Visualizing Data PDF
Document Details
Uploaded by UnbiasedAzalea
UVic
Tags
Summary
This document discusses the importance of data visualization, exploring tables, graphs, and charts to examine data, identify patterns, and communicate findings effectively. It covers various graph types, including histograms, bar graphs, line graphs, and box plots, suitable for different data representations. Understanding these techniques is crucial for effective data analysis, though poor choices in visualization can mislead readers.
Full Transcript
2/12/25, 11:55 AM OneNote Visualizing Data Thursday, January 30, 2025 11:51 AM Tables and graphs (plots, charts..): Why use graphs? Before analysis: examine data (shape, outliers, et...
2/12/25, 11:55 AM OneNote Visualizing Data Thursday, January 30, 2025 11:51 AM Tables and graphs (plots, charts..): Why use graphs? Before analysis: examine data (shape, outliers, etc. ) and look for patterns Analysis phase: examine realtionships, differnce between samples, idetify other patters Publicaiton: convey key findings, illistrate your evidnece But can be used to mislead (on porpuse or not), and poor choices can confuses Types of graphs: Histogram Frequency (or %) of data in classes/bins Shows distributions (shape) of continuous data Spotting outliers- extreme values Are these "bad" data or normal sample variation ○ What might "bad" data be caused by? https://uvic-my.sharepoint.com/personal/lucybryden_uvic_ca/_layouts/15/Doc.aspx?sourcedoc={9faa0b91-e898-498c-a6e1-c5e15b84c2ef}&action=edit&wd=target… 1/3 2/12/25, 11:55 AM OneNote Other "shapes" can suggest sub-group within your sample A smoothed histogram ○ Density here is the probaility densiry function- the spares are beyond our needa, but realtes to probability of a speciufic being drawn at random from sample Other "shapes" can suggest sub-Types of graphs: Bar graphs Discrete data (categories) Using sample categories instead of bins No "shape" to examine, but can visually compare categories ○ Categorical data- Comparisions (counts, frequencies) amount categories Line Graph: Ordered Categories- relationships between variables or change across times Means Plot: https://uvic-my.sharepoint.com/personal/lucybryden_uvic_ca/_layouts/15/Doc.aspx?sourcedoc={9faa0b91-e898-498c-a6e1-c5e15b84c2ef}&action=edit&wd=target… 2/3 2/12/25, 11:55 AM OneNote Continuous Data- good to show change in mean or variability over time (basically, a line graph with error bars added) Box Plot: Continuous data- comparison of distributions of samples Box divides sample into interquartile range. Whiskers indicate +/- 1.5* IQR In total, represents 99.3% of data IF normal distribution Important to notes in figure caption https://uvic-my.sharepoint.com/personal/lucybryden_uvic_ca/_layouts/15/Doc.aspx?sourcedoc={9faa0b91-e898-498c-a6e1-c5e15b84c2ef}&action=edit&wd=target… 3/3
