Professional Documents
Culture Documents
Statistics
Statistics
Statistics
PGSTAT-01 / MASTAT-01
Mathematical Analysis
Block 1- Riemann Stieltjes integrals, Fourier series and Functions of bounded variation
Absolutely continuous functions. Riemann Stieltjes integrals. Basic theorems. Definitions, Linear properties,
integration by parts, change of variable in . Riemann Stieltjes integrals, upper and lower integrals, necessary
and sufficient conditions for existence of . Riemann Stieltjes integrals, integral as a function of parameters,
differentiation under the integral sign.
Fourier series, orthogonal system of functions, Fourier series of a function relative to an orthogonal system,
properties of Fourier coefficients, Reusz- Fischar theorem, convergence and representation problems for
Fourier metric series, sufficient conditions for convergence of Fourier series at a particular point.
Functions of bounded variation, total variation, function of bounded variation expressed as the difference of
increasing functions, continuous functions of bounded variation, Absolutely continuous functions.
Metric Spaces, open and closed sets, limit and cluster points, Cauchy Sequences and completeness,
Convergence of sequences, Completeness of R”. Baire’s theorem. Cantor’s ernary set as example of a perfect
set which is now here dense.
Unit 5: Continuity
Continuity and uniform continuity of a functio n from a Metric space to a Metric space. Open and closed
maps, Compact spaces and compact sets with their properties. Continuity and compactness under continuous
maps.
PGSTAT-02 / MASTAT-02
Probability space of a random experiment .probability measures, random variables as a measurable function.
Field induced by a sequence of random variables, decomposition of distribution functions in purely discrete,
absolutely continuous and singular components.
Unit 3: Convergence
Sequences of distribution functions, Helly - Bray theorem, Different types of convergence of sequence of
random variables distribution function of random vectors, Weak and strong law of large numbers, Khinchin.
Borel and Kolmogorav theorems.
Borel-Cantelli lemmas and zero-one law, Characteristic function, Inversion theorem, Continuity theorem,
One dimensional central limit problem: lindeberg- levy, Lyapunov, Lindeberg-Feller theorems.
PGSTAT-03 / MASTAT-03
Statistical Inference
Bhattacharya bound, Chapman Robbins and Kiefer (CRK) bound, maximum likelihood estimation, Zehna
theorem for invariance, Cramer theorem for weak consistence, asymptotic normality, BAN and CAN
estimators, asymptotic efficiency.
Confidence interval and confidence coefficient, shortest length confidence interval, relation between
confidence estimation and hypotheses testing.
Generalized Neyman Pearson lemma, UMP tests for distributions with MLR, LR tests and their properties,
UMPU tests, similar regions, Neyman structure, Invariant tests.
PGSTAT-04 / MASTAT-04
Linear Estimation- estimable functions, estimations and error space, Best linear unbiased estimate (BLUE),
Markov theorem distribution of quadratic form, Estimable linear hypotheses generalized F and T tests.
Analysis of Variance : Two-way classification with equal number of observation per cell and Tukey’s test
general two-way classification, Analyses of covariance,
Balanced Incomplete Block Design (BIBD), construction of BIBD, intra block and inter block analysis, split
plot design.
PGSTAT-05 / MASTAT-05
Survey Sampling
Sampling Theory: stratified sampling, Post-stratification and deep stratification, Methods of allocation, ratio
and regression estimators, double sampling in ratio and regression estimation.
Cluster sampling with equal clusters two stage and multi-stage sampling, Non sampling errors.
Varying probability sampling with and without replacement, cumulative total and Lahiri’s methods of
selection, Estimation of population mean, Desraj ordered estimates.
PGSTAT-07(P) / MASTAT-07(P)
Stochastic Process
Two state Markov sequences, Markov chains, determination of n-step transition probabilities, Chapman-
Kolmogorov equations, first return and first passage probabilities.
Classification of states, communication states, periodicity, stationary probability distributions and limit
theorems for Ergodic chains.
Continuous time Markov processes. Poisson (point) process, birth and death processes, random walk and
gambler’s ruin problem.
Simple branching process, probability generating function and moments of number of individuals in the n-th
generation, fundamental theorem of probability of extinction.
PGSTAT-09 / MASTAT-09
Decision Theory
Decision theoretic problem as a game, basic elements, optimal decision rules, unbiased ness, invariance,
ordering.
