Lecture 6: Describing data (part 2)
September 19, 2024 (3rd week of classes)Read and watch everything
Describing data via summary statistics and their relations with statistical distributions
Samples and populations typically consist of numerous individual observational units and their associated information (observations, variables).
To characterize these samples, we use summary statistics (mean, median, variance, etc.) that serve as estimates for the corresponding summaries of their statistical populations.
In this second lecture on describing data, we will explore spread statistics related to the median. We will delve deeper into the properties of various location and spread statistics and examine how they relate to the shape of frequency distributions.
Frequency distributions are the gateway to understanding probabilities and uncertainty. Therefore, grasping the roles of summary statistics for location (mean, median) and spread (variance, standard deviation, interquartile range) and their relationship to the properties of frequency distributions is essential.
Connecting summary statistics for location and spread enables us to perform statistics - the science of making informed decisions with incomplete information. Since we never have complete information, accounting for uncertainty is critical! In essence, we often make decisions on location statistics and assess the uncertainty of these decisions on spread statistics. We will cover this concept in later lectures.
Lecture
Slides: