Data Visualization Tools ✅

Scatterplot

- A data visualization tool that displays a set of points plotted on the horizontal and vertical axis used to observe and show the pattern or relationship between variables. - Relationships between the variables may be described as positive or negative, strong or weak, linear or nonlinear.

Pictogram

- A pictogram uses icons or pictures to give more engaging overall view of small sets of discrete data. - Used to show ratings or scoring, or could spice up a simple bar chart for extra impact.

Dot Map

- A type of visualization model that uses a dot symbol to represent a constant number of objects - Detect spatial patterns - Generally used to show how things are distributed over a geographical region

Treemap

- Display hierarchical data as a set of nested rectangles. Each branch of the tree is given a rectangle, which is then tiled with smaller rectangles representing sub-branches. - Alternative way of visualizing the hierarchical structure of a tree diagram while also displaying quantities for each category via area size.

Waterfall

- Expresses a visual example of how cumulative effects work on data. This chart can be used to show how the starting value is influenced by a series of values. -- Also known as flying bricks chart, Mario chart, or bridge due to its distinct look.

Stacked Bar Chart

- Extends the standard bar chart from looking at numeric values across one categorical variable to two. -- Each bar is divided into a number of sub-bars stacked end to end, each one corresponding to a level of the second categorical value. -- Can be difficult to compare columns that don't start at the same baseline. --- Use a legend to distinguish variables --- Use when trying to show how a larger category is divided into smaller categories.

Donut Chart

- Focus readers more on reading the length of the arcs rather than comparing the proportions between the slices. - Deemphasizes the use of the proportional areas of the slices unlike pie charts. - A pie chart with an area of the center cut out. - More space efficient than pie charts. The blank space inside of this chart can be used to display information in it.

Lollipop Chart

- Good for data that has been divided into categories and for showing the relationship between a number and a category. - The same as a bar chart but it has thin lines with a dot for the value. This chart has a horizontal (categories) and a vertical axis (values) that are both labeled. - Helpful when you would have a bar chart with values that are close to each other. It is more pleasing to the eye when you would have a full bar chart.

Bar/Column Chart

- Good for displaying data that has been organized into categories. - Always label horizontal and vertical axis - Never use the 3D bar chart.

Diverging Bar Chart

- Just like vertical bar charts, but instead they align the data on the center baseline instead of the left and the right. - Good visual when you are trying to show the proportions above goal value or you are trying to visualize results on a Likert scale.

Speedometer (Gauge Charts and Dial Charts)

- Shows the maximum, the minimum, and the present value of data being analyzed.

Bubble Map

- Used for visualizing the proportions of a population in a certain geographic region. - The area of the circle is directly related to the value in the data set.

Venn Diagram

- Used to display all the possible logical relationships between a collection of sets. Each set is represented by a circle. -- This may also be used to show comparison - Contained within each set is a collection of items or entities that all have something in common.

Choropleth Map

- Used to display geographical maps by using different shades, patterns, and colors to help the viewer visualize a certain pattern or variation. -- Example: socioeconomic data like populations and crime rates.

Line Chart

- Used to display quantitative values over a continuous interval or time period. - Most frequently used to show trends and analyze how the data has changed over time

Box and Whisker Plot

- Used to show the distribution of a group of data. - Data is displayed in five parts: the minimum, first quartile, median, third quartile, and the maximum.

Marimekko Chart

- Used to visualize categorical data over a pair of variables. - Helpful for detecting relationships between categories and their subcategories through the two axes. - Both axes are presented in percentages scales to determine width and height. - They are sometimes hard to read and make accurate comparisons but are better for giving an overview of data.

Radar Chart

- Used when we are displaying ordinal measurements. -- Primarily suited for showing extreme outliers and commonality between data points in the chart.

Area Chart

- Useful for seeing volume changes over a period of time, overall trends, and continuity across a dataset, without focusing on specific data values. - Based on the line chart. The area between the axis and line are commonly emphasized with colors. - Not good for short time spans

Heat Map

- Uses colors to visualize data. -- Values are represented as colors. - Normally, all rows are one category and the columns are divided into subcategories, which all will match up in a matrix. -- A legend is required to read this successfully.

