Statistical Data Analysis | Data Analysis | Statistics Services | Data Collection - Statswork

SHORT NOTES
• Statistical data analysis is a process of performing numerous
statistical functions involving collection of data, interpretation
of data and lastly, validation of the data.
• Statistics stated that the descriptive or summary statistics
are used to summarize/describe the sample data and the
inferential statistics are used to infer conclusions from the
hypotheses framed.
“Statistics is the only science where the experts may come up with
different conclusion with the same data”
Research Planing | Data Collection | Semantic Annotation | Consumer & Retail Analytics | Econometrics Copyright © 2019 Statswork. All rights reserved

STATISTICAL DATA ANALYSIS
• Statistics are the branch of mathematics used to analyse the data that can
describe, summarize and compare.
• Statistical data analysis is a process of performing numerous statistical functions
involving collection of data, interpretation of data and lastly, validation of the data.
• Numerous statistical tools such as SAS, SPSS, STATA, etc., are available
nowadays to analyse the statistical data from simple to complex problems based
on the nature of the study.
Statswork experts develop new tools and new approaches on improving the
marketing for your business and predict future trends.

TYPES OF STATISTICAL DATA ANALYSIS
1
2
Summary or Descriptive statistics
Inferential statistics

SUMMARY OR DESCRIPTIVE STATISTICS
Descriptive statistics are used to summarize data from a sample.
Eg. Mean, Median, Standard deviation, Variance, etc.

INFERENTIAL STATISTICS
Inferential statistics are used to make conclusions from data through the null and
alternative hypotheses that are subject to random variation. Simply, it can be stated
that the descriptive or summary statistics are used to summarize/describe the sample
data and the inferential statistics are used to infer conclusions from the hypotheses
framed.
Experts to develop your approach and coding implementation on improving
the business for future trends.

USES OF STATISTICS
Provides a better understanding from the data and
precise description of a state of art under study. Assist in the appropriate and effective planning of a
statistical analysis in any field of study.
Assist in presenting complex data in a appropriate
tabular and graphical format for easy and clear
knowledge of the sampled data.
Assist in understanding the pattern and trends of
variations in the sampled data.
Helps to make valid inferences, by measuring the
reliability parameters for the sampled data towards
the population.
1
2
3
4
5
Statswork experts has experience in handling dissertation, assignment and
tool developed for your future business with assured 2:1 distinction.

MAJOR ROLE OF STATISTICS
Statistical analysis inmarket
research
BI -Business intelligence
Data analytics in Big data,
Machine Learning and Deep
learning, etc
Financial and economic studies.

DATA MEAN IN STATISTICS
The nature of the data plays a vital role in
the field of statistics.
In statistics, there are various kinds of data are available:
Discrete data and continuous data are grouped as
numerical, Categorical data involving nominal and ordinal
Mostly, every sampled data belong to any one of two
groups: categorical or numerical and are described in the
following table for easy understanding.
01
02
03

DATA CLASSIFICATIONS
Categorical Values/observations that can be
grouped into categories with no natural
ordering and having some sort of ordering.
1.CATEGORIAL DATA 2. NUMERICAL DATA
Numerical Values/observations that can be
measured and these numbers can be placed
in ascending or descending order.
Table shows the gender of the respondents
Figure shows the percentage of gender of the respondents
Table shows the age of the respondents

1.CATEGORIAL DATA CLASSIFICATIONS
These are values/observations with no natural
ordering.
Examples: Gender, eye colour, etc.
Nominal Ordinal
Values or observations put in order or ranked or
containing a rating scale. You can order and
count these variables but it cannot be measured.
Example: Likert scale, etc

2. NUMERICAL DATA CLASSIFICATIONS
Discrete Continuous
Values or observations that can be counted
as separate and distinct. It can take only
particular values.
Examples: number of pens in a box; number
of students in a class, etc.
Values that can be measured are considered as
continuous data. They can be further divided into
two types: Finite and Infinite. And, it can take any
value from minus infinity to plus infinity.
Examples: height, time and temperature.

PMF (Probability Mass Function) and PDF (Probability Density Function)
• In statistical data analysis, continuous data are scattered under continuous distribution function, also called as
te PDF or Probability Density Function.
• The discrete data are scattered under discrete distribution function, also called as PMF or Probability Mass
Function.
• The phrase ‘density’ is used for data in continuous form because density cannot be counted, but can be
measured. Normal distribution, Poisson distribution, Binomial distribution, etc., are most commonly used
distribution in statistical analysis.
• Statistical data analysis are broadly classified into two types: Univariate and Multivariate. To analyse the data
which contains only one variable, the univariate statistical analyses such as t-test, z-test, f test, one way
ANOVA, etc., can be performed.
• If the data contains two or more variables, multivariate techniques such as factor analysis, regression analysis,
discriminant analysis, etc., can be performed depends on the nature of the study.

STATISTICAL
ANALYSIS

• t-TEST
t-test analysis is a statistical model which compares the values
in two different groups to determine when there is enough
difference between the data.

2.ANALYSIS OF VARIANCE
Analysis of Variance (ANOVA) is a method utilised to decide whether
the mean values of dependent variables remain constant when
implemented in different groups which are independent of each other.

Predictive Analytics – Predictive analytics in statistics uses predictive algorithms and ML
techniques to define the probability of future results, behaviour, and patterns based on the
existing data.
Causal Analysis – This type of analysis searches the data for the elementary reason to
understand the causes.
Exploratory Data Analysis (EDA) – EDA is an alternative to inferential statistics, emphases on
detecting general trends and patterns in the data and to track the strange associations. It is
widely used by the data scientist to check the assumptions of the hypotheses, to detect outliers,
to handle missing data, etc.
Mechanistic Analysis – This kind of analysis is not a usual type of statistical analysis. Though, it
is worth stating here because, it is used in the big data analysis in some industries, it has an
important role in this big data era.
3.
4.
5.
6.

SUMMARY
Primary step involves the
identification of nature of the
data to be analysed.
Secondly, explore the association
between data and underlying
population in study.
Build a suitable model to summarize the
data and proceed for further analysis.
Check the validity of the model and take
decisions about the hypotheses.
Explore predictive analysis to run situations that will
guide us for future actions.

Statswork Lab @
Statswork.com
www.statswork.com

PHONE NUMBER
UK : +44-1143520021
INDIA : +91-4448137070
EMAIL ADDRESS
info@statswork.com
GET IN
TOUCH
WITH US

Statistical Data Analysis | Data Analysis | Statistics Services | Data Collection - Statswork

More Related Content

What's hot (20)

Similar to Statistical Data Analysis | Data Analysis | Statistics Services | Data Collection - Statswork (20)

More from Stats Statswork (20)

Recently uploaded (20)

Statistical Data Analysis | Data Analysis | Statistics Services | Data Collection - Statswork