Institute of Science and Technology
Bachelor of Science in Computer Science and Information Technology
Course Title: Statistics II
Course no: STA164
Nature of course: Theory + Lab
Full Marks: 60 + 20 + 20
Pass Marks: 24 + 8 + 8
Credit Hours: 3
Course Description : This course contains basics of statistics, descriptive statistics, probability, sampling, random variables and mathematical expectations, probability distribution, correlation and regression
Course Objective : The main objective of this course is to impart the knowledge of descriptive statistics, correlation, regression, sampling, theoretical as well as applied knowledge of probability and some probability distributions.
Sampling distribution of mean and proportion; Concept of Central Limit Theorem; Concept of inferential Statistics; point estimation; Properties of a “Good” estimator: unbiasedness, consistency, efficiency and sufficiency; Methods of estimation: Maximum likelihood estimation, Method of moments; Interval estimation: Confidence interval and confidence coefficient, confidence limits, confidence interval of mean for normal population. Confidence interval for proportion; Determination of sample size, relationship of sample size with desired level of error. Problems and illustrative examples related to computer Science and IT
Types of statistical hypotheses – null and alternative hypothesis, type I and type II errors, level of significance, critical value and critical region, power of the test, concept of p-value and use of p - value in decision making, steps used in testing of hypothesis, one sample tests for mean of normal population (for known and unknown variance), test for single proportion, test for difference between two means and two proportions, paired sample t-test; Linkage between confidence interval and testing of hypothesis; Assumptions for applying independent t-test, paired t-test; Test of equality of two variances
Parametric vs. non-parametric test; Needs of applying non-parametric tests; One-sample test: Run test, Binomial test, Kolmogorov–Smirnov test; Two independent sample test: Median test, Kolmogorov-Smirnov test, Wilcoxon Mann Whitney test, Chi-square test; Paired-sample test: 2 Wilcoxon signed rank test; Cochran’s Q test; Friedman two way analysis of variance test; Kruskal Wallis test.
Multiple and partial correlation; Introduction of multiple linear regression; Least square estimation of parameters; Properties of least square estimators; Matrix approach to multiple linear regression; Hypothesis testing of multiple regression(upto two independent variables): Test of significance of regression, test of individual regression coefficient; Model adequacy test: Residual analysis, influential observation, multicollinearity; Coefficient of determination, Adjusted R2, and their interpretations.
Basic terminologies of experimental design; Basic principles of experimental designs; Completely Randomized Design (CRD): Statistical analysis of CRD, ANOVA table, Advantages and disadvantages, concept of multiple comparisons; Randomized Block Design (RBD): Statistical analysis of RBD for one observation per experimental unit, ANOVA table, Efficiency of RBD relative to CRD, Estimations of missing value (one observation only), Advantages and disadvantages; Latin Square Design (LSD): Statistical analysis of m x m LSD for one observation per experimental unit, ANOVA table, Estimation of missing value in LSD (one observation only), Efficiency of LSD relative to RBD, Advantage and disadvantages.
Definition and classification; Markov Process: Markov chain, Matrix approach, Steady- State distribution; Counting process: Binomial process, Poisson process; Simulation of stochastic process; Queuing system: Main component of queuing system, Little’s law; Bernoulli single server queuing process: system with limited capacity; M/M/1 system: Evaluating the system performance.
The laboratory work includes implementing concepts of statistics using statistical software tools such as SPSS, STATA etc.
|S. No.||Practical problems||No. of practical problems|
|1||Sampling distribution, random number generation, and computation of sample size||1|
|2||Methods of estimation (including interval estimation)||1|
|3||Parametric tests (covering most of the tests)||3|
|4||Non-parametric test(covering most of the tests)||3|
|7||Design of Experiments||3|
|Total number of practical problems||15|