Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
ASTM D4375-96 (Reapproved 2011) is under the jurisdiction of Committee D19 on Water and establishes a uniform standard for calculating, expressing, and symbolizing fundamental statistical parameters. The scope emphasizes that prior to performing many statistical procedures, certain variables must be calculated using a standardized technique. This practice assures the user that all calculations are performed in the same manner and that all results are presented consistently across different laboratories and studies.
The practice defines core statistical concepts: a population is the complete set of all possible observations of a phenomenon; a sample is a subset of data drawn from that population; a statistic is an estimated quantity calculated from a sample; and a parameter is a measurable quantity characteristic of the population. An observation is defined as “a fact duly noted and recorded.” The standard explicitly notes that while a population may be infinite, N and n are treated as finite for all calculations.
To ensure clarity and reduce errors, the practice provides an exact mapping between symbols for sample statistics (Roman letters) and population parameters (Greek letters).
| 📐 Parameter Name | 🟦 Sample Symbol | 🎯 Population Symbol | 📏 Definition |
|---|---|---|---|
| Size | n | N | Number of observations (finite for calculations) |
| Observation | xi | Xi | Individual value duly noted and recorded |
| Mean | x̄ | μ | Average of the observations |
| Variance | s2 | σ2 | Average squared deviation from the mean |
| Standard Deviation | s | σ | Dispersion (square root of the variance) |
| Std Dev of the Mean | sx̄ | σμ | Standard error of the mean |
| Relative Std Dev (%) | RSD | RSDp | Coefficient of variation as a percentage |
Section 6 of the standard provides the exact formulas required for all fundamental calculations. These formulas are the building blocks for data analysis in water quality testing.
| 🎯 Parameter | 📐 Sample Formula | ⚡ Population Formula |
|---|---|---|
| Mean | x̄ = Σ xi / n | μ = Σ Xi / N |
| Variance | s² = Σ (xi − x̄)² / (n − 1) | σ² = Σ (Xi − μ)² / N |
| Standard Deviation | s = √ s² | σ = √ σ² |
| Std Dev of the Mean (SEM) | sx̄ = √ (s² / n) | σμ = √ (σ² / N) |
| Relative Std Dev (CV %) | RSD = 100 × s / x̄ | RSDp = 100 × σ / μ |
Per Section 3.1 of the standard, a population is the complete set of data that consists of all possible observations of a phenomenon. It is the entire group of interest (which may be infinite). A sample is a finite subset of data drawn from this population. Since full populations are rarely observable, we calculate sample statistics (like x̄) to estimate population parameters (like μ).
Using n in the denominator tends to produce an estimate of the population variance that is too small, especially for small sample sizes. Dividing by n − 1 (the degrees of freedom) corrects for this bias, making the sample variance, s², an unbiased estimator of the population variance, σ². This correction is known as Bessel’s correction, and its specific use in the sample formula is mandated by this practice.
The SEM, denoted as