23 Communicating insights

This chapter is derived from the Australian Bureau of Statistics ^[1]; licensed under a Creative Commons Attribution 4.0 International licence.

Presenting the results in a clear and logical format to the client is one of the most important tasks for the person managing the survey. When presenting results, the format of the presentation should be tailored to address the aims and objectives of the survey and to satisfy the potential users of the results. Consideration should be given to the level of statistical understanding of the clients and users, particularly in regard to statistical terminology. The presentation needs to be effective, easy to understand and convey the main features of the data.

Written Reports

When presenting the data, some form of a written report is essential. The report should convey the main features clearly and follow a logical progression, use as little jargon as possible, provide insight into the data and make the results as interesting as possible. As the author of the report, you should convey specific messages rather than generalised information. You should also put forward theories to explain the findings and encourage the users to further explore the data. If appropriate, you may need to include recommendations.

The contents of the report and its balance of words, tables and graphs will naturally depend on the topic, the results and the likely readers. Graphs and tables convey complex information clearly and can be used to add variety. At all times it should be remembered that the report is written to be read, and so needs to make sense and be understandable.

A survey report generally covers:

Introduction

The introduction states the purpose and aims of the survey and the aims of the report; gives the background to the research; defines terms and concepts; and states whether the survey is testing an hypothesis or is exploratory.

Methodology

The methodology describes the method of sampling and information on the survey population, as well as how the data was analysed and the statistical procedures which were used.

Findings and Analysis

The findings and analysis section is the main part of the report which deals with details of the sample numbers, response rates, results and interpretation of tabulations etc. and discusses possible courses of action.

Conclusions and Recommendations

The conclusions summarise the major findings of the report and answers questions posed in the introduction. The recommendations outline what actions are indicated on the basis of the conclusions.

Appendices and References

The appendices consist of items which may be useful to the reader (e.g. the questionnaire) but not essential to the report. References list the books, journals and papers referred to in the study.

Remembering that the report is likely to serve as a basis for discussion, some other important considerations are the title, use of headings and sub-headings, the colour and design of the cover and the overall appearance of the report – it should stimulate the reader’s interest.

Statistical Representation

The manner in which the results are presented will depend on the data and the types of descriptive statistics required. Tables and graphs are the most common form of presentation but other types are available. In general, tables are more detailed – showing the actual values, whereas graphs are more useful in showing relationships – concentrating on the form, shape and movement of the data. Graphs are particularly useful in representing the change in the value of a data item over a period of time. Usually, either a graph or a table will be sufficient to represent a set of data.

Tables

Tables are the most common form of statistical presentation. Tables present additional information which cannot be shown in general text. A good table is one in which patterns and exceptions stand out when looking at the table, followed by a small paragraph commenting on the table. Tables are usually only used to present a few values as they become difficult to comprehend if they involve too many numbers.

Tables should have clear headings. Some other useful guidelines are:

• to round data to 4 or 5 significant figures which makes the data easier to see and manipulate;
• reading down is easier than reading across a row, especially for a large number of items;
• row and column averages or percentages may help the reader interpret the data – widely spaced columns are difficult to compare and should be avoided, and
• totalling rows and/or columns is usually helpful

Graphs

We can also use a sequence of simple graphs to tell a story about the data and to give insight into findings. This can be supported by an explanatory paragraph.

Graphs are a visually attractive way of presenting data. They maintain the interest of the readers and encourage them to think about the data. Although the amount of information which can be presented is limited, graphs often reveal or highlight “hidden” facts in complex data. Trends and relationships are more clearly grasped from a graph rather than a table or text and are therefore better remembered by the reader. However, graphs are not always necessary and should only be used where it is appropriate. Keep in mind that the reader may not be familiar with the data and therefore you need to include sufficient information on the graph to explain the data.

Constructing Graphs

• Titles: A title is essential and is best placed at the top. It should indicate the “what, where and when” of the graph as concisely as possible and should be larger than the lettering on the graph itself
• Scales: the horizontal scale usually measures the time unit where a graph is over a period of time, and the vertical scale measures the variable under consideration. Where possible the vertical scale should begin at zero
• shading and colouring can be added to create visual emphasis;
• both axes should be marked and named with scales and units;
• all parameters and variables should be defined as concisely as possible;
• a legend may be necessary, particularly for detailed graphs with shading and/or colouring;
• labels should be used if more than one variable is plotted on the same graph; and
• footnotes may be used to explain unusual features such as breaks in the series.

Types of Graphs

The decision as to which type of graph to use depends on the type of data being presented. The following are some of the types of graphs that could be used:

• Line or Curve Graphs

These graphs are used when emphasis on the movement rather than the size of the data item or when several series are being compared. These types of graphs show variations in the data plotted over a period of time.

• Bar or Column Graph

This type of graph depicts numerical values over a given variable. The value is represented by the height of the column. This type of graph is especially effective for showing large changes from one period to the next.

• Grouped Columns/Bars

These graphs compare different categories on the same graph. Groups of columns, with each column in the group representing a different category, are plotted on the same axis.

• Pie Chart

These charts are used for comparison (in percentage terms) of components. The components can be compared with each other and the contribution they make with the whole. These graphs are best used when there is a small number of categories.

• Map

A map is used to show the boundaries of areas. Various shadings for different regions can show how the value of variable changes between locations.

• Other Graphs

Some other graphs which are available include Index, Pictogram, Surface Chart, Cumulative Curve, Deviation Line, Sliding Bar Chart, Dot Chart, Population Pyramid, Map Chart, Stacked Bar and Scatter Diagram.

Other Forms of Presentation

Oral Presentations

Depending on the circumstances (users, type of data, results), a written report may be inadequate or may need to be supplemented. Oral presentation of the results of a survey is often neglected as an important means of conveying information. Whereas a written report provides great detail with a wide range of results, an oral session can only emphasise a few major points. However, this can often be most suitable depending on the audience. As with a written report, the poor presentation may cause the survey results to be rejected. The spoken word and visual aids can have a great impact on an audience. The presenter therefore should be aware of who the presentation is aimed at and know what survey results may be contrary to existing ideas.

Posters

A poster is one way to attract attention but only one direct statement should be made. The message must be noticeable at a glance and the poster itself must be attractive to encourage possible users to inspect it.

Panel Exhibits

A panel exhibit is an extension of the poster presentation. This type of presentation gives more details and expands several main ideas. Again it is important that the panels be colourful and attractive.

Charts (often referred to as an infographic)

A chart may be appropriate depending on the data. A chart is an outline map that can contain photographs, words, figures, graphs, diagrams, maps, symbols, illustrations, etc (eg. a weather chart).

The infographic Generation Alpha created by McCrindle 2021 is licensed under  a  Creative Commons Attribution 4.0 International Licence ^[2]

Videos

The use of videos and television can provide an additional means of communication of the survey results.

Conclusion

It is important to present data well. If we have gone to the effort, time and expense of undertaking a study, then we have to ensure that we present the data in a clear, logical way. We must consider the use of text, tables and diagrams to construct a document that is useful and understandable. The ultimate aim of any presentation is to inform the user of the results of the research in a way that can be used to promote informed decision making.