Course Title: Computational Statistics

L T P/ SW/F TOTAL
S W CREDIT
Course Code: CSIT139
UNITS
Credit Units: 3 2
3 - - 4
Level: UG

Course Objectives:
After studying the concept of random variables in probability theory, the knowledge of Statistical
distributions as well as the parameters determining them are of paramount significance. It gives
the idea, how the total probability is distributed among the possible values of random variables.
The main objective of the course is to provide the detailed knowledge of the characterization of
all the useful discrete, absolutely continuous and singular distributions. Interrelations of various
Statistical
Models producing different families require further investigations. With the exploration of the
concepts the students will be able to formulate the mathematical/statistical models for real data
set arising in various fields. Also characterize a property which is possessed by a distribution and
that distribution alone.

Prerequisites:
NIL

Student Learning Outcomes:

The student will be able to:
• Formulate solutions using different charts and graphs.
• Distinguish between probability models appropriate to different chance events
• Appraise problems using probability.
• Develop the solution of the problems based on probability space and limit theorems.
• Apply solution of the problems based on Correlation coefficient and Regression
coefficient.

Course Contents / Syllabus:

4 Module I: 20%
Weightage
Concept of statistical population, Attributes and variables (discrete and
Continuous). Different types of scales – nominal, ordinal, ratio and interval.
Primary data – designing a questionnaire and schedule, collection of primary
data, checking their consistency. Secondary data. scrutiny of data for internal
consistency and detection of errors of recording. Presentation of data :
classification, tabulation, diagrammatic & graphical representation of grouped
data. Frequency distributions, cumulative frequency distributions and their
graphical representations, histogram, frequency polygon and ogives. Stem and
 Leaf plot. Box Plot.
5 Module II: 20%
Weightage
Measure of central tendency and dispersion, merits and demerits of these
measures. Moments and factorial moments. Shephard’s correction for
moments. Skewness and Kurtosis and their Measures. Measures based on
quartiles. Bivariate data, Method of least squares for curve fitting.
6 Module III: 30%
Weightage
Correlation and regression, rank Correlation (Spearman’s and Kendall’s
measure), Intra-class correlation, correlation ratio. Partial and Multiple
Correlation & Multiple Regression for Trivariate data.
7 Module IV: 30%
Weightage
consistency. Association of attributes, Independence, Measure of association
for 2x2 table. Chi-square, Karl Pearson’s and Tschuprow’s coefficient of
association. Contingency tables with ordered categories.
8 Pedagogy for Course Delivery:
The class will be taught using theory and practical methods using software in a
separate Lab sessions. In addition to numerical applications, the real life
problems and situations will be assigned to the students and they are
encouraged to get a feasible solution that could deliver meaningful and
acceptable solutions by the end users. The focus will be given to incorporate
probability and related measures to develop a risk model for various
applications.

Pedagogy: The course will be delivered in blended mode.

Assessment Scheme
Theory (%) Lab (%) Total
100 0 100

Theory Assessment (L&T):

Continuous Assessment/Internal Assessment End Term
(40 %) Examination
(60%)
Components Viva CT Self Work Attendance
(Drop down)

Weightage (%) 5 10 20 5 60

Text & References:

1. Goon,Gupta & Dasgupta: Fundamentals of statistics. Vol. I. The world press Private
 Ltd., Calcutta.
2. Yule, G.U. and Kendall, M.G.: An Introduction to the theory of statistics. Charles
Griffin & Company Ltd.
3. C. E. Weatherburn: Mathematical Statistics.