Coursera Course: Data Analysis and Statistical Inference

Duke University

Description:

Even though the course from www.coursera.com provides the necessary guidance needed by the students, they will need some extra assistance outside the given course guidelines. In order to understand the lessons better a student will need some actual class sessions. These classroom sessions are provided by TutorTeddy.com based on the courses of Coursera. Students can interact with professional instructors can get their queries answered and learn faster.

The course emphasizes on the principles of statistics and it gives us a detailed idea of the subject and how data are analyzed. This particular course will help the students to learn how effectively data should be used at times of uncertainty. Details of data collection, analyzing data and making inferences from the data and finally drawing conclusions regarding the phenomena of the real world form the basis of this course.

Objectives:

• Significance of data collection- Why it is important to select the appropriate methods of collection? And what are the drawbacks of the methods of data collection and how much they affect the scope of making inferences?


• The use of the R software for summarizing the data in a numerical and visual manner and how data analysis is performed.


• Conceptual understanding of the statistical inference is been provided.


• Analyzing single variables by using and applying confidence interval for estimation and hypothesis tests for testing and studying the relationship between the two variables to get an idea of the natural phenomena and make decisions based on the data.


• The procedure of modeling and investigating the relationships between two variables (or more than two variables) in the context of regression.


• Accurately interpreting the data in an effective manner that is based on the context and not relying on statistical jargon.


• Evaluation of the claims based on data and data driven decisions.


• Involving and completing the research project that includes the simple statistical inferences and the various modeling techniques.

Syllabus of the Course:

Week 1 is based on introduction to data that includes how studies should be designed and concepts of exploratory data analysis and idea of simulation.

Week 1 is based on introduction to data that includes how studies should be designed and concepts of exploratory data analysis and idea of simulation.

Week 2 includes the concepts of Probability and distributions-the basics of probability and conditional probability; the details of normal and the binomial distribution.

Week 3 gives us an idea on Central Limit theorem; the concepts of confidence intervals and hypothesis testing.

Week 4 includes the inference for different estimators and basics of decision errors, confidence and significance.

Week 5 deals with comparison of two means; bootstrapping method of re-sampling; inference based on t-distribution; and ANOVA method for comparing three(or more) means.

Week 6 includes the inference for categorical variables that includes testing of a single proportion, comparison of two proportions and inferences based on simulation and Chi-Square test for comparing three (or more) proportions.

Week 7 tells us about linear regression that gives us an idea of the relationships between two quantitative variables; how linear regression is performed for a single predictor; handling outliers in linear regression; making inferences from linear regression.

Week 8 is based on the concepts of multiple linear regressions that include regression having multiple predictors, inferences from multiple linear regression, how model is selected and diagnosed.

Week 9 is based on advanced topic that tells us about Bayesian and frequentist inference.

Week 10 is the time for final exam.

Format of the Course:

Video lectures containing quiz questions of 5-10 minutes in length are been included in the class. Homework assignments are there that consists of ungraded questions from textbooks, graded multiple choice quizzes, data analysis project and computational data analysis assignments, and inclusion of a midterm and a final exam at the end of the Coursera.