Bayes and minimax principles, generalized. Bayes rules, extended Bayes rules,
Admissibility, completeness, minimal complete class, separating and s upporting hyper plane theorems,
Minimax theorem, complete class theorem, equalizer rules, examples, multiple decision problems.
PGSTAT-10 / MASTAT-10
Multivariate Analysis
Multivariate normal distribution, Characteristic function, marginal and conditional distributions, multiple and
partial correlation coefficient.
Unit 2: MLE of parameters and sampling distributions of multiple and partial correlations
Maximum likelihood estimators of the mean vector and covariance matrix, sample Multiple and partial
correlation coefficients and their null sampling distributions
Wishart distribution. Its characteristic function, additive property of Wishart distribution, Hoteling’s T2 and
its applications
Nonparametrics
Order statistics, Distribution of maximum, minimum and r-th order statistic, Joint distribution of r-th and s-th
order statistic,
one sample and two sample location tests. Mann- Whitney U- Test, Application of U-statistic to rank tests.
One sample and two sample Kolmagorov-Smirnov tests. Run tests. Pitman ARE.
PGSTAT-12 / MASTAT-12
Econometrics
Linear regression model. Assumptions, estimation of parameters by least squares and maximum likelihood
methods tests of hypotheses and confidence estimation for regression coefficients, R2 and adjusted R2 , point
and interval predictors
Use of dummy variables, model with non-spherical disturbances, estimation of parametric by generalized
equation, Seemingly unrelated regression equations (SURE) model and its estimation
Unit 3: Structural and reduced form of the model and identificatio n problem
Simultaneous equations model, concept of structural and reduced forms, problem of identification, rank and
order conditions of indentifiability
Limited and full information estimators, indirect least squares estimators, two stage least squares estimators,
three stage least squares estimators.
PGSTAT-14(P) / MASTAT-14(P)
Demography
Block-4. Mortality
Unit-1 : Introduction, crude death rate (CDR), specific death rates (SDR), standardized death
rate (STDR).
Unit-2 : Life table, abridge life table, model life table of UNO (old and new), coale and demny
model, brass model through logit transformation.
B.Sc. Statistics / B.A. Statistics
UGSTAT-01
Statistical Methods
Unit-I- Estimation :
Point Estimation, properties of a good estimators, Consistency, Unbiased ness,
Efficiency, Sufficiency, Confidence Interval Estimation .
Unit-II- Method of Estimation:
Procedures of Estimation, Method of Moments, method of Maximum Likelihood,
Method of Scoring, Properties of Estimators.
Unit-III- Testing of Hypothesis :
Statistical Hypothesis, Simple and Composite Hypothesis, Critical Region, Two
kinds of Error, One-tailed and Two-tailed tests, Test of Significance, Most Powerful
Test, Uniformly Most Powerful Test .
Unit-I- Representation of Transportation Problem (Non-Ge nerated & Balance d Cases only) &
Assignment Proble m as Linear Programming Proble m:
Introduction of T.P. & A.P., Transportation Problem as LPP, Non-Degenerate
Transportation Problem, Balanced Transportation Problem, Assignment Problem &LPP,
Balanced Assignment Problem.
Unit-II- Different Methods of Finding Initial Feasible Solution of a Trans portation Problem
(T.P., MODI Method of Finding Optimal Solution of a T.P.) :
Introduction, Basic Feasible Solution of a Transportation Problem, Modified
Distribution Method (MODI), Vogel’s Approximation Method (VAM), Maximization in a
Transportation Problem .
Unit-III- Solution of Assignment Problem With using Hungarian Method :
Introduction, Solution of an Assignment Problem, Hungarian Method, Maximization
in an Assignment Problem.
Unit-I- Neyman- Pearson Lemma, Likelihood Ratio Test & Their Uses :
Introduction, Neyman-Pearson Lemma, Likelihood Ratio Test.
Unit-II- Testing of Means of Normal Population :
Introduction, One Sample Problem, Two Sample Problem.
Unit-I- Inte rval estimation :
Introduction, Confidence Interval & Confidence Coefficient, C.I. For Sample Mean
from a Normal Population, C.I. for differences of Means From Two Normal Population.
Unit-II- Shortest & Shortest Unbiased Confidence Intervals :
Introduction, Intervals of Shortest Length, Neyman’s Principle of Shortest Confidence
Interval, Unbiased Confidence Interval, Shortest Unbiased Confidence Interval, Case of
Discreet Random Variables.
UGSTAT-09 (P)
UGSTAT-10 (P)
UGSTAT-11 (P)