Scribd
Upload
4 views

Biostatistics Week 3

Uploaded by

ibrahimmdyusuf071
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views

Biostatistics Week 3

Uploaded by

ibrahimmdyusuf071
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 24

Measures of Central

Tendency
Lecture by DR S. A Bashir
KASU 2021
week 3
Central Value

 Also known as Average


 Definition:
average is an attempt to find out one single figure to describe
whole of figures….. Clark

the average is sometimes described as a number which is typical of


whole group… Leabo
Objectives of Averaging

 To get a single value representing entire data


 To facilitate comparison between different data
Qualities of average

 Easy to understand
 Should be simple to compute so it can be used widely
 Representativeness of all items
 Cannot be unduly affected by extreme observations
 Be capable of further algebraic computations e.g BODMAS
 Uniqueness:
average should be properly defined so that it must have only one
single value for a given data. Should be irrespective of personal variation
and bias
 Sampling Stability:
the stability of the averages calculated from different sets of data
which are collected randomly should not differ significantly.

# the difference will be less the average would be called more stable
and vice versa
Examples of measures of central
tendency
 Mean or average age of marriage for girls in northern Nigeria
 Mean Birth Weight
 Total fertility Rate
 Average income rate
 Mean poverty rate
 Average household size : average differences from north to south
Common averages for Summary

 Arithmetic Mean
 Meadian
 Mode
 Other measures of location which include:
 Quartiles
 Percentiles
 proportions
The Mean

 Types Of Mean

 Arithmetic Mean
 Weighted Mean
 Geometric Mean
 Harmonic Mean
Arithmetic Mean

 Most popular and widely used


 Provides one summary value of the observations

 Defination:
sum of all values of observation divided by the number of
observations it is denoted by X
Quantitative Data : ∑fm/∑f
Showing HB levels of students in a class (n = 30)

Class interval Mid point of Frequency (f) f(m)


class interval
(m)
8 – 10gm% 9 15 135
11 – 13gm% 12 14 168
14 – 16gm% 15 1 15
∑f = 30 ∑fm = 318
Weighted Mean

 When the relative importance of different items is different then the


mean calculated is the weighted mean
 weight; signifies the relative importance of an item

 the weighted mean is calculated in two steps


Table showing Hb levels for children
in a school
Class No of children Mean Hb Levels (gm
%)
1 54 10.4
2 52 11.2
3 49 10.8
4 48 12.1
5 48 10.7
 The weighted mean is calculated:

 Step 1: sum of (mean HB for each class * number of children in class)

 Step 2 : divide step one by total number of children in school

 & the non-weighted mean ignores the fact that the number of
children in each class is not the same (hence unequal weights)
Geometric Mean

 It is define as the Nth root of the product of N observations

 It is theoretically considered as the best average


 It gives an idea of the average rate of changes occurring between
observations.
Harmonic mean

 Definition
 This is defined as the reciprocal of the arithmetic mean

 Harmonic mean = N/1/x1 + 1/x2 + 1/x3……..


Median

 The median is the value that divides the observations or distributions


into 2 equal parts
 It can also be defined as the central value or a series of observations
when arranged in ascending order

 Example:
 ages of students in a school;
 9, 10, 7, 8, 8, 8, 7, 4, 10, 11, 5, 5, 6, 3, 5, 8, 9, 4
 Arrange in ascending order;
 3, 4, 4, 5, 5, 5, 6, 7, 7, 8, 8, 8, 8, 9, 9, 10, 10, 11
 ½(n+n) for even distribution
Merits of Median

 Extreme values do not affect median significantly


 It is useful in markedly skewed distributions
 Most appropriate average in qualitative data
 Can be calculated graphically
Limitations of Median

 Data must be arranged


 It is a positional average
 The value does not represent the changes in distribution
 It is incapable of algebraic manipulation
 Median is affected by sampling fluctuations
Mode

 Mode is the value of observation which occurs maximum number of


times in the data.
 i.e the observation with the highest frequency.

 Data with two attributes with similar frequency.. The values with more
condense variables is the mode
 With observations with multiple attributes with the same frequency
then the mode is calculated
 Mode = 3 median – 2 mean
Merits of Mode

 It represents he most frequent value


 It is not unduly affected by extreme values
 Can be determined graphically
 Can be determined in open ended distributions
Limitations of Mode

 The value of mode is not unique always, in some cases it may be


bimodal sequence
 Not subject to algebraic manipulation
 Does not represent other attributes of the distribution
 It is not a rigidly defined measure…. There are several methods for
calculating mode
Merits of Average

 Simplest to understand and easy to commute


 Affected by value of every item in the distribution
 It is relatively reliable
 It is calculated hence not related to position or frequency
Limitations of Mean

 Very small values and large values unduly affect the value of
the mean

 It is not always a good measure of central value. In the case of


“U” shaped distributions the mean may not correctly
represent the central value
Thank you

You might also like