Statistics
Module 1, Lecture 2
Introduction to
Descriptive Statistics
Frequency Distribution
Central Tendency
Variability
MaryEllen Tancred, Ph.D.
Module 1 Learning Objectives
In this module, students will be able to:
1. Define basic terms in statistics including independent and dependent variable; nominal,
ordinal, interval and ratio measurements; and discrete and continuous data.
2. Define descriptive statistics.
3. Describe and apply frequency distribution and measures of central tendency.
4. Describe measures of variability.
5. Calculate the mean, variance, and standard deviation of a given data set.
6. Describe and apply bivariate descriptive statistics.
7. Define and describe the use of inferential statistics and give examples of inferential
statistics.
8. Define multivariate analysis.
Introduction: Statistics
and the Clinical Laboratory
• The majority of medical decisions are based on
laboratory data.
• Clinical laboratories spend considerable time and
resources to make certain that the test results
generated are accurate. Concepts in statistics are
utilized in laboratories for this purpose.
• Statistical analyses are used in clinical
laboratories primarily for method evaluation and
quality control.
Introduction: Statistics
and the Clinical Laboratory
• Method Evaluation: before a new test method is
implemented in a clinical laboratory, its performance
must be verified before patient results are reported.
• Quality Control: Once a test method’s performance is
verified as acceptable and is implemented in a clinical
laboratory, quality control measures are necessary to
ensure acceptable performance on a continual basis.
Data from clinical laboratories must be summarized in
order to monitor performance. Performance is
monitored for the most part with the use of descriptive
statistics.
Descriptive Statistics
Descriptive Statistics: summarize, organize, and characterize
data.
Common examples include
o Frequency Distributions
o Descriptions of center (central tendency)
o Descriptions of spread (dispersion)
o Descriptions of shape (distribution)
These examples can be displayed graphically allowing the
patterns to be described.
Descriptive Statistics-
Frequency Distribution
• A frequency distribution is a simple method
to describe data.
• This method organizes data according to the
frequency of occurrence.
• Frequency distributions can be illustrated in
different formats such as tables and
histograms.
Descriptive Statistics-
Frequency Distribution
Table Illustrating Frequency Distribution of BUN
results of normal patients assayed:
Range of Patient BUN Results Frequency of Results
(number of patients)
3 – 6 mg/dL 5
7 – 10 mg/dL 10
11 - 14 mg/dL 18
15 – 18 mg/dL 10
19 – 22 mg/dL 5
Descriptive Statistics-
Frequency Distribution
Table Illustrating Frequency Distribution of BUN
results of normal patients assayed:
Range of Patient BUN Results Frequency of Results
(number of patients)
3 – 6 mg/dL 5
7 – 10 mg/dL 10
11 - 14 mg/dL 18
15 – 18 mg/dL 10
19 – 22 mg/dL 5
Descriptive Statistics-
Frequency Distribution
Range of Patient BUN Results
Descriptive Statistics-
Frequency Distribution
Range of Patient BUN Results
Descriptive Statistics
Frequency Distribution
Descriptive Statistics
Frequency Distribution
Descriptive Statistics
Frequency Distribution
Descriptive Statistics
Frequency Distribution
Descriptive Statistics-Measures of
Center (Central Tendency)
Data can be further described and
summarized using measures of central
tendency.
Descriptive Statistics-Measures
of Center (Central Tendency)
Mean, Median,
and Mode are
measures of
Center (Central
Tendency)
Descriptive Statistics-Measures
of Center (Central Tendency)
•Mean (referred to as the average, “x-bar” )
•Median (the middle value)
•Mode (the value that occurs most frequently)
Descriptive Statistics
Commonly Used Stats Abbreviations
It is helpful to review the frequently used symbols and
abbreviations to perform the common calculations used in
descriptive statistics.
Descriptive Statistics
Commonly Used Stats Abbreviations
It is helpful to review the frequently used symbols and
abbreviations to perform the common calculations used in
descriptive statistics.
