Transcript Medical statistics

Medical
statistics
The medical statistics is a science
which studies health of the
population depending on social,
economic, cultural, sanitaryhygienic, medical and biologic
factors and has a goal of
establishing tendencies of these
dependences in conditions of activity
of system medical care.
The medical statistics studies:
1.0 Health of the population:
1.1 Demographic processes;
1.2 Morbidity;
1.3 Invalidity ;
1.4 Somatometry and determining of
biochemical constants;
1.5 Mental health and psychometry.
2.0 Conditions of an environment and people’s
life styles:
2.1 Air;
2.2 Water;
2.3 Radiation;
2.4 Nutrition;
2.5 Material welfare;
2.6 Work and training;
2.7 Rest;
2.8 Behavior.
3.0 Medical base:
3.1 Medical establishments ;
3.2 Health manpower ;
3.3 The budget of public health services.
4.0 Activity of system of public health
services:
4.1 Ambulatory and polyclinics;
4.2 Hospitals;
4.3 Drugstores;
4.4 Social - medical activity.
The ways of formation of
statistical integrity :
 1.0 By volume
 2.0 By time
 3.0 By type
The plan and program of medicostatistical research includes:
1.0 Data collection:
1.1 A concentration and preservation of the
data;
1.2 Data transmission.
2.0 Data processing:
2.1 Normalization (standardization) of the data;
2.2 Coding and grouping of the data;
2.3 Registration;
2.4 Calculation of average values, dispersions,
errors;
2.5 Comparison, definition of a difference;
2.6 Correlation, regress, complex estimations.
3.0 The analysis of the data:
3.1 Survey, interpretation analysis;
3.2 The mathematical analysis: disperse,
multifactor, initial, logistic, system, etc.
Registration and accounting medical
documents can serve as programs of medicstatistical research .
Medical-statistical research can be complete
or selective.
 Complete or continuous research covers all
observation units.
 Selective research covers a representative
part of the supervision units, which enables
to evaluate phenomenon in whole.
 Research is of great importance. The
territory strongly influences the results of
research.
 The next question is time and term of the
research. Research can last constantly, that
is to be current, to be carried out
periodically, during certain time or to be onestage.
Constant researches are: studying of natural
movement of the population, periodic —
studying of prevalence of chronic diseases,
one-stage — population census, fixing of a
condition of medical service
After gathering the statistical data is being
processed. This process includes
quantitative and qualitative check, coding
and grouping of these data. Quantitative
check means check of correctness of
statistical record of documents, qualitative
— logic comparison of the data, for
example, age and the diagnosis, age and
employment, growth and weight of a body,
etc. Later there is coding. To each
quantitative or qualitative characteristic of
the phenomenon certain code is given.
 Grouping may be a distribution of the data
according
to
quantitative
or
qualitative
characteristics with the purpose of their analysis
 Variable — is a quantitative or qualitative values of
the concrete characteristic of the phenomenon, for
example, newborn can have length of a body 47,
48, 49, 50, etc
 An absolute value — the number which
characterizes the phenomenon in its absolute
(arithmetic) value.
 A relative value — a number which characterizes
the relation of one value to another and can mean
a part, frequency or a ratio of one number to
another. An absolute value — the number which
characterizes the phenomenon in its absolute
(arithmetic) value.
Table 2.1
A variation line
2900
Number of
newborns, n
1
3000
2
3100
3
3200
3
3300
2
3400
1
Weight of newborns, gr.
The range is the difference between
the highest and lowest values in a
series.
 1.The range is used to measure data
spread.
 2.The range provides no information
concerning the scatter within the series.
 Statistical totality will consist of elements, which
have identical characteristics and represent an
object of the statistical analysis. For example, in
research of demographic problems of the country
by statistical set there will be all of its population;
in research of the stationary aid — hospitalized
patients.
 General statistical totality includes all elements of
research.
 Selective statistical totality contains a part of
general totality, which represents all of its
elements. It should to be selected from general
statistical set to give the same chance to get in
sample to each statistical unit.
 Statistical unit (unit supervision) submitted by an
element of which there is a statistical set (for
example, a person, a family, a newborn, a
pregnant woman, a patient with ischemic heart
disease , etc.
 Statistical attribute is a general property for all
units, which is studied during statistical research,
for example, studying of weight, growth, disease
in newborn etc.
 Statistical index is the statistical value which
makes
it
possible
to
characterize
the
phenomenon.
 Processing the statistical data and the formation of
statistical tables allows understanding the
researched phenomena better.
 Statistical tables are breadboard models,
which will consist of columns and lines on
which crossing statistics data are placed.
 There are simple, group
tables.
and combined
Table 2.2
Number of medical establishments in the
area (the simple table)
Medical establishments
Number of
establishments
District hospitals
75
Areal hospitals
1
Regional hospitals
20
Total
96
Table 2.3 Territorial distribution of medical
establishments in the area (the group table)
Medical
establishments
District
hospitals
Regional
hospitals
Areal
hospitals
Total
North Center
South
Total
20
40
15
75
5
12
3
20
-
1
-
1
25
53
18
96
 The average value characterizes the phenomenon
in one way. It is much more frequently applied in
the statistical analysis — an average term of stay
of the patient in bed, average spaciousness of
hospitals, etc.
 The dispersion from average value shows
variability (fluctuation) of an individual cases in
relation to average value.
 The average error displays the relation of the
statistics received at selective research, to a
parameter of continuous or complete research.
 Parameters of correlation and regress are used for
definition of functional, causal relationships
between two or more characteristics.
 Extensive parameters characterize
structure of statistical totality .
the
 Intensive parameters display frequency of
the phenomenon in the environment,
indicate its level.
Relative and average values and
their reliability
In medical statistics themselves the following
kinds of relative parameters are used:
 Extensive;
 Intensive;
 Relative intensity;
 Visualization ;
 Correlation
 The extensive parameter or a parameter of
distribution characterizes a parts of the
phenomena (structure), that is it shows, what part
from the general number of all diseases (died) is
made with this or that disease which enters into
total.
 The general formula of its subtraction is the
following:
part × 100
common number
 The intensive parameter characterizes
frequency or distribution. It shows, how
frequently the given phenomenon occurs in
the given environment.
 General formula of the calculation is the
following:
phenomenon ×100(1000;10 000;100 000)
environment
 Parameters of relative intensity represent a
numerical ratio of two or several structures
of the same elements of a set, which is
studied.
 The parameter of visualization characterizes
the relation of any of comparable values to
the initial level accepted for 100.
 The parameter of correlation characterizes
the relation between diverse values.
 General formula of the calculation is the
following:
phenomenon ×100(1000;10 000;100 000)
environment (which doesn’t produces this
phenomenon)
Dynamic lines
are the lines, which one consists
from homogeneous of values,
which one characterize change
any one appearances for a
definite span.
Dynamic analysis
 Pure gain - a difference between
following and previous numbers of
dynamic lines.
 Rate of gain - the relation of the pure
gain to previous number increased on
100 %.
 Rate of growth - the
relation of
following and previous numbers of
dynamic lines increased on 100 %.
Average values are parameters of the basic
quality of the phenomena which are studied,
or a unit of measurements of the central
tendency of distribution a variant.
In all researches which concern a state of
health, the great value has comparison of
the phenomenon with the standard as which
the average value acts.
Average simple arithmetic is
determined according to the
model:
X