Density Plot

- Visualizes the distribution of data over a period of time with the use of numeric variables. - Delivers the same concept as a histogram, but are better at determining the distribution shape.

Pie Charts

A circular statistical graphic, which is divided into slices to illustrate numerical proportion. They are considered a good choice used for nominal data.

Histogram

A data visualization tool used to represent the frequency distribution of a variable. Bar charts compare data, while Histograms show the distribution of data.

By most positive or most negative (the number of positive outcomes will go to the right and the number of negative outcomes will go to the left)

How are diverging bar charts generally sorted?

The box in the middle of the plot is simply called the "box" while the lines extending from either side of it are known as "whiskers."

How is a box plot formatted?

One-to-One

One dot represents a single object.

One-to-Many

One dot represents a unit. (Ex: One dot = Ten trees)

False

T or F: Bigger boxes equate to bigger data sets.

True

T or F: Diverging bar charts are often used with survey data.

True

T or F: In a bubble map, the bigger the number in a population the larger the circle is, leading to overlaps in bubbles in a region.

- Easy to read - Easy to compare the distribution of items considering the concentration of the dots.

What are advantages of dot maps?

- Summary statistics - Symmetry of a data set

What are box plots good for showing?

- Exact values are not shown - Outliers may not be shown

What are disadvantages of box plots?

- The more lines, the more clutter there is on the chart making it harder to read. -- Stick to 3-4 lines per graph

What are disadvantages of using line charts?

- Skewed Left - Skewed Right - Bimodal - Multi-modal - Symmetric

What are some patterns of a histogram?

- Bold color scheme - Data is following the same scale and constraints - Make sure the divergence line has a purpose

What are the "do's" of diverging bar charts?

- Shows large amounts of data - Visually pleasing to the viewer

What are the advantages of the choropleth map?

Not as quick and easy to understand as vertical bar charts

What are the cons of diverging bar charts?

Correlation is sometimes confused with causation.(scatterplot may reveal correlation, but doesn't provide info on causation)

What are the cons of scatterplots?

- Hard to compare and interpret data - The viewer may think that larger regions have more emphasis on them than smaller regions.

What are the disadvantages of the choropleth map?

- Illustrates trends - Can work well with large quantities of data

What are the pros of scatterplots?

- Distinct suspended block view - Color coordinated - Shows increasing and decreasing values clearly

What are the qualities of waterfall charts?

One-to-One One-to-Many

What are the two types of dot maps?

- How the whole is divided: for each level of the hierarchy, it is easy to understand which entity is the most important and how the whole is distributed among entities. - How the hierarchy is organized.

What are the two types of ways treemaps are used to show information simultaneously?

- Inventory or performance Analytics - Common in financial values - Can display quantitative data

What are the uses of waterfall charts?

- Cross-examining multivariate data - Show changes to data over time

What are uses of a heat map?

Value Amount

What does bar length equal?

Timescale or a sequence of intervals.

What does the x-axis represent on a line chart?

Qualitative Value

What does the y-axis represent on a line chart?

Counts

What is a bar chart good for showing?

A disadvantage can be that it is hard to tell the differences between the color shades.

What is a disadvantage of a heat map?

It might be difficult to read the values because the dot at the end of the line is made bigger than the line itself making the exact value hard to define.

What is a disadvantage of the lollipop chart?

Showing size and proportion at the same time.

What is a good use for marimekko charts?

The regional size areas does not cause any problems when comparing proportions over geographic regions.

What is an advantage of using bubble maps?

Simple presentation; easy to read and create.

What is an advantage of using line charts?

Likert Scale

What is an example of when we would use a diverging bar chart?

Intersection Area

When a set overlaps in a venn diagram, what is this referred to as?

When: - Plotting nominal or ordinal data - Comparing multiple categories

When are histograms NOT useful?

- When plotting continuous data - When one wants to see the shape of the data's distribution

When are histograms useful?

When trying to determine whether two variables are related.

When can a scatterplot be used?

- When there are a large number of variables - When totals have long labels - When you need more than 10 bars.

When should we not use stacked bar charts?