Descriptive Statistics
Commonly Used Stats Abbreviations
It is helpful to review the frequently used symbols and
abbreviations to perform the common calculations used in
descriptive statistics.
Descriptive Statistics
Commonly Used Stats Abbreviations
It is helpful to review the frequently used symbols and
abbreviations to perform the common calculations used in
descriptive statistics.
Descriptive Statistics
Commonly Used Stats Abbreviations
It is helpful to review the frequently used symbols and
abbreviations to perform the common calculations used in
descriptive statistics.
Descriptive Statistics-Measures
of Center (Central Tendency)
To Determine the Mean
Descriptive Statistics-Measures
of Center (Central Tendency)
To Determine the Mean
Descriptive Statistics-Measures
of Center (Central Tendency)
To Determine the Mean
Descriptive Statistics-Measures of Center
(Central Tendency)
Example: Determine the Symbol/ Meaning
Abbreviation
Mean of the following
BUN (mg/dL) values 12, ΣX Sum/add up (Σ) the data points
11, 16, 14, 13, 13, 15 (X):
using the formula 12+11+16+14+13+13+15 = 94
n total number of data points = 7
X
X
n X data points = 12, 11, 16, 14,
13, 13, 15
Mean = 13.4 mg/dL
Mean (average) value of the
dataset 94/7 = 13.4
Descriptive Statistics-Measures of Center
(Central Tendency)
Example: Determine the Symbol/ Meaning
Abbreviation
Mean of the following
BUN (mg/dL) values 12, ΣX Sum/add up (Σ) the data points
11, 16, 14, 13, 13, 15 (X):
using the formula 12+11+16+14+13+13+15 = 94
n total number of data points = 7
X
X X data points = 12, 11, 16, 14,
n
13, 13, 15
Mean = 13.4 mg/dL
Mean (average) value of the
dataset 94/7 = 13.4
Descriptive Statistics-Measures of Center
(Central Tendency)
Example: Determine the Symbol/ Meaning
Abbreviation
Mean of the following
BUN (mg/dL) values 12, ΣX Sum/add up (Σ) the data points
11, 16, 14, 13, 13, 15 (X):
using the formula 12+11+16+14+13+13+15 = 94
n total number of data points = 7
X
X
n X data points = 12, 11, 16, 14,
13, 13, 15
Mean = 13.4 mg/dL
Mean (average) value of the
dataset 94/7 = 13.4
Descriptive Statistics-Measures of Center
(Central Tendency)
Example: Determine the Symbol/ Meaning
Abbreviation
Mean of the following
BUN (mg/dL) values 12, ΣX Sum/add up (Σ) the data points
11, 16, 14, 13, 13 15 using (X):
the formula 12+11+16+14+13+13+15 = 94
n total number of data points = 7
X
X
n X data points = 12, 11, 16, 14,
13, 13, 15
Mean = 13.4 mg/dL
Mean (average) value of the
dataset 94/7 = 13.4
Descriptive Statistics-Measures of Center
(Central Tendency)
The Median is the middle value. To determine the
median
1. the data is first arranged in rank order from the
least value to the greatest value.
2. The median value is the data point that divides the
dataset in half (50% of the data points will be
above and below the median value).
Descriptive Statistics-Measures of
Center (Central Tendency)
Example: 1. Arrange the BUN data from least value
to most:
Determine the Median of
the following BUN (mg/dL) 11, 12, 13, 13, 14, 15, 16
values 12, 11, 16, 14, 13,
13, 15
In this example, there are 2. Determine the value that divides the
an odd number of data data in half (the middle value, where 50%
points (7 numbers) of the data points are above and below this
value). In this case there is an odd number
of data points, making one of the data
points the median value. The median BUN
value is 13.0 mg/dL.
