An extension of the concept of histogram to display the colour image content.
Bagplot : 2D boxplot
A generalisation of the boxplot, this visualisation relies on the median (red star) and the representation of 50% of the observations (dark blue area).
Box plot showing variation in under-18 conception rates per county across England.
County level 2008 US presidential election returns.
Bussiness cycle clock
This is a tool offered by the Organisation for Economic co operation and Development (OECD) to help visualise the business cycles around four main themes: Industrial production, business confidence, consumer confidence and composite leading indicators. The cycles are visualised as lines going counter clockwise for any given pair of countries. The regions of the graph represent a section in this cycle:
"Expansion – series is increasing and above 100;
Downturn – series is decreasing but above 100;
Slowdown – series is decreasing and below 100;
Recovery – series is increasing but below 100."
This plot offers a snapshot of several climatic variables for a station. This type of diagram is widely used by geographers, agronomists and other earth scientists.
Conditional density plot
This is a type of conditional plot where the distribution of a categorical variable is shown to change over the values of a continuous variables. In the example, the distribution of the variable indicating the distribution of the treatment outcome (for an arthritis blind trial conducted in 1988) is plotted against age.
This visualisation is used in conjunction with a regression in order to enable statistical inference. Conditional trees are useful for processes that take place in discrete stages.
A visualisation to display a variable distribution conditional on the distribution of at least a second variable. In the example, the number of breaks is displayed conditional on the type of wool and the level of tension.
Correlation matrix plot
This visualisation enables the visual representation of a correlation matrix. This particular example is about lawyers' ratings of state judges in the US Superior Court for 1977 on variables such as judicial integrity, demeanour, diligence and others.
A conditioning plot with splines added. It allows the visualisation of a variable distribution conditional on the values of the relevant groups of interest.
Effect plots work by identifying high-order terms in a generalised linear model, a statistical technique. Once these terms are identified fitted values are derived and plotted for the relevant groups.
Election Seat Calculator
Interactive tool that combines the power of a cartogram, a bar chart and a pie chart to explore possible outcomes of the 2010 election.
Funnel plot generated in excel by the Association of Public Health Observatories to illustrate prevalences.
Income levels of geo-demographic clusters.
Google Data Explorer
This interactive tool developed by Google offers a large amount of data, ranging from databases on public debt in Europe (in the screenshot) to education statistics in California. It is fully flexible so the user can select can choose between line, char graphs and maps, as well as the contextual information to be displayed.
Health profile, benchmarking performance of an area on a range of variables against the regional average.
High density regions
Plot of the probability density function with emphasis on the highest densities.
Histogram of rank distribution
Competitiveness Index in rural areas, 2006. The distribution curve in each graph hints at the overall performance and the spread of scores. The skew to the left or higher ranks on both the Overall Index of Competitiveness and the Input measures and the shorter tail confirming greater signs of health in rural local authorities on these measures, than the skew to the right or lower ranks and longer tail on the Output and Outcome measures.
Academic citations between journals (boxes) and fields (colours). 'Compass points' indicate citations for a specific journal - incoming (white arrow) and outgoing (black arrow).
Lattice confidence intervals
A simple graph that allows the presentation means and confidence intervals of several inter-related variables in an experiment.
Line chart with error limits
Line chart showing actual teenage conception rates (green line) in comparison to trajectory (red circles), 1997 to 2010.
Line chart: Curves
This is an example of the use of a line chart to plot mathematical functions.
The set of line graphs shows how demographics of students in American schools have evolved in the last two decades. Here, New York City schools is selected, compared with New York State schools (gray line).<br /><br />The blue and gray lines are almost parallel everywhere, which tells us that in terms of the change in demographic composition, New York City pretty much resembled New York State during this entire period. <br />However, in terms of demographic composition, rather than the change in composition, New York City schools are very different from the rest of the state, in that the proportion of white is lower by a third while that of minorities are much higher, especially black and Hispanic students.<br />State-wide (as well as city-wide), black and white students have been declining as a proportion while Hispanics and Asians have increased. <br />The extent of the change is immediately visible, Asians have jumped from 7% to 14% for example.
Line graph with converging lines
Income before housing costs of a lone Parent with 2 children under 11 in private rented housing compared with gross earnings (by benefit type).
The matrix chart divides the screen into a grid. Rows represent the values in one text column (e.g., political candidate) and columns represent another text column (e.g., states of the US). Each cell then shows a circle or bar that represents the value for its row/column combination (e.g., contribution to Hillary Clinton from New York).
