✦ScienexySCIENCE KNOWLEDGE LIBRARY
reference · SCI-REF-006-109

Scientific Data, Graphs, Tables and Statistical Representation

Introduces the symbols and conventions used to organize, summarize, visualize, and statistically analyze scientific data. It covers tables, graph axes, variable notation, descriptive statistics, distributions, regression, correlation, and the presentation of uncertainty.

x̄ = (Σxᵢ)/n; s = √[Σ(xᵢ − x̄)²/(n − 1)]; SE(x̄) = s/√n

Explanation

Scientific data notation provides a standardized way to record observations, describe variables, summarize distributions, and communicate relationships between quantities. Data tables organize observations into rows and columns, with clear headings, variable names, units, and appropriate precision. Graphs represent relationships visually using axes, scales, markers, lines, and error bars. The independent variable is commonly placed on the horizontal axis and the dependent variable on the vertical axis when that arrangement matches the study design. Axis labels should identify the quantity and its unit, often in the form Quantity / unit, such as time / s or temperature / K. Descriptive statistics summarize a dataset. The arithmetic mean is represented by x̄ for a sample and often by μ for a population. The sample median is commonly denoted by a contextual symbol or described directly. Sample standard deviation is represented by s, while population standard deviation is represented by σ. Variance is represented by s² for a sample and σ² for a population. The sample size is usually denoted by n, while population size may be denoted by N. The standard error of the sample mean is commonly s/√n under independent sampling assumptions. Probability is often represented by P, and a probability density function by f(x). A normal distribution is represented by N(μ, σ²), where μ is the mean and σ² is the variance. Correlation coefficients describe the strength and direction of association, with Pearson's correlation coefficient commonly denoted by r for sample data and ρ for a population. Linear regression is often written y = β₀ + β₁x + ε, where β₀ is the intercept, β₁ the slope, and ε the error term. R² represents the coefficient of determination in common regression settings. Error bars may represent standard deviation, standard error, confidence intervals, or another uncertainty measure; the graph legend must state which interpretation applies. Statistical significance, confidence intervals, effect sizes, and practical significance are distinct concepts and should not be conflated.

Variables

SymbolMeaningUnit

xᵢ

The ith observation in a dataset

Same as the measured variable

x̄

Sample arithmetic mean

Same as the observations

μ

Population mean

Same as the observations

s

Sample standard deviation

Same as the observations

σ

Population standard deviation

Same as the observations

n

Number of observations in a sample

Dimensionless count

SE

Standard error of an estimator, commonly the sample mean

Same as the estimator

r

Sample Pearson correlation coefficient

Dimensionless

R²

Coefficient of determination in regression

Dimensionless

Example or application

A worked example has not yet been added.

Definition

Scientific data and statistical notation is the system of symbols, labels, mathematical representations, and graphical conventions used to organize, analyze, summarize, and communicate observed or calculated data.

Purpose

Provides common conventions for organizing scientific observations, summarizing datasets, displaying relationships, and evaluating statistical patterns.

Importance

Consistent data notation improves the readability, transparency, reproducibility, and interpretability of scientific results. Proper statistical representation helps researchers distinguish observed variation, uncertainty, correlation, and model performance.

Table And Graph Conventions

ElementPurposeSymbol

Table title

Describes the dataset or measurement being presented.

Column heading

Identifies the variable and, where relevant, its unit.

Horizontal axis

Often represents an independent or explanatory variable.

x

Vertical axis

Often represents a dependent or response variable.

y

Error bar

Displays a specified uncertainty or variability interval.

Context-dependent

Legend

Identifies data series, markers, symbols, and plotted conditions.

Scale

Defines how numerical values map to positions on an axis.