Descriptive Statistics-Measures of
Center (Central Tendency)
Example: 1. Arrange the BUN data from least value to
most:
Determine the Median of
the following BUN (mg/dL) 11, 12, 13, 13, 14, 15, 16
values 12, 11, 16, 14, 13,
13, 15
In this example, there are
an odd number of data 2. Determine the value that divides the data in
points (7 numbers) half (the middle value, where 50% of the data
points are above and below this value). In this
case there is an odd number of data points,
making one of the data points the median
value. The median BUN value is 13.0 mg/dL.
Descriptive Statistics-Measures of
Center (Central Tendency)
Example: 1. Arrange the BUN data from least value to
most:
Determine the Median of
the following BUN (mg/dL) 11, 12, 13, 13, 14, 15, 16
values 12, 11, 16, 14, 13,
13, 15
In this example, there are
an odd number of data 2. Determine the value that divides the data in
points (7 numbers) half (the middle value, where 50% of the data
points are above and below this value). In this
case there is an odd number of data points,
making one of the data points the median value.
The median BUN value is 13.0 mg/dL.
Descriptive Statistics-Measures of
Center (Central Tendency)
Example: 1. Arrange the BUN data from least value to
most:
Determine the Median of
11, 12, 13, 14, 15, 16
the following BUN (mg/dL)
values 12, 11, 16, 14, 13, 15
In this example, there are
an even number of data
points (6 numbers) 2. In this case, 2 data points are in the
middle of the data set (50% of data points
are above and below these values). The
median is determined by averaging the 2 data
points (13 + 14 divided by 2). The median BUN
value is 13.5 mg/dL.
Descriptive Statistics-Measures of
Center (Central Tendency)
Example: 1. Arrange the BUN data from least value to
most:
Determine the Median of
11, 12, 13, 14, 15, 16
the following BUN (mg/dL)
values 12, 11, 16, 14, 13, 15
In this example, there are
an even number of data
points (6 numbers) 2. In this case, 2 data points are in the
middle of the data set (50% of data points
are above and below these values). The
median is determined by averaging the 2 data
points (13 + 14 divided by 2). The median BUN
value is 13.5 mg/dL.
Descriptive Statistics-Measures of
Center (Central Tendency)
Example: 1. The most frequent value in
Determine the Mode of a dataset is the Mode:
the following BUN
(mg/dL) values 11, 12, 12, 12, 13, 14, 15, 16
11, 12, 12, 12, 13, 14, 15, 2. In this case, the number 12
16 occurs more frequently than
the other numbers.
Therefore, the Mode for this
set of BUN data is 12 mg/dL.
Descriptive Statistics-Measures of
Center (Central Tendency)
Example: 1. The most frequent value in a
dataset is the Mode:
Determine the Mode of
the following BUN 11, 12, 12, 12, 13, 14, 15, 19, 19, 19
(mg/dL) values
2. In this case, there are 2 numbers
11, 12, 12, 12, 13, 14, 15, that occur more frequently than the
19, 19, 19 other numbers in the dataset.
Therefore, there are 2 modes for this
set of BUN data: 12 mg/dL and 19
mg/dL. This is an example of bi-
modal distribution.
Descriptive Statistics-Measures of
Center (Central Tendency)
1. The most frequent value in a
dataset is the Mode:
11, 12, 12, 12, 13, 14, 15, 19, 19, 19
2. In this case, there are 2 numbers
that occur more frequently than the
other numbers in the dataset.
Therefore, there are 2 modes for this
set of BUN data: 12 mg/dL and 19
mg/dL. This is an example of bi-
modal distribution.
Descriptive Statistics-Measures of Shape
and Center (Central Tendency) Summary
Shape:
Normal,
Skewed,
Bi-Modal
Center:
Mean,
Median,
Mode
Descriptive Statistics
Measures of Shape and Center
(Central Tendency) Summary and Notes
Normal Distribution
• Bell shaped, symmetrical
• Mean, Median, and Mode are equal
• Equal lengths of tails
Descriptive Statistics
Measures of Shape and Center
(Central Tendency) Summary and Notes
Skewed Distribution
• Positively skewed: the right tail is
longer than the left tail. The mean is
greater than the median.
