Which Chart When?
1.Bar chart
Type of data: Categorical, quantitative
When to use it: Use a bar chart to
compare data across categories.
What it shows: Bar charts display data
using rectangular bars, with the length of
the bar representing the value. The bars
can be horizontal or vertical
When to avoid it: Avoid using a bar chart
when there are too many categories or if
the data is continuous
2.Line Chart
Type of data: Continuous, time-series
When to use it: Use a line chart to show
trends over time.
What it shows: Line charts plot data
points connected by lines. The X-axis
usually represents time, and the Y-axis
represents the value.
When to avoid it: Only use a line chart
when there is a logical order or
relationship between data points.
3.Donut Chart
Type of data: Categorical, proportional
When to use it: Use a donut chart to show the
proportion of each category.
What it shows: Donut charts represent
data as slices of a circle, each
representing a percentage of the total.
When to avoid it: Avoid using donut charts
when there are too many categories or
comparing data across groups
4.Scatter plot
Type of data: Continuous, bivariate
When to use it: Use a scatterplot to
display the relationship between two
variables.
What it shows: Scatterplots plot data
points on a two-dimensional plane, with
one variable on the X-axis and the other
on the Y-axis.
When to avoid it: Don't use a scatterplot
when the relationship between variables
is irrelevant or when comparing multiple
categories
5 .Area Chart
Type of data: Continuous, time-series
When to use it: Use an area chart to show
the volume or magnitude of data over
time.
What it shows: Area charts are similar to
line charts, but the area between the line
and the X-axis is filled, emphasizing the
volume or magnitude.
When to avoid it: Avoid using an area
chart with multiple data series with
overlapping areas, as it can be confusing.
6.Bubble Chart
Type of data: Continuous, multivariate
When to use it: Use a bubble chart to
display the relationship between three
variables.
What it shows: Bubble charts are a
variation of scatterplots, with the size of
the bubbles representing the third
variable.
When to avoid it: Don't use a bubble
chart when the size of the bubbles is not
meaningful or when comparing multiple
categories.
7.Histogram
Type of data: Continuous, univariate
When to use it: Use a histogram to
display the data distribution.
What it shows: Histograms are similar to
bar charts, but the data is divided into
equal intervals, and the bar's height
represents the data frequency in each
interval.
When to avoid it: Avoid using histograms
when the data is categorical or
comparing data across groups.
8. Heatmap
Type of data: Continuous, multivariate
When to use it: Use a heatmap to display
the relationship between two variables
using color intensity.
What it shows: Heatmaps use a color
scale to represent the value of each cell in a matrix, with one
variable on the X-axis and the other on the Y-axis. Darker colors
indicate higher values, while lighter colors represent lower values.
When to avoid it: Don't use a heatmap when the
relationship between variables is irrelevant, when the data is
categorical, or when comparing multiple categories.
9.Treemap
Type of data: Categorical, hierarchical
When to use it: Use a treemap to display
hierarchical data or to show the
proportion of each category as a whole.
What it shows: Treemaps use nested
rectangles to represent data, with the
size of each rectangle proportional to its
value. Color can be used to indicate
additional information.
When to avoid it: Avoid using treemaps
when there are too many categories or
the data is not hierarchical
10.Radar Chart
Type of data: Continuous, multivariate
When to use it: Use a radar chart to
display the performance or
characteristics of different categories
across multiple dimensions.
What it shows: Radar charts use a
circular layout with multiple axes, each
representing a dimension. Data points
are plotted on each axis and connected
to form a shape.
When to avoid it: Don't use a radar chart
when there are only a few dimensions or
when comparing data across groups.