Meta analysis plot
A chart used to summarise the findings of several studies about a common variable. It presents confidence intervals for each one of the studies considered. The example presents data on the effectiveness of silver sulfadiazine coating on venous catheters for preventing bacterial colonisation of the catheter and bloodstream infection.
Parallel Sets (ParSets)
Parallel Sets is a technique for visualizing categorical data. It helps you get away from representing individual data points, and instead show sets and subsets of items with certain combinations of criteria.<br />This example illustrates the people on board the Titanic. In a way, ParSets is a mix between parallel coordinates and treemaps/mosaic plots.
Probability line chart
Shows probability of defaulting on mortgage increase when amount owed surpasses value of property. 'Underwater' section shows loan-to-value ratio of more than 100%.
A complex graph for presenting detailed population about population growth. It integrates other visualisation types: Histograms, representation of the quantile regressions, and boxplots for the residual values.
This is a visualization technique developed to describe how performance varies across the 54 libraries in Leicestershire.
From the report “Creating RF Plots for all libraries allows us to see variation within and between the different sites. Whilst the seven largest libraries dominate in terms of absolute numbers, scaling the colour scheme by a power function allows us to see variation amongst the smaller quantities” (p. 2).
This is a circular histogram plot which displays directional data and the frequency of each class. It is widely used in geography, geology and other earth sciences.
Chart showing the proportion of an offence type within a particular CSP is significantly much higher, slightly higher, as expected, slightly lower or much lower compared to the profile of offences cross the whole county.
Scorecard at ward level
Joint Strategic Needs Assessment, Alcohol related harm admission rates (NI 39), wards benchmarked against the county average.
This type of graph is a modification of the histogram In the example, the distribution of the treatment outcome for an arthritis blind trial conducted in 1988 is plotted against age.
Music artists listened to over time, using data taken from last.fm
Stream graph variation
US Box Office data, showing takings and ranking each week. This visualisation is based on the data and original idea displayed <a href="/vis/id=282">here</a> but uses an alternative method to calculate and depict the areas on the graph.
A type of scatterplot, this visualisation allows the representation of three variables. In the example, the plot presents the proportions of employment in the primary, secondary and tertiary sectors for 12 European countries in 1978, 1986 and 1997.
Time series plot
This plot represents the outcome of a forecasting model a with simulated data set. The orange region show the confidence intervals for the forecast.
This is an interactive tool to visualize debate transcripts.<br />Click on the 'Load another transcript' button to choose a different transcript. The top section shows the distribution of some selected words within the text across a 'timeline' which goes from left to right. Each speech segment is the same width and the height of the small white bars show the number of occurrences of that word for that segment. You can add new words with the text box in the top right corner. You can remove existing words by clicking on them.<br /><br />Right below the word distribution graphs is a similar coloured set showing a spectral decomposition of the text based on who spoke and how much was said. In this case the bar heights give the amount of text for each segment. Click and drag the mouse left to right to move along the timeline and show the actual text for 3 consecutive segments.
Triangular plot area
This graph presents the ratios of the three variables as positions in a triangle.
Tukey's hanging rootogram
This visualisation is a variation of the concept of histograms, combining observed and predicted distributions in a simple way.
Urban Diary Aquarium
Saturday track record of three participants of the UrbanDiary project recorded in London. The data is plotted with the z-axis representing time of the day. The time frame in this case is 24 hours and starts from the bottom at 00h00 passing the time upwards to 24h00. Each participant has a time reference icon over the home location, where the journey starts and ends.
There is one female and two male participants, of whom the female and one male participant have family. The single male goes in to work just as normal although it is a Saturday and returns home in the afternoon to do some sport activity locally where he lives. His journey starts at 08h23, ends at 17h19 and travels around 15 km. The woman does some local activities with her family and travels in to her workplace briefly later on. She starts her day at 07h01, ends at 20h09, and covers 30 km wile traveling. The Second male participant spends his day in the local area. This journey starts at 11h45, ends at 18h53, and measures 5 km.
This graph is a modification of the boxplot that enables the representation of densities and other distributions. The image shows the boxplot together with its possible modifications.
World Bank Data Visualizer
The World Bank has created a complex visualisation tool to make available 49 indicators for 209 countries and 18 aggregates from 1960-2007. Data includes social, economic, financial, information & technology, and environmental indicators. The visualisation is completely customizable bubble chart in the spirit of 'gapminder' and the user selects the x and y axis dimensions as well as the variable that determine the size of the bubbles and the time point to be displayed.