Descriptive Statistics
Measures of Shape and Center
(Central Tendency) Summary and Notes
Skewed Distribution
• Negatively skewed: the right tail is
shorter than the left tail. The median
value is greater than the mean.
Descriptive Statistics
Measures of Shape and Center
(Central Tendency) Summary and Notes
Bimodal Distribution
• There are 2 modes, and 2 normal
distributions
Descriptive Statistics-Variability
Once the center of data has been described,
determining how the data is dispersed
(spread) provides additional useful
information.
Descriptive Statistics-Variability
(Spread, Dispersion)
• The variability (spread, dispersion) indicates the
relationship of the data points to each other and
relative to the mean.
• Calculations of Variability include
o Range
o Standard Deviation (SD)
o Variance
Descriptive Statistics-Measures of
Variability (Spread, Dispersion)
Measures of
Variability
• Range
• SD
• Variance
Descriptive Statistics-Measures
of Variability
Example: The range is the difference
Determine the Range of between the highest and
the following BUN lowest values
(mg/dL) values
11, 12, 12, 12, 13, 14, 15, 19
11, 12, 12, 12, 13, 14, 15,
19 The Range is 19-11 = 8.
Descriptive Statistics-Variability
SD Calculation and Abbreviations
The formula for SD (s, σ)
Descriptive Statistics
Measures of Variability
Determine the Standard Data used to Calculate SD
Deviation (s, SD, σ) of the
following BUN (mg/dL)
X
values.
11 11 – 12.7 = - 1.7 2.89
11, 12, 12, 12, 13, 14, 15,
12 12 – 12.7 = - 0.7 0.49
n = 7, ΣX = 89 12 12 – 12.7 = - 0.7 0.49
12 12 – 12.7 = - 0.7 0.49
Mean = 12.7 13 13 – 12.7 = 0.3 .09
14 14 – 12.7 = 1.3 1.69
SD Calculation
15 15 – 12.7 = 2.3 5.29
Sum = 89 Sum = 11.43
SD = √11.43/6 = 1.38
Descriptive Statistics
Measures of Variability
Determine the Standard Data used to Calculate SD
Deviation (s, SD, σ) of the
following BUN (mg/dL)
X
values.
11 11 – 12.7 = - 1.7 2.89
11, 12, 12, 12, 13, 14, 15,
12 12 – 12.7 = - 0.7 0.49
n = 7, ΣX = 89 12 12 – 12.7 = - 0.7 0.49
12 12 – 12.7 = - 0.7 0.49
Mean = 12.7 13 13 – 12.7 = 0.3 .09
14 14 – 12.7 = 1.3 1.69
SD Calculation
15 15 – 12.7 = 2.3 5.29
Sum = 89 Sum = 11.43
SD = √11.43/6 = 1.38
Descriptive Statistics
Measures of Variability
Determine the Standard Data used to Calculate SD
Deviation (s, SD, σ) of the
following BUN (mg/dL)
X
values.
11 11 – 12.7 = - 1.7 2.89
11, 12, 12, 12, 13, 14, 15,
12 12 – 12.7 = - 0.7 0.49
n = 7, ΣX = 89 12 12 – 12.7 = - 0.7 0.49
12 12 – 12.7 = - 0.7 0.49
Mean = 12.7 13 13 – 12.7 = 0.3 .09
14 14 – 12.7 = 1.3 1.69
SD Calculation
15 15 – 12.7 = 2.3 5.29
Sum = 89 Sum = 11.43
SD = √11.43/6 = 1.38
Descriptive Statistics
Measures of Variability
Determine the Standard Data used to Calculate SD
Deviation (s, SD, σ) of the
following BUN (mg/dL)
X
values.
