Data Science: Statistics and Machine Learning Specialization by Johns Hopkins University – Coursera

Statistics and Machine Learning Specialization by Johns Hopkins University ranks 8th in the list of best online statistics courses. This online course is available through Coursera. The course is designed for students who have a basic understanding of statistics and machine learning. It covers statistical inference, regression models, and data analysis machine learning methods. Learners will also be able to create data products utilizing a variety of tools and approaches, as well as interact with real-world data. Furthermore, the students will have a full understanding of how to develop and implement prediction functions, as well as how to use advanced statistics to draw conclusions about populations and scientific insights from data.

The course contents are:

Statistical inference

• In this module, the learners will understand how to draw conclusions about populations and perform various inferences, including statistical modeling and data-related strategies. Moreover, the learners will understand the uses of designs and randomization in data analysis and the broad theories of frequentists, Bayesian, and Likelihood. In addition, the learners will explore various complexities faced with missing data, observed and unobserved confounding, and bias while handling data.

Regression models

• The second module explores the linear models for assumptions, regression models, and a subset of linear models. Furthermore, the learners will explore the statistical analysis tools for modern data scientists and cover many concepts, including regression analysis, least-square, and inference using statistical models.
• Besides, the learners will delve into advanced concepts and learn to use ANOVA test and analysis of residuals and variability and building scatterplots for presenting analytical reports.

Practical machine learning

• This module covers the essential components of building a prediction function on practical applications. The learners will explore the concepts of training and test data sets, overfitting, and error rates associated with computational models. In addition, the basics of the range of a model and essential machine learning algorithms such as regression. Classification trees, Naïve Bayes, and random forests are covered in-depth with hands-on lab sessions.

Data science capstone

• The final module is mandatory for learners as the capstone requires creating usable and public data products from real-world problems in collaboration with industry, government, or academic partners. The learners are required to clear the capstone to attain the certificate of completion.

Instructor: Brian Caffo, Jeff Leek, and Roger D. Peng

Level: Intermediate

Duration: 6 months

User Review: 4.6/5

No. of Reviews: 484

Price: Free Enrollment (Additional charges for certification may apply)

Website: coursera.org/specializations/data-science-statistics-machine-learning