Ma 
N
Average mixed arithmetic is
determined according to the model:
Xn
Mз 
n
 Mode or dominant – is a variant, which
occurs in a variation line with the greatest
frequency.
 Median - is a variant ,which occupies
median position. In a case if number of the
variant is pair, the median represents
average value of two variant ,which occupy
median position.
Average values
1. Arithmetical mean
(M)
-
2. Moda (Module)
(Mo)
3. Median
(Me)
-
-
is generalized value, which
gives characteristics by one
of
the
number
for
occurrence, that may have
many
an
individual
manifestations
is a value of the feature,
which is founded in totality
most frequently
is a value of the feature,
which occupies medium
position in variation line and
divides it in two symmetrical
parts
The methods of determination of
arithmetical mean
1. Simple arithmetical
mean
M 
V
n
2. Weight arithmetical
mean
M
VP


n
3. Method of moments
dp

M  A
*i
n
is calculated when variants are
met with equal frequency and
quantity of observations (n) is ≤
30
is calculated when variants are
met with different frequency and n
is >30
is calculated when variants are
expressed by great numbers and
quantity of observations is
expressed by hundreds and
thousands of incidents
Properties of arithmetical mean
 1. It occupies an average position in
variation line
 2. It has abstract character
 3. Sum of deflection of all variants from
medium value is equal to 0
Thank you!