1500.0 - A guide for using statistics for evidence based policy, 2010  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 20/10/2010  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All  
Contents >> Communicate statistical findings


Being able to turn data into information or communicate statistical information accurately is vital for effective decision-making. The following section provides an overview of writing statistical commentary and using tables and graphs to communicate statistical findings.

Writing about data

Writing about statistics provides an opportunity to present your analysis in a way that tells a story about the data. In effect, statistical writing can bring data to life, making it real, relevant and meaningful to the audience. When communicating statistical information it is important to ensure that the information presented is clear, concise and accurate. It is also important to provide contextual information and to draw out the main relationships, causations and trends in the data.

The following provides some useful tips to follow when writing about statistics:

    • describe the context within which the topic sits

    • present the complete picture to avoid misrepresentation of the data

    • accurately convey the main findings clearly and concisely

    • include definitions to support correct interpretations of the data

    • where necessary include information on how the data was collected, compiled, processed, edited and validated

    • include information on data quality and data limitations

    • use plain, simple language and where possible minimise the use of jargon

    • ensure information and data are accurate

    • where possible avoid using data that have data quality concerns

    • use tables and graphs to present and support your written commentary.

The following tips can help you ensure that statistical information is accurate, and easy to read and understand:

    • avoid subjective language or descriptions (e.g. slumped to 45%)

    • statements should be backed up by the data (e.g. a greater proportion of 0-14 year olds identified as Indigenous than 15-24 year olds (5.8% compared to 4.1%))

    • use proportions to improve flow and ease of comprehension (e.g. nearly three quarters (73%) of females)

    • use rates when comparing populations of different sizes (e.g. age specific death rate, crime rates)

    • a percentage change (the relative change between two numbers) is different from a percentage point change (the absolute difference between two percentages)

    • be careful of percentage change and small numbers (e.g. the region experiences a 100% increase in the number of reported crimes (from two reported incidences in 2002 to four reported incidences in 2003))

    • figures should always be written as numbers (e.g. 45% instead of forty-five percent)

    • comparison of large numbers can be improved by using a different scale

    • rounded figures are used in text and raw data in tables.

Using tables, graphs and maps to communicate statistical findings

Whether writing a report or making a presentation, the story should be told by your evidence. A simple table, graph or map can explain a great deal, and so this type of direct evidence should be used where appropriate. However, if a particular part of your analysis represented by a table, graph or map does not add to or support your argument, it should be left out.

While representing statistical information in tables, graphs or maps can be highly effective, it is important to ensure that the information is not presented in a manner that can mislead the reader. The key to presenting effective tables, graphs or maps is to ensure they are easy to understand and clearly linked to the message. Ensure that all the necessary information required to understand what the data is showing is provided, as the table, graph or map should be able to stand alone.

Tables, graphs and maps should:

    • relate directly to the argument

    • support statements made in the text

    • summarise relevant sections of the data analysis

    • be clearly labelled.

Using tables to communicate statistical findings

An effective table does not simply present data to the audience, it supports and highlights the argument or message being presented in the text, and helps to make the meaning of that message clear, accessible, and memorable for the audience.

The following checklist may be useful when creating tables:

    • label each table separately

    • use a descriptive title for each table

    • label every column

    • provide a source if appropriate

    • provide footnotes with additional information required for understanding table

    • minimise memory load by removing unnecessary data and minimising decimal places

    • use clustering and patterns to highlight important relationships

    • use white space to effect

    • order data meaningfully (e.g. rank highest to lowest)

    • use a consistent format for each table.

It is also very important not to present too much data in tables. Large expanses of figures can be daunting for a reader, and can actually obscure your message.

Using graphs to communicate statistical findings

Graphs are also a useful tool for presenting data. They provide a way to visually represent and summarise complex statistical information. They are especially useful for revealing patterns and relationships that exist in the data and for showing how things may have changed over time. A well placed graph may also be useful in improving readability by breaking up large chunks of text and tables.

There are a range of different graphs used for presenting data, such as bar graphs, line graphs, pie graphs and scatter plots. It is important to use the right type of graph for presenting the information.

Effective graphs are easy to read and clearly present the key messages. Points to consider when using graphs for presentation purposes are as follows.

    Title: Use a clear descriptive title to properly introduce the graph and the information it contains.

    Type of graph: Choose the appropriate graph for your message, avoid using 3D graphs as they can obscure information.

    Axes: Decide which variable goes on which axis, what scale is most appropriate.

    Legend: If there is more than one data series displayed, always include a legend, preferably within the area of the graph, to describe them.

    Labels: All relevant labels should be included, including thousands or percentages, and the name of the x-axis if required.

    Colour/shading: Colours can help differentiate, however, know what is appropriate for the medium you’re using.

    Footnotes: These can help communicate anything unusual about the data, such as limitations in the data, or a break in the series.

    Data source: Where appropriate, provide the source of data you’ve used for the graph.

    3/4 Rules: For readability, it’s generally a good rule of thumb to make the y axis 3/4 the size of the x-axis.

Using maps to communicate statistical findings

A map can often convey a message more concisely than words. Using maps to present statistical information about a geographic area can provide a quick overview of what a set of data is showing and highlight the patterns and relationships in different regions.

When presenting statistical information in a map format, ensure that you label each map correctly; include a legend; provide a scale; and include all contextual information to assist with understanding the data, and any limitations there may be.

The fundamental components that together make up a good map, include:

    • prominent, clear title

    • clear, self-explanatory legend

    • neat, uncluttered layout

    • if a thematic map, unobtrusive but useful topographic detail

    • explanation of the detail, accuracy and currency of the data

    • easily understood scale bar

    • acknowledgement of whom produced the map.

The ABS provides a number of products for thematically mapping census statistics for a chosen location. The maps illustrate the distribution of selected population, ethnicity, education, family, income, labour force, and dwelling characteristics.

Previous PageNext Page