0% found this document useful (0 votes)
14 views24 pages

1 - 2 Biostatistics

Uploaded by

Mela Mela
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
14 views24 pages

1 - 2 Biostatistics

Uploaded by

Mela Mela
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

Biostatistics

Prof. Dr. Elizana Petrela


Statistics
• Researchers, in a very wide variety of fields, use statistics to make
sense of the large sets of data they collect in studying a great number
of interesting problems.

• Statistics can be defined as “the science of organizing and analyzing


information,” making that information easier to understand.
• Statistics are used to make sense of often large and unwieldy sets of
data.
• Statistics can be used in any field to answer a very wide variety of
research questions and hypotheses.
Statistics
A set of tools and techniques that is used for

• describing;
• organizing;
• analyzing, data
• interpreting
Statistics

Two large sectors can be identified :

• Descriptive statistics
• Inferential statistics

4
• Descriptive statistics are used to organize and describe the
characteristics of a collection of data. The collection is sometimes
called a data set or just data.
• Inferential statistics are often (but not always) carried out after
descriptive statistics. They are used to make inferences from a smaller
group of data to a larger one.
• An example is using results from one kindergarten classroom to infer,
or generalize, about a population of a whole kindergarten grade.
Descriptive statistics

Its objective is to organize, summarize, present and interpret


(describe) data in an appropriate way to draw conclusions.

It collects information on the population or on a part of it,


summarizes through indices (of position and variability) and
presents through appropriate graphs, the results obtained.

6
Descriptive statistics
• Descriptive statistics organizes and summarizes observations, allowing
an overview of the general characteristics of a series of data.

• Descriptive statistics can take different forms, such as tables, graphs


and numerical summary measures.
Inferential statistics
• It deals with drawing general conclusions about the characteristics of
a population by observing and analyzing only a part of its units, a
sample, usually selected through random sampling.

• Among the tools, which we will see, to achieve this “generalization”


of the characteristics of a sample to the population are
• the point estimate,
• confidence intervals and
• hypothesis tests.
Sample & Population
• A sample is a portion or subset of a larger population. Data from
samples may be used for description only, or to generalize something
about the larger population.
• A population is a full set from which a sample is taken: all the possible
cases of interest.
• Data from a sample can be used to infer properties of a whole
population.
Data
• Data are measures, of quality and/or quantity, of objects
(observations) that are being studied in the particular phenomenon
of interest.
The appropriate use of statistical procedures requires the
understanding of the relationship between data and
numbers.
The characteristics being measured are called variables.
The values of variables are the data characteristics you
wish to investigate.
The values which are assigned to the variables are called
observations.
Different types of data
Data

Qualitative Quantitative

Binary Ordinal Discret Continous


Nominal

12
Data are measured on 4 different
scales
• They are: nominal, ordinal, interval, and ratio.
• When data are measured using the nominal scale, numbers merely represent
which category an observation belongs to.
• When data are measured on the ordinal scale, the numbers represent an
ordering or ranking of the data.
• Nominal and ordinal data are inherently categorical (individuals fall within
categories).
• When data are measured on the interval scale, the numbers represent equal
units from one value to another on the scale.

E. Petrela
Data (cont)
• And when data are measured on the ratio scale, the data have a
meaningful zero value representing the absence of a quantity being
measured.
• Interval and ratio data is quantitative.
• Qualitative data is divided into data with discrete or a finite or
countable number of outcomes or continuous/infinite outcomes.

E. Petrela
Quantitative data
• they are used to collect the bare facts, the numbers.

• These are statistical and structured data, which are used to support
the drawing of general conclusions from the research.

• Quantitative data answer the question "How much"


Qualitative data
• collect information that attempts to describe a topic rather than
measure it: these are impressions, opinions and points of view.
• A qualitative survey is less structured and aims to delve into the topic
in question to gather information about people's motivations,
thoughts and attitudes.
• All this on the one hand provides a deep understanding of the
research questions, but on the other makes it more difficult to
analyze the results.
• Qualitative data answers the question “How”.
In simple words…
• Quantitative data provides the numbers that demonstrate the overall
general points of the research, while

• qualitative data provides the details and insights needed to fully


understand the implications.
Nominal variables

• Values ​enter into unordered categories


• are by class or category,
• are the least precise, and
• are mutually exclusive.
• do not have a measurement scale.
• diagnose,
• blood groups,
• ethnicity,
• and political affiliation can be nominal variables.
Binary variables
• are those variables that assume only two values, such as:

• healthy - sick,
• alive - dead,
• therapy - placebo.
Ordinal variables
• When the order between categories is important, the data is called
ordinal data.
• Many types of medical information can be characterized by more
than two values ​and have a clear direction (e.g., best to worst), but
these data are not measured by a rigorous measurement scale.
• Examples:
• stages of a disease: 1,2,3,4
• NYHA classification: I, II, III, and IV
• nutrition level: underweight, normal, overweight, obese
Discrete variables
• For discrete data, both order and magnitude are important.
• Numbers represent actual measurable quantities rather than mere
symbols.
• They can take on specific values ​– often whole numbers – NOT
intermediate values. They take on a finite or countable amount of
values.

• the number of new cancer cases,


• the number of students in a class,
• the number of births in a woman, etc.
Continuous variables
• are variables that can take on any type of value,
• they take on a non-countable but continuous quantity of values,
• they have a fixed measurement scale,
• Examples:
• height,
• weight,
• blood pressure,
• blood glucose level,
• hemoglobin level, etc.
La raccolta dei dati
• The study is the method we use to obtain information about a
particular characteristic, which is of interest to the researcher. The
revelations can be:
• continuous: when they are recorded as the phenomenon occurs
(marriages, births, deaths, meteorological measurements,
epidemiological, etc.);
• periodic: when censuses are carried out at regular intervals of time
(every 10 years)
• occasional: when there is no periodicity (pre-election surveys,
opinion surveys, damage caused by an earthquake).
Important!!!
• It is necessary to make distinctions between different types of data,
since different techniques are used to analyze them.

You might also like