Learn what sampling is and why it is useful, understand the problems caused by convenience sampling, and learn about the differences between true randomness and pseudo-randomness.

Sampling and point estimates

Reasons for sampling

Simple sampling with dplyr

Simple sampling with base-R

Convenience sampling

Are findings from the sample generalizable?

Are these findings generalizable?

Pseudo-random number generation

Generating random numbers

Understanding random seeds

Introduction to Sampling

Learn how to and when to perform the four methods of random sampling: simple, systematic, stratified, and cluster.

Simple random and systematic sampling

Simple random sampling

Systematic sampling

Is systematic sampling OK?

Stratified and weighted random sampling

Which sampling method?

Proportional stratified sampling

Equal counts stratified sampling

Weighted sampling

Cluster sampling

Benefits of clustering

Performing cluster sampling

Comparing sampling methods

3 kinds of sampling

Summary statistics on different kinds of sample

Sampling Methods

Learn how to quantify the accuracy of sample statistics using relative errors, and measure variation in your estimates by generating sampling distributions.

Relative error of point estimates

Calculating relative errors

Relative error vs. sample size

Creating a sampling distribution

Replicating samples

Replication parameters

Approximate sampling distributions

Exact sampling distribution

Approximate sampling distribution

Exact vs. approximate

Standard errors and the Central Limit Theorem

Population & sampling distribution means

Population and sampling distribution variation

Sampling Distributions

Learn how to use resampling to perform bootstrapping, used to estimate variation in an unknown population. Understand the difference between sampling distributions and bootstrap distributions.

Introduction to bootstrapping

Bootstrap true or false

True

False

Principles of bootstrapping

With or without replacement

With replacement

Without replacement

Generating a bootstrap distribution

Comparing sampling and bootstrap distributions

Bootstrap statistics and population statistics

Sampling distribution vs. bootstrap distribution

Compare sampling and bootstrap means

Compare sampling and bootstrap standard deviations

Confidence intervals

Confidence interval interpretation

Calculating confidence intervals

Congratulations!

Bootstrap Distributions

Coffee ratings

Spotify song attributes

Employee attrition

Sampling is a cornerstone of inference statistics and hypothesis testing. It's tremendously important in survey analysis and experimental design. This course explains when and why sampling is important, teaches you how to perform common types of sampling, from simple random sampling to more complex methods like stratified and cluster sampling. Later, the course covers estimating population statistics, and quantifying uncertainty in your estimates by generating sampling distributions and bootstrap distributions. Throughout the course, you'll explore real-world datasets on coffee ratings, Spotify songs, and employee attrition.

Introduction to Statistics in R

Learn how you can perform common types of sampling in R, including simple random sampling and more complex methods like stratified and cluster sampling.

Sampling in R

Master sampling to get more accurate statistics with less data.

Associate Data Scientist in R

Datenanalyst  in R

Statistiker in R

Grundlagen der Statistik in R

Bootstrap resamples should be the same size as the original sample.

Each row in the dataset should have an equally likely chance of being drawn in a resample.

A bootstrap distribution consists of many replicates of the statistic of interest.

Resampling means sampling without replacement.

Bootstrap samples should be smaller than the original sample.

The statistic of interest for each bootstrap sample is always the mean.

A bootstrap distribution is the same thing as a sampling distribution.

Principles of bootstrapping

Sampling in R

Interaktive Übung