McMaster logo

## Faculty of Social Sciences

Find the most recent updates here, as well as FAQs and information for students, faculty and staff.

# Populations and Sampling Distributions

## Collecting data on a population-level poses many challenges, so statisticians often use carefully selected samples to make claims about the world.

As a consumer of statistical information, it is important to understand how claims about populations can be made from sample-level data, and as a researcher, it is important to know how to move between the worlds of samples and populations.

Resource:Samples and Populatio;ns (Kerby Shedden – UMichigan)
Type: Slide show
Who it’s for:People looking for a refresher on why we use samples and what they tell us about a population
Why we love it:It covers key vocabulary elements that will be useful in all quantitative social science work. Topics covered include examples of populations, simple random samples, independent and identically distributed (IID) samples, and non-IID samples.

Resource:What is a Sampling Distribution? | Puppet Master of Statistics (MarinStatsLectures)
Type: Video
Who it’s for:Anyone looking to understand the two-way relationship between populations and samples
Why we love it:This video really helps you move between the worlds of samples and populations. It also helps to answer the question ‘what can statistics teach us about the world?’. Also the puppets make it a lot of fun.

Resource:Populations and Samples – Statistics at Square One (the BMJ)
Type: Textbook excerpt
Who it’s for:Anyone looking to understand what populations and samples mean in statistics
Why we love it:This resource goes beyond defining populations and samples and provide some guidance on how effective researchers can think critically about the populations and samples involved in their work. Topic covered include populations, samples, unbiasedness and precision, randomization, variation between samples, standard error of the mean, standard error of a proportion or a percentage, and problems with non-random samples.