Concept Architecture
Concept
Theoretically, Standard Deviation is a statistical measure of dispersion that quantifies the average spread of observations around their mean. It is the square root of the variance and is expressed in the same units as the original data, making it directly interpretable. Standard deviation is fundamental to probability theory, statistical inference, estimation, and modelling because it characterises variability within a population or sample and underpins many statistical methods.
Mathematically, standard deviation is defined as the square root of the second central moment of a distribution. Population standard deviation is calculated using all observations in the population, whereas sample standard deviation applies Bessel's correction to provide an unbiased estimate of population variability. Under the Normal distribution, standard deviation determines the spread of observations around the mean and forms the basis of z-scores, confidence intervals, hypothesis tests, and effect size measures.
In practice, standard deviation is calculated during descriptive statistical analysis and is routinely reported for continuous variables in health economics, including healthcare costs, quality-adjusted life years, utility scores, treatment outcomes, and resource utilisation. It is also used in sample size calculations, regression modelling, probabilistic sensitivity analysis, and simulation models.
Purpose
Used to quantify variability within continuous data, summarise dispersion, estimate uncertainty, support statistical inference, and provide a fundamental measure of variability in health economic analyses.
Mathematical Formulae
Primary Formula
Population standard deviation:
� = �[(1/N) ? ?(x? ? ?)�]
where:
- � = population standard deviation
- ? = population mean
- N = population size
Supporting Formulae
Sample standard deviation:
s = �[(1/(n ? 1)) ? ?(x? ? x?)�]
Variance:
�� = (1/N) ? ?(x? ? ?)�
Sample variance:
s� = (1/(n ? 1)) ? ?(x? ? x?)�
Related Mathematical Methods
- Variance
- Coefficient of Variation
- Z-score
- Standard Error
- Confidence Interval
- Normal Distribution
- Descriptive Statistics
- Mean Squared Error
Example
Annual healthcare costs are recorded for five patients:
�6,500, �7,200, �7,800, �8,100 and �9,400
The sample mean is:
�7,800
The sample variance is:
1,165,000
The sample standard deviation is:
s = �1,165,000
= �1,079.35
This indicates that individual healthcare costs typically vary by approximately �1,079 around the sample mean.
Excel Implementation
| Function | Example Formula | Health Economics Application |
|---|---|---|
| STDEV.S | =STDEV.S(B2:B101) | Calculate the sample standard deviation of healthcare costs or QALYs. |
| STDEV.P | =STDEV.P(B2:B101) | Calculate the population standard deviation when all observations are available. |
| VAR.S | =VAR.S(B2:B101) | Calculate the sample variance before taking the square root. |
| AVERAGE | =AVERAGE(B2:B101) | Calculate the sample mean used in standard deviation estimation. |
| SQRT | =SQRT(VAR.S(B2:B101)) | Derive the standard deviation from the sample variance. |
VBA (Optional)
Automate calculation of standard deviations and descriptive summary statistics across multiple health economic outcome variables.
Sources
- Fisher RA. Statistical Methods for Research Workers.
- Casella G, Berger RL. Statistical Inference.
- Altman DG. Practical Statistics for Medical Research.
- Mood AM, Graybill FA, Boes DC. Introduction to the Theory of Statistics.
- Briggs A, Claxton K, Sculpher M. Decision Modelling for Health Economic Evaluation.
- Drummond MF, et al. Methods for the Economic Evaluation of Health Care Programmes.
- NICE Health Technology Evaluation Manual.
Related Concepts (2)
Library
Publications
1
Bayesian Methods in Health Economics — Gianluca Baio, 1st Edition ed., 2012 (Chapman & Hall / CRC Press)
An overview of Bayesian statistical methods for the analysis of health economic data, covering economic evaluation concepts, statistical cost-effectiveness analysis, Bayesian computation and MCMC, and applied health economic evaluation.
BookView source →
Frequently Asked Questions (6)
What is the standard deviation?
A dispersion measure representing the average distance of data points from the mean, calculated as the square root of the variance.
Source: Casella G, Berger RL. Statistical Inference. 2nd ed. Duxbury; 2002.
What does the standard deviation tell us about the spread of data?
The standard deviation summarises how far, on average, the values in a dataset lie from their mean, giving a measure of spread in the same units as the data themselves. A small standard deviation means the observations cluster tightly around the average, while a large one means they scatter widely. It is the square root of the variance, which makes it more interpretable than the variance because it shares the data's units. How widely values spread around the mean is what it captures. Kirkwood and Sterne (2003) describe this measure.
Source: Kirkwood & Sterne 2003
How is the standard deviation calculated?
The standard deviation is calculated by taking the differences between each value and the mean, squaring them, averaging the squared differences to obtain the variance, and then taking the square root to return to the original units. So the standard deviation is calculated as the square root of the variance, which averages the squared deviations from the mean, meaning it uses all the data and gives greater weight to values far from the mean, and this is why it is sensitive to outliers, with the square root step bringing the measure back to the scale of the data for easier interpretation.
Source: Casella & Berger 2002
What does the standard deviation indicate?
The standard deviation indicates the amount of variability or spread in a dataset around its mean: a small standard deviation means the values cluster closely around the mean, while a large one means they are widely dispersed. For approximately normal data, it also indicates the proportion of values within a given distance of the mean. So the standard deviation indicates how spread out the data are, which conveys the consistency or variability of the values, and for normal distributions it has a precise interpretation, with known percentages of the data lying within one, two, and three standard deviations of the mean.
Source: Casella & Berger 2002
How does the standard deviation relate to the variance?
The standard deviation relates to the variance as its square root: the variance is the average of the squared deviations from the mean, in squared units, and the standard deviation is its square root, expressed in the original units of the data. So the standard deviation and the variance measure the same variability, differing in scale, with the variance in squared units and the standard deviation on the data's scale, which is why the standard deviation is usually preferred for reporting and interpretation, being directly comparable to the data and the mean, while the variance is often used in calculations and theory.
Source: Casella & Berger 2002
When is the standard deviation an appropriate measure?
The standard deviation is an appropriate measure of dispersion when the data are reasonably symmetric and free of extreme outliers, since it then represents the typical spread well and uses all the data; it is less suitable for skewed data or data with outliers, which inflate it. So the standard deviation is appropriate for symmetric, roughly normal data, where it is an efficient and informative measure of variability and pairs naturally with the mean, whereas for skewed or outlier-prone data the interquartile range is often preferred, since the standard deviation can be distorted by extreme values and give a misleading impression of the spread.
Source: Casella & Berger 2002
Trust Record
Verified by Dr Darrin Baines
British health economist
Professional identity: darrinbaines.org
Verification date: 25 Dec 2025
Content version: 1.0.0
Canonical Identity
- Persistent URI
- https://healtheconomics.wiki/concept/standard-deviation
- Term code
- HE-ES-SA-199
Stable URI · Machine-readable · Resolvable · CC BY 4.0