Descriptive Statistics Notation

StatisticSymbolFormula

Sample mean

x̄

x̄ = Σxᵢ/n

Population mean

μ

μ = Σxᵢ/N

Sample variance

s²

s² = Σ(xᵢ − x̄)²/(n − 1)

Population variance

σ²

σ² = Σ(xᵢ − μ)²/N

Sample standard deviation

s

s = √s²

Population standard deviation

σ

σ = √σ²

Standard error of sample mean

SE(x̄)

SE(x̄) = s/√n under the usual independent-sampling assumptions

Range

R

R = x_max − x_min

Probability And Distribution Symbols

SymbolMeaning

P(A)

Probability of event A.

P(A|B)

Conditional probability of A given B.

f(x)

Probability density function or another function, depending on context.

F(x)

Cumulative distribution function.

N(μ, σ²)

Normal distribution with mean μ and variance σ².

p

Often denotes a probability or p-value, depending on context.

α

Significance level in a statistical test.

β

May represent a regression coefficient or Type II error probability, depending on context.

Regression And Correlation Notation

Linear Model

y = β₀ + β₁x + ε

Symbols

SymbolMeaning

β₀

Intercept parameter.

β₁

Slope parameter.

ε

Random error term in a statistical model.

r

Sample Pearson correlation coefficient.

ρ

Population correlation coefficient.

R²

Coefficient of determination.

Interpretation

Correlation describes association and does not by itself establish a causal relationship. Regression describes a modeled relationship under specified assumptions.

Uncertainty And Graph Notation

NotationMeaning

y ± u

Estimate with a stated uncertainty, where the interpretation of u must be specified.

95% CI

A confidence interval constructed using a method with 95% long-run coverage under its assumptions.

SD

Standard deviation, describing data spread.

SE

Standard error, describing the estimated sampling variability of a statistic.

IQR

Interquartile range, Q₃ − Q₁.

LOD

Limit of detection in analytical contexts.

Data Presentation Principles

  • Label every axis with the quantity and its unit where applicable.

  • Use a scale that makes the data variation interpretable.

  • Identify all plotted data series clearly.

  • State what error bars represent.

  • Distinguish raw observations from calculated summaries.

  • Report sample size when it is relevant to interpretation.

  • Avoid misleading axis truncation or inappropriate graphical scaling.

  • Use consistent numerical precision and unit conventions.

  • Identify missing data and excluded observations transparently.

  • Report statistical methods and relevant model assumptions.

Worked Examples

ProblemSolution

Calculate the mean of 2, 4, and 6.

x̄ = (2 + 4 + 6)/3 = 4.

Find the sample range of 3, 5, 8, and 10.

R = 10 − 3 = 7.

A dataset has sample standard deviation 4 and sample size 16. Calculate the standard error of the mean.

SE = 4/√16 = 1, assuming independent observations and the usual sampling conditions.

Interpret a graph axis labelled distance / m.

The plotted numerical values represent distance measured in metres.

Common Errors

  • Omitting units from graph axes.

  • Confusing standard deviation with standard error.

  • Treating correlation as proof of causation.

  • Failing to identify the meaning of error bars.

  • Confusing population parameters with sample statistics.

  • Using an inappropriate graph scale.

  • Reporting statistical significance without considering effect size and uncertainty.

  • Interpreting a p-value as the probability that a hypothesis is true.

Applications

  • Experimental science and laboratory reports.

  • Environmental data analysis.

  • Biological and medical research.

  • Engineering testing and quality control.

  • Statistical modeling and machine learning.

  • Scientific publications, dashboards, and research presentations.

Reference

  • NIST/SEMATECH, e-Handbook of Statistical Methods.

  • JCGM 100, Evaluation of Measurement Data: Guide to the Expression of Uncertainty in Measurement.

  • IUPAC, Quantities, Units and Symbols in Physical Chemistry (Green Book).

  • OpenStax, Introductory Statistics.

Related Topic

  • SCI-REF-006-101

  • SCI-REF-006-105

  • SCI-REF-006-107

  • SCI-REF-006-108

Sources and verification

Sources are shown as provided in the project data. Not every source has yet been independently verified. Please report errors or missing citations.

  • Source verification pending; check an authoritative textbook, university, standards body, or peer-reviewed source.

Suggest a correction or source · More in Scientific Symbols & Notation