Statistical Methods

Statistical methods help us identify patterns, trends, and relationships in data, test hypotheses and assess the significance of results. They are essential for analysing data, making predictions and drawing meaningful conclusions.

There are four main ways to conduct statistical methods:


1. Descriptive Statistics

Describes and summarises the key features of a dataset in an informative and meaningful way. Understanding the basic characteristics of data before deeper analysis.

Key measures include:

  • Measures of central tendency - mean, median, and mode, showing where the centre of the data lies.
  • Measures of dispersion - range, variance and standard deviation, showing how spread out the data is from the centre.
  • Measures of distribution shape - skewness and kurtosis- are used to describe the asymmetry and peakedness of a distribution.
  • Frequency distributions - showing how often values occur, usually visualised with histograms, bar charts or frequency tables.

Example: For the dataset
66, 34, 12, 98, 77, 91, 13, 66, 90, 54
The mode is 66.


2. Inferential Statistics

Inferential statistics use sample data to make predictions or inferences about a larger population, accounting for uncertainty and sampling errors.

Common techniques include:

  • t-test - compares the means of two groups.
  • ANOVA - compares means across three or more groups and determines if there is a significant difference.

Example: A company wants to test whether income differs by age group. An ANOVA test could compare income across age brackets such as 18-24, 25-34, 35-44 and 45+.


3. Parametric Methods

This statistical analysis method assumes the data follows a specific distribution or pattern. This allows the use of mathematical models and well-defined statistical tests to analyse and draw conclusions from the data.

Example: Predicting an individual's future income based on two variables - age and current income - using a regression model.


4. Nonparametric Methods

These methods make fewer assumptions about the underlying distribution of data. It can be used when the data does not meet the assumptions of parametric methods, when the data is not normally distributed or when the sample sizes are small.

Common techniques:

  • Wilcoxon signed-rank test compares two paired samples, e.g., measuring the treatment's effect on patient health.
  • Kruskal-Wallis test - compares medians across three or more groups without assuming a normal distribution, e.g., testing whether income levels affect anxiety rates.

In summary:
Statistical methods, whether descriptive, inferential, parametric, or nonparametric, provide the tools to move from raw numbers to meaningful insights. Choosing the correct method depends on your data type, distribution, and research question.

Author:
Claudina Mukangabo
Powered by The Information Lab
1st Floor, 25 Watling Street, London, EC4M 9BR
Subscribe
to our Newsletter
Get the lastest news about The Data School and application tips
Subscribe now
© 2025 The Information Lab