Scribd
Upload
25 views

Lecture4B Slides

Uploaded by

Ntando Mandla Makwela
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
25 views

Lecture4B Slides

Uploaded by

Ntando Mandla Makwela
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/ 8

Average Deviation

• The average deviation from the mean is


calculated as the average difference between
each observation and the mean of the
variable.
• The average deviation is problematic because
the positive and negative deviations cancel
each other out and average to zero; therefore
the average deviation does not provide useful
information
Variance

• The issue of the average deviation averaging


to zero can be solved by using either the
absolute deviation from the mean or the
squared deviation from the mean.
• Variance is calculated as the average of the
squared deviations about the mean for a set
of observations for both raw (ungrouped)
and frequency (grouped) data.
• The variance of a variable is one of the most
commonly used measures of dispersion and
it provides numerical information about the
amount of variation within the values of a
variable.
• The larger the variance, the more spread out
the data is; a lower variance indicates a lower
range of values.
Standard Deviation
• The standard deviation of a variable is the
square root of the variance of the variable.
• The standard deviation measures how tightly
a set of values is clustered around the mean.
• If a set of numbers is close to the average
value then a low standard deviation is
expected. A lower standard deviation would
likely be an indicator of stability. In contrast,
if the set of numbers is spread across a
greater range it may present a high standard
deviation.
• As with the variance, the standard deviation
can be calculated for both raw (ungrouped)
and frequency (grouped) data.
• APPLICATION
• The variance and the standard deviation can
be affected by outliers i.e. a few very large or
very small observations (the same applies to
the mean).
• Due to this, if the distribution is skewed it is
preferable to use a measure of variation that
is not affected by outliers e.g. the
interquartile range
Exercise 1
The output below was generated for two
variables: attention control and age

Attention
Control Age
N Valid 200 200
Missing 0 0
Mean 12.55 27.23
Median 13.00 25.50
Std. Deviation 2.401 4.832
Minimum 6 20
Maximum 19 37
Percentiles 25 11.00 23.00
75 14.00 31.00
• What is the range for attention control in the sample?
• What is the range for age in the sample?
• What is the fiftieth percentile for attention control in
the sample?
• What is the lower quartile for attention control in the
sample?
• What is the interquartile range for age in the sample?
• Based on the data above, would the mean be a
suitable measure of central tendency to use as a basis
to calculate variation for attention control in the
sample? Please justify your answer.
• Based on the data above, would the mean be a
suitable measure of central tendency to use as a basis
to calculate variation for age in the sample? Please
justify your answer.

You might also like