Applied Statistics
Course description
42770 Applied Linear Models
This course aims to discuss the applications of linear models including: Main concepts of linear algebra, applications of simple and multiple regression models, multivariate normal distribution, quadratic forms, examples of quadratic forms from the ANOVA tables, distribution of the quadratic forms, non-central Chi-square, F and t distributions and their relationship with the ANOVA tables, testing general linear hypotheses, Confidence intervals and regions, using statistical package for real applications of linear models.
41760 Foundation of Statistics
This is an introductory course in statistics designed to provide students with the basic concepts of data analysis and statistical computing. Topics covered include basic descriptive measures, measures of association, probability theory, confidence intervals, and hypothesis testing. The main objective is to provide students with pragmatic tools for assessing statistical claims and conducting their own statistical analyses.
42772 Applied Multivariate Analysis
The objective of this course is to teach topics of multivariate statistics such as PCA, Factor analysis/SEM, Cluster Analysis and Multidimensional Scaling/Correspondence Analysis. The emphasis of the course will be on applications and use one statistical software packages for analyzing data such as R, SAS, SPSS-AMOS, SmartPLS, LISREL. Multivariate Analysis of Variance (MANOVA). The course includes preparing a term paper using real data and Project presentation.
42771 Design of Experiment
This course aims to discuss the fundamentals of experimental designs and the analysis methods including: A brief review of (complete randomized, randomized complete block design, Latin square and Graeco-Latin square), Incomplete blocks design (balanced and partially balanced), Factorial experiments, Split plots, Confounding, Response surface methodology's steepest ascent, Selection of optimal designs (optimality criteria). Implementing the statistical techniques on real data sets using statistical computing packages.
42773 Time Series
Survey of forecasting and time series methods. Models for stationary and non-stationary time series; ARIMA model identification, estimation, and forecast development. Unit root tests , Seasonal and dynamic models. ARCH and GARCH models. Case studies.
42774 Survival Analysis
This course deals with methods analyzing time-to-event data which may be censored and/or truncated. The main topics are: Types of censoring and truncation, Survival distributions, Estimating a survival curve parametrically and non-parametrically, Proportional and non-proportional hazards regression models, Frailty models, Accelerated failure time and other parametric models, Nonparametric methods. Implementing the statistical techniques on real data sets using statistical packages.
42791 Thesis
رسالة (A) يقوم الطالب بإعداد مقترح لبحثه ويحصل على تغذية راجعة من المشرف. فإذا استطاع الطالب أن يناقش مقترح الرسالة المقدم ويدافع عنه بكفاءة يُعّد ناجحًا. رسالة (B) يكمل الطالب بحثه ويلتقي بشكل منفرد مع المشرف من أجل استكمال العمل على بحثه. ويتوقع من الطالب أن ينهي جمع البيانات، والاستعداد لتحليل البيانات ووضع اللمسات الأخيرة على الأطروحة والاستعداد للدفاع عنها.
42775 Sampling Techniques
Review of some basic statistical and probability concepts, main objectives of statistics, main sampling techniques: simple, stratified, cluster and systematic random samplings. Ratio and regression estimation. Other sampling techniques: multistage, probability proportionate to size, and stratified multistage sampling. Estimation of Population size, capture recapture techniques. The sampling and non-samplingerrors, nonresponse. Sampling for rare events. Using statistical packages.
42776 Bayesian Methods
Principles of Bayesian Statistics. Bayesian analysis of data in different fields of science. Modelling data using Hierarchical and non-hierarchical models, including linear and generalized. Model checking, model selection and model comparison. Bayesian computation using Markov Chain Monte Carlo algorithms. Applications in the sciences utilizing computer software.
42778 Nonparametric Statistics
Review of the order statistics concept, Inference based on ranked data, Inference about the parameters of one or more independent populations, Inference using one or more related samples, Chi-square and Kolmogorov-Smirnov tests for goodness of fit, Wald-Wolfowitz test, Rank correlation and other measures of association, Nonparametric procedures in regression analysis.
42779 Statistical Quality Control
A comprehensive coverage of modern quality control techniques to include the design of statistical process control systems, acceptance sampling, advanced control charts such as CUSUM and EWMA charts and the Process Capability Analysis. The emphasis of the course will be on applications and use one statistical software packages for analyzing data such as R, Minitab, SPSS, IMSL, Mathematica or Matlab.EXCEL sheets could be used also. The course includes preparing a term paper using real data and Project presentation.
42781 Categorical Data Analysis
The course objective is to learn basic knowledge and skills of how to analyze categorical data. Specific topics include: basic contingency table analysis, generalized linear regression model, binary regression models, loglinear models, clustered categorical data analysis, and the current research problems in categorical data analysis. For statistical computing, it focuses on using R software for performing categorical data analysis. The emphasis of the course will be on applications and use one statistical software packages for analyzing data such as R, Minitab, SAS, Mathematica or Matlab. The course includes preparing a term paper using real data and Project presentation.
42761 Regression Analysis
Simple and multiple linear regression models: Methodology for fitting models, Statistical inference, Diagnostics and remedies, Solving using matrix algebra. Dealing with qualitative predictors, Interaction effects. Variable selection and model building. Generalized linear models, Logistic regression, Regression with ordinal and nominal responses. Regression with autocorrelated errors. Non-parametric regression. Case studies.
42783 Data Mining
This course is designed to give the student the foundational tools to help discover and navigate the increasingly popular field of statistical machine learning and data mining. We provide a gentle yet thorough introduction to supervised learning with topics such as multiple linear regression (MLR) and nonlinear regression, pattern recognition using techniques such as logistic regression and support vector machines. We also cover unsupervised learning, featuring cluster analysis, feature selection, dimensionality reduction and latent variable models. The course culminates with modern techniques of model selection and model aggregation.
42782 Special Topics
This course will provide an introduction to some topics according to the students’ needs..