Presentation of Quantitative Data (AQA A-Level Psychology): Revision Notes
Presentation of Quantitative Data
Quantitative data needs to be presented clearly so that patterns, trends and relationships can be identified and understood. There are several methods available for displaying numerical information, each with specific uses and advantages.
Introduction to data presentation
Presentation and display of quantitative data refers to the various methods used to show numerical scores and findings from research studies. This involves transforming raw data into visual or tabular formats that make it easier to interpret results and identify patterns.
Worked Example: Converting to Percentages
Data can be converted into percentages by multiplying by a factor of 100. For instance, a test score of 67 out of 80 would be calculated as:
Correlational data from studies can be displayed using correlation coefficients, showing positive, negative or no correlation between variables. This data is typically presented using scattergrams to illustrate both the strength and direction of relationships between variables.
Scattergrams are particularly powerful because they allow researchers to visualise not just whether a correlation exists, but also how strong that relationship is and whether there are any outliers in the data.
Graphs and charts
Visual representations make data more accessible and allow viewers to quickly identify patterns and trends that might not be obvious in raw numerical form.
Bar charts
Bar charts are designed for presenting non-continuous (categorical) quantitative data. They display information by comparing different categories, such as comparing performance between males and females.
Key features of bar charts include:
- Categories are positioned along the horizontal x-axis
- Bars should be the same width and separated by spaces
- The spaces indicate that the x-axis variable is not continuous
- Can display totals, means, percentages or ratios
- Can show two values together for direct comparison
Bar charts are particularly useful when you need to compare distinct groups or categories where the data points are separate and unconnected.
Histograms
Histograms are used specifically for continuous quantitative data, such as test scores or measurements. While they appear similar to bar charts, there are important differences.
Key Difference from Bar Charts: The most critical distinction is that histograms have no spaces between bars because the data is continuous, while bar charts have spaces between bars because the data represents separate categories.
Distinctive characteristics of histograms:
- Continuous scores are placed along the x-axis
- Frequency is shown on the y-axis (vertical)
- No spaces between bars because the data is continuous
- Each bar should have equal width representing equal category intervals
- The continuous nature means each value flows into the next
Histograms are ideal for showing the distribution pattern of continuous variables and identifying whether data follows a normal distribution.
Frequency polygon (line graph)
A frequency polygon presents continuous data by connecting points with lines, creating a graph that shows the shape of the data distribution.
Frequency polygons are created by plotting points at the midpoint of what would be the top of each bar in a histogram, then connecting these points with straight lines.
Advantages of frequency polygons:
- Allow comparison of two or more frequency distributions on the same graph
- Clearly show the shape of the data distribution
- Can identify trends over time or between groups
- Take up less visual space than histograms when comparing multiple datasets
The line connects the midpoint of what would be the top of each bar in a histogram, creating a smooth curve that represents the data pattern.
Pie charts
Pie charts display the frequency of different categories as percentages of the whole dataset. The circle is divided into sections, with each section representing a different category.
Essential features of pie charts:
- Each section is colour-coded for easy identification
- Percentages are usually indicated for each section
- The entire circle represents 100% of the data
- Most effective when there are relatively few categories
- Good for showing proportional relationships within a dataset
Pie charts work best when you want to emphasise how different parts contribute to the whole, rather than comparing specific values between categories. They become difficult to read when there are too many small sections.
Tables
Tables provide a numerical method for presenting quantitative data in an organised format. Unlike data tables that show raw scores, results tables summarise the main findings from studies.
Results tables typically include:
- Data totals for different groups or conditions
- Measures of central tendency (mean, median, mode)
- Measures of dispersion (range, standard deviation)
- Number of participants in each group
- Sometimes percentages alongside raw numbers
Tables are particularly valuable because they present precise numerical values that can be easily compared, while graphs provide visual approximations that show general patterns and trends.
Distributions
Distributions describe the different patterns that quantitative data can follow, based on how values are spread and how frequently they occur.
Normal distribution
Normal distribution represents data that is evenly spread on both sides of the mean, creating a symmetrical, bell-shaped curve when plotted on a graph.
Characteristics of normal distribution:
- Most scores cluster around the mean value
- Equal numbers of scores fall above and below the mean
- Fewer scores appear at the extreme ends (very high or very low)
- Creates a symmetrical bell-shaped curve
- The mean, median and mode are all at the same point
Methods for Checking Normal Distribution:
- Visual examination - observing whether most scores cluster around the mean
- Calculating measures of central tendency - checking if mean, mode and median are similar
- Plotting frequency distribution - creating a histogram to see if it forms a bell-shaped curve
When data is not normally distributed, it is described as skewed distribution, where scores are not evenly spread on both sides of the mean.
Key Points to Remember:
- Bar charts are for categorical data with separated bars, while histograms are for continuous data with connected bars
- Frequency polygons allow easy comparison of multiple distributions on one graph
- Pie charts show proportional relationships and work best with fewer categories
- Tables provide precise numerical values while graphs show visual patterns
- Normal distribution creates a symmetrical bell curve with most scores around the mean