The importance of summarising raw data in psychological research

In psychological research, raw data from experiments or studies often consists of unprocessed scores or observations, such as test results from participants. This data needs to be summarised to reveal patterns and draw meaningful conclusions. Summarising helps researchers understand typical values and how much variation exists, which is essential for comparing groups or testing hypotheses.

Why summarise data:

• Raw data alone is hard to interpret, as it does not highlight averages or differences.
• Summaries allow for comparisons, such as between experimental conditions.
• They support statistical testing and help identify if results are due to chance or real effects.

Measures of central tendency

Measures of central tendency provide a single value that represents the 'centre' of a data set, giving an idea of a typical score. These are useful in psychology for summarising participant performance in studies, like average recall in memory experiments. There are three main types: mean, median, and mode.

Mean

The mean is the arithmetic average of a set of scores. It is calculated by adding all scores and dividing by the number of scores. This measure uses every value in the data set, making it sensitive to all data points.

Formula for the mean:

$\text{Mean}=\frac{\text{sum of all scores (}\mathrm{\Sigma }\text{)}}{\text{number of scores (}n\text{)}}$

Where:

• Sum of all scores (Σ) = Total when all values are added together
• Number of scores (n) = Count of data points in the set

Strengths and limitations of the mean:

• Strengths - Accounts for every score, providing a precise average.
• Limitations - Can be distorted by extreme values, known as outliers, which are unusually high or low scores that skew the result.

Median

The median is the middle value in a data set when scores are arranged in ascending order. It is less affected by outliers, making it useful for skewed data in psychological studies.

How to calculate the median:

1. Arrange scores from lowest to highest.
2. If the number of scores is odd, the median is the middle one.
3. If even, average the two middle scores.

Strengths and limitations of the median:

• Strengths - Resistant to outliers and easy to compute.
• Limitations - Does not use all data values, so it may ignore important information.

Mode

The mode is the most frequently occurring score in a data set. It is straightforward to identify and useful for categorical data in psychology.

To find it, count the frequency of each score and select the one with the highest count. A data set can be bimodal if two scores occur equally often.

Strengths and limitations of the mode:

• Strengths - Simple and highlights common trends.
• Limitations - May not exist if no score repeats, or may not represent the data well if frequencies are similar.

Worked example - Calculating measures of central tendency

In a psychology study on attention spans, participants completed a task with distractions (condition A) and without (condition B). The raw scores (in minutes) are:

Condition A: 1, 3, 4, 5, 3, 6, 2, 4, 5, 9

Condition B: 10, 11, 12, 13, 10, 14, 9, 11, 12, 15

Calculate the mean, median, and mode for each condition.

Step 1: Calculate the mean for condition A

• Sum (Σ) = 1 + 3 + 4 + 5 + 3 + 6 + 2 + 4 + 5 + 9 = 42
• n = 10

$\text{Mean}=\frac{42}{10}=4.2$

Step 2: Calculate the mean for condition B

• Sum (Σ) = 10 + 11 + 12 + 13 + 10 + 14 + 9 + 11 + 12 + 15 = 117
• n = 10

$\text{Mean}=\frac{117}{10}=11.7$

Step 3: Calculate the median for condition A

• Ordered scores: 1, 2, 3, 3, 4, 4, 5, 5, 6, 9
• Middle two: 4 and 4

Median = (4 + 4) / 2 = 4

Step 4: Calculate the median for condition B

• Ordered scores: 9, 10, 10, 11, 11, 12, 12, 13, 14, 15
• Middle two: 11 and 12

Median = (11 + 12) / 2 = 11.5

Step 5: Identify the mode for each condition

• Condition A: 3, 4, and 5 each appear twice (multimodal)
• Condition B: 10, 11, and 12 each appear twice (multimodal)

Step 6: Interpretation

The higher mean (11.7) and median (11.5) in condition B suggest better attention without distractions. The mode is less informative here due to multiple frequencies.

Measures of spread

Measures of spread describe how much scores vary or 'spread out' from the central value, which is important in psychology for understanding consistency in data. The two key measures are range and standard deviation.

Range

The range is the simplest measure of spread, showing the difference between the highest and lowest scores. It gives a quick sense of data variability but can be heavily influenced by outliers.

Formula for range:

$\text{Range}=\text{highest score}-\text{lowest score}$

Strengths and limitations of range:

• Strengths - Easy to calculate.
• Limitations - Ignores how scores are distributed and is sensitive to extremes.

Standard deviation

Standard deviation (often abbreviated as SD or sd) measures the average distance of scores from the mean, providing a more comprehensive view of spread. A low SD indicates scores cluster closely around the mean, while a high SD shows greater variation. In psychological research, it helps assess if results are consistent across participants.

How to calculate standard deviation:

1. Find the mean.
2. Subtract the mean from each score to get deviations.
3. Square each deviation, average them, and take the square root.

Strengths and limitations of standard deviation:

• Strengths - Accounts for all data and is useful for inferential statistics.
• Limitations - Complex to compute manually and assumes normal distribution.

Worked example - Calculating measures of spread

Using the attention span data from the previous example:

Condition A scores: 1, 3, 4, 5, 3, 6, 2, 4, 5, 9 (mean = 4.2)

Condition B scores: 10, 11, 12, 13, 10, 14, 9, 11, 12, 15 (mean = 11.7)

Calculate the range and standard deviation for each (SD values can be approximated for this example).

Step 1: Calculate range for condition A

Highest = 9, lowest = 1

$\text{Range}=9-1=8$

Step 2: Calculate range for condition B

Highest = 15, lowest = 9

$\text{Range}=15-9=6$

Step 3: Calculate standard deviation for condition A

Deviations from mean (4.2): -3.2, -2.2, -1.2, 0.8, -1.2, 1.8, -2.2, -0.2, 0.8, 4.8

Squared and averaged, then square root gives SD ≈ 2.25

Step 4: Calculate standard deviation for condition B

Deviations from mean (11.7): -2.7, -1.7, 0.3, 1.3, -1.7, 2.3, -2.7, -0.7, 0.3, 3.3

Squared and averaged, then square root gives SD ≈ 1.89

Step 5: Interpretation

Condition A has a larger range (8) and SD (2.25) than condition B (range 6, SD 1.89), indicating more variability in attention spans with distractions. This suggests distractions lead to less consistent performance.