population, e.g. we collect data on female Insects, or
measure height of a specimen over time.
15
 Population and Sample

 In most cases it is impossible to obtain data

for the whole population. Why?---- ,---- , ---
--.
 Hypothetical population: In many cases
the population is imaginary.
 That is why often we take measurements
(estimate) from a sample of the population.

16
 Population and Sample

 A sample is a subset of the population.

 It is a relatively small number of observations
from the population being investigated.
 Statistics allows us to draw conclusions about
a population based on data obtained from a
sample
 Sampling units are individuals in the ordinary
biological sense from which sample for a study
will be drawn. 17
Population and Sample

18
 Example

A biologist took  The observation (data) is

132mm.
measurement of the
 Variable is wing length.
wing length of 25
 Sampling unit: a starling
starlings from a from the communal roost
communal roost. One  Sample: the 25 starlings
starling had a wing that were captured
length of 132mm.  Statistical population: all
starlings in the roost …
In this example:  Biological population: all
starlings.
19
 Parameters and Statistics
 In statistics the biologist calculates or estimates quantities
(e.g. mean) to characterize the sample or population.
 A Parameter is the entity which describes the population
(i.e. it is a characteristic of the population). Eg Mean
 A Statistic(s) is a characteristic or measure obtained from
the sample. (Caution: other meanings of Statistics)
 Statistic(s) refers to anyone of many computed or
estimated statistical quantities, such as the mean, the
standard deviation, or the correlation coefficient.
 Statistic(s) Is an estimate of a population parameter.
20
Parameters and Statistics

21
 Parameters and Statistics

 Convention: symbols for parameters are

in Greek letters, for statistics in Roman
letters (e.g.  and s).

22
 Classification of Data/ Types of
Measurement Scale

Biological data (i.e  1. Data on a RATIO

measurements or scale
observations of the  2. Data on an
attribute of interest INTERVAL scale
to the biologist)  3. Data on an
can be classified ORDINAL scale
into four main  4. Data on a
types NOMINAL scale

23
 Ratio Scale

 Most biological measurements result in

data on a Ratio Scale.
Characteristics
Constant size interval between adjacent
units* (Very important)
True zero (with a physical significance)
Examples: length, number of items, weight,
volume, rates, length of time.
24
 Interval Scale
Characteristics
Constant size interval between adjacent
units, but
No true zero
Examples: Temperature scales (oC and oF).
Note: K is on a ratio scale (why?);
Circular scales (time of day, compass pts)

25
 Ordinal Scale
 Some observations have no numerical differences. They
show relative differences instead of quantitative
differences.
 Clear ranking of the observations
 Order of the values is important and significant, and not
the intervals between each one.
Characteristics:
They are ranked (i.e. they show ORDER)
Examples: height (taller, shorter), environmental disturbance
(more disturbed, less) 26
 Nominal Scale

 These are variables classified by some quality they

are called attributes.
 Data on nominal scale is a discrete classification of
data, in which observations are neither measured nor
ranked (ordered) but are merely classified into various
mutually exclusive categories or attributes, without
any numeric significance. Eg sex (Male/female);
taxonomic category; colour, marital status, exam perf.
 Characteristics:
No numerical value
27
Variables and Measurement scale

28
Variables and Measurement scale

29
 Accuracy and Precision
Significant Figures
Accuracy of a measurement is the
closeness of the measurement to the true
value of the variable being measured
It depends on the instrument used.
Accuracy is expressed in significant
figures.
Example: What is the difference between
73, 73.5, and 73.58? How about 73.5 and
73.50?
30
 Precision

 Precision means the closeness of

repeated measurements of the same
quantity.
 It depends on the skill of the person
making the measurements
 It is possible for a measurement to be
precise without being accurate.

31
Accuracy and Precision

32