Statistics for Data Science Online Course

Statistics for Data Science and Business Analysis

This course will teach you fundamental skills that will enable you to understand complicated statistical analysis directly applicable to real-life situations. Modern software packages and programming languages are now automating most of these activities, but this course gives you something more valuable—critical thinking abilities. This course will help you understand the fundamentals of statistics, learn how to work with different types of data, calculate correlation and covariance, and more. Careers in the field of data science are some of the most popular in the corporate world today. And, given that most businesses are starting to realize the advantages of working with the data at their disposal, this trend will only continue to grow.

Course Curriculum

Introduction

• What does the Course Cover?

Sample or population data?

• Understanding the difference between a population and a sample

The fundamentals of descriptive statistics

• The various types of data we can work with
• Levels of measurement
• Categorical variables. Visualization techniques for categorical variables
• Numerical variables. Using a frequency distribution table
• Histogram charts
• Cross tables and scatter plots

Measures of central tendency, asymmetry, and variability

• The main measures of central tendency: mean, median, mode
• Measuring skewness
• Measuring how data is spread out: calculating variance
• Standard deviation and coefficient of variation
• Calculating and understanding covariance
• The correlation coefficient

Practical example: descriptive statistics

• Practical example

Distributions

• Introduction to inferential statistics
• What is a distribution?
• The Normal distribution
• The standard normal distribution
• Understanding the central limit theorem
• Standard error

Estimators and estimates

• Working with estimators and estimates
• Confidence intervals - an invaluable tool for decision making
• Calculating confidence intervals within a population with a known variance
• Student’s T distribution
• Calculating confidence intervals within a population with an unknown variance
• What is a margin of error and why is it important in Statistics?

Confidence intervals: advanced topics

• Calculating confidence intervals for two means with dependent samples
• Calculating confidence intervals for two means with independent samples (part 1)
• Calculating confidence intervals for two means with independent samples (part 2)
• Calculating confidence intervals for two means with independent samples (part 3)

Practical example: inferential statistics

• Practical example: inferential statistics

Hypothesis testing: Introduction

• The null and the alternative hypothesis
• Establishing a rejection region and a significance level
• Type I error vs Type II error

Hypothesis testing: Let's start testing!

• Test for the mean. Population variance known
• What is the p-value and why is it one of the most useful tool for statisticians?
• Test for the mean. Population variance unknown
• Test for the mean. Dependent samples
• Test for the mean. Independent samples (Part 1)
• Test for the mean. Independent samples (Part 2)

Practical example: hypothesis testing

• Practical example: hypothesis testing

The fundamentals of regression analysis

• Introduction to regression analysis
• Correlation and causation
• The linear regression model made easy
• What is the difference between correlation and regression?
• A geometrical representation of the linear regression model
• A practical example - Reinforced learning

Subtleties of regression analysis

• Decomposing the linear regression model - understanding its nuts and bolts
• What is R- squared and how does it help us?
• The ordinary least squares setting and its practical applications
• Studying regression tables
• The multiple linear regression model
• Adjusted R-squared
• What does the F-statistic show us and why we need to understand it?

Assumptions for linear regression analysis

• OLS assumptions
• A1. Linearity
• A2. No endogeneity
• A3. Normality and homoscedasticity
• A4. No autocorrelation
• A5. No multicollinearity

Dealing with categorical data

• Dummy variables

Practical example: regression analysis

• Practical example: regression analysis