Descriptive Analytics

Dr. Nikhil Ghag

SIOM Nashik
What is Descriptive Analytics

Descriptive analytics is about finding “what has happened” by

summarizing the data using innovative methods and analyzing the past
data using simple queries.

Example – Walmart, Cholera outbreak in London John Snow

Descriptive analytics is the starting point of analytics-based solution to

problems. It helps to understand the data and provide directions for
predictive and prescriptive analytics. Business Intelligence (BI), which
largely involves creating reports and business dashboard that led to John Snow’s spot map of cholera outbreak in London, 1854.

actionable insights, is essentially a descriptive analytics exercise.

 Structured and Unstructured Data

• Structured data means that the data is described

in a matrix form with labelled rows and
columns.
• Machine generated data such as images
generated by satellite, magnetic resonance
imaging (MRI), electrocardiogram (ECG) and
thermography are few examples of unstructured
data.
• The importance of unstructured data in decision
making has increased

https://en.wikipedia.org/wiki/Clickstream
http://hortonworks.com/hadoop-tutorial/how-to-visualize-website-clickstream-data/
http://searchcrm.techtarget.com/definition/clickstream-analysis
https://www.qubole.com/blog/big-data/clickstream-data-analysis/
Cross-sectional, Time Series, and Panel Data

1. Cross-Sectional Data: A data collected on many variables of interest at the same time or duration
of time is called cross-sectional data. For example, consider data on movies such as budget, box-
office collection, actors, directors, genre of the movie during year 2017.

2. Time Series Data: A data collected for a single variable such as demand for smartphones
collected over several time intervals (weekly, monthly, etc.) is called a time series data.

3. Panel Data: Data collected on several variables (multiple dimensions) over several time intervals
is called panel data (also known as longitudinal data). Example of a panel data is data collected on
variables such as gross domestic product (GDP), Gini index, and unemployment rate for several
countries over several years.
TYPES OF DATA MEASUREMENT SCALES
Nominal Scale (Qualitative Data)

Nominal scale refers to variables that are basically names (qualitative data) and also known as categorical variables. For example,
variables such as marital status (single, married, divorced) and industry type (manufacturing, healthcare, banking and finance) fall
under nominal scale

Ordinal Scale

Ordinal scale is a variable in which the value of the data is captured from an ordered set, which is recorded in the order of magnitude.
For example, in many survey data, Likert scale is used.

Interval Scale

Interval scale corresponds to a variable in which the value is chosen from an interval set. Variable such as temperature measured in
centigrade (°C) or intelligence quotient (IQ) score are examples of interval scale.

Ratio Scale

Any variable for which the ratios can be computed and are meaningful is called ratio scale
POPULATION AND SAMPLE

• Population (also known as universal set) is the set of all possible data for a given
context whereas sample is the subset taken from a population

• In many analytical problems, we make inference about the population based on the
sample data. There are many challenges in sampling (process of selecting an
observation from the population).

• An incorrect sample may result in bias and incorrect inference about the population.
 MEASURES OF CENTRAL TENDENCY
Mean (or Average) Value

• Mean is the arithmetical average value of the data and is one of the most frequently used measures of central tendency. Associated with the mean is a
phenomenon often called “wisdom of crowd”, according to which the collective wisdom of people is better than any individual person’s knowledge.

• Making decisions solely based on mean value is not advisable. In capital asset procurement such as procurement of fighter aircraft and weapons, defense
services across the world use mean time between failures (MTBF) as one of the measures of system reliability (performance).

Median (or Mid) Value

• Median is the value that divides the data into two equal parts, that is, the proportion of observations below median and above median will be 50%.

Mode

• Mode is the most frequently occurring value in the data set

PERCENTILE, DECILE, AND QUARTILE

• Decile corresponds to special values of percentile that divide the data into 10 equal parts. First decile contains first 10% of the data and second decile
contains first 20% of the data and so on.

• Quartile divides the data into 4 equal parts. The first quartile (Q1) contains first 25% of the data, Q2 contains 50% of the data and is also the median
Problem

Time between failures (in hours) of a wire cutter used in a cookie manufacturing oven is given in Table
2.4. The function of the wire-cut is to cut the dough into cookies of desired size.
(a) Calculate the mean, median, and mode of time between failures of wire-cuts.
(b) The company would like to know by what time 10% (ten percentile or P10) and 90% (ninety percentile
or P90) of the wire-cuts will fail?
(c) Calculate the values of P25 and P75.
Solution
MEASURES OF VARIATION

1. Range - Range is the difference between maximum and minimum value of the data. It captures the data spread. In

the data in Table 2.4, the range = 102 – 2 = 100.

2. Inter-Quartile Distance (IQD) - Inter-quartile distance (IQD), also called inter-quartile range (IQR), is a measure of

the distance between Quartile 1 (Q1) and Quartile 3 (Q3).

3. Variance - Variance is a measure of variability in the data from the mean value. Variance for population, s 2, is

calculated using

4. Standard Deviation
MEASURES OF SHAPE - SKEWNESS AND KURTOSIS

• Skewness is a measure of symmetry or lack of symmetry. A data set is symmetrical when the proportion of data
at equal distance (measured in terms of standard deviation) from mean (or median) is equal

• Pearson’s moment coefficient of skewness

• Kurtosis
 DATA VISUALIZATION

Histogram

Histogram is the visual representation of the data which can be used to assess the probability distribution
(frequency distribution) of the data.

Histogram is very useful since it assists data scientist to identify the following:

1. The shape of the distribution and to assess the probability distribution of the data.

2. Measures of central tendency such as median and mode.

3. Measures of variability such as spread.

4. Measure of shape such as skewness.

The cumulative histograms are called Ogive curves

DATA VISUALIZATION

Bar Chart

Bar chart is a frequency chart for qualitative variable (or

categorical variable). Histograms cannot be used when the
variable is qualitative.

Pie Chart

Pie chart is mainly used for categorical data and is a circular

chart that displays the proportion of each category in the data set.
 DATA VISUALIZATION
Scatter Plot

Scatter plot is a plot of two variables that will assist data scientists to
understand if there is any relationship between two variables. The relationship
could be linear or non-linear

Box Plot (or Box and Whisker Plot)

Box plot (aka Box and Whisker plot) is a graphical representation of

numerical data that can be used to

understand the variability of the data and the existence of outliers. Box plot is
designed by identifying the following descriptive statistics:

1. Lower quartile (1st Quartile), median and upper quartile (3rd Quartile).

2. Lowest and highest value.

3. Inter-quartile range (IQR).

Population and Sampling

The process of identifying a subset from a population of elements (aka observations or cases) is called
sampling process or simply sampling

Identification of target population that is important for a given problem under study.

Decide the sampling frame.

Determine the sample size

Sampling method