11 11 – 12.7 = - 1.7 2.89
11, 12, 12, 12, 13, 14, 15,
12 12 – 12.7 = - 0.7 0.49
n = 7, ΣX = 89 12 12 – 12.7 = - 0.7 0.49
12 12 – 12.7 = - 0.7 0.49
Mean = 12.7 13 13 – 12.7 = 0.3 .09
14 14 – 12.7 = 1.3 1.69
SD Calculation
15 15 – 12.7 = 2.3 5.29
Sum = 89 Sum = 11.43
SD = √11.43/6 = 1.38
Descriptive Statistics
Measures of Variability
Determine the Standard Data used to Calculate SD
Deviation (s, SD, σ) of the
following BUN (mg/dL)
X
values.
11 11 – 12.7 = - 1.7 2.89
11, 12, 12, 12, 13, 14, 15,
12 12 – 12.7 = - 0.7 0.49
n = 7, ΣX = 89 12 12 – 12.7 = - 0.7 0.49
12 12 – 12.7 = - 0.7 0.49
Mean = 12.7 13 13 – 12.7 = 0.3 .09
14 14 – 12.7 = 1.3 1.69
SD Calculation
15 15 – 12.7 = 2.3 5.29
Sum = 89 Sum = 11.43
SD = √11.43/6 = 1.38
Descriptive Statistics
Measures of Variability
Determine the Standard Data used to Calculate SD
Deviation (s, SD, σ) of the
following BUN (mg/dL)
X
values.
11 11 – 12.7 = - 1.7 2.89
11, 12, 12, 12, 13, 14, 15,
12 12 – 12.7 = - 0.7 0.49
n = 7, ΣX = 89 12 12 – 12.7 = - 0.7 0.49
12 12 – 12.7 = - 0.7 0.49
Mean = 12.7 13 13 – 12.7 = 0.3 .09
14 14 – 12.7 = 1.3 1.69
SD Calculation
15 15 – 12.7 = 2.3 5.29
Sum = 89 Sum = 11.43
SD = √11.43/6 = 1.38
Descriptive Statistics
Measures of Variability
Taking the data
from the previous
slide, the Standard
Deviation of the
following BUN
(mg/dL) values (11,
12, 12, 12, 13, 14,
15) is 1.38.
Mean = (12.7) + 1 34% 34%
SD (1.38) can be 11.3 12.7 14.1
displayed 1 SD from the mean is 12.7 + 1.38 giving a range of 11.3 to 14.1.
graphically.
This means that 68% of the values will fall between 11.3 to 14.1
(within 1 SD). This shows a normal distribution where half of the
values are greater than the mean, and half the values are below the
mean.
Descriptive Statistics
Measures of Variability
Taking the data
from the previous
slide, the Standard
Deviation of the
following BUN
(mg/dL) values (11,
12, 12, 12, 13, 14,
15) is 1.38.
Mean = (12.7) + 2 313.5% 34% 34% 13.5%
SD (2 x 1.38) can 9.94 11.3 12.7 14.1 15.5
be displayed 2 SD from the mean is 12.7 + 2.76 giving a range of 9.94 to 15.5.
graphically.
This means that 95% of the values will fall between 9.94 and 15.5
(within 2 SD).
Descriptive Statistics
Measures of Variability
Taking the same
data from the
previous slides, the
Standard
Deviation of the
following BUN
(mg/dL) values (11,
12, 12, 12, 13, 14,
15) is 1.38.
34% 34%
13.5%
Mean = (12.7) + 3
313.5%
2.5% 2.5%
8.56 9.94 11.3 12.7 14.1 15.5 16.8
SD (3 x 1.38) can 3 SD from the mean is 12.7 + 4.14 giving a range of 8.56 to 16.8.
be displayed
This means that 99.7% of the values will fall between 8.56 and 16.8
(within 3 SD).
graphically.
Descriptive Statistics-
Measures of Variability
The Variance: the variance is calculated by
squaring the standard deviation. It is also calculated
by dividing the sum of squares by (n-1).