How to Calculate Precision and Intermediate Precision in Method Validation

In the validation of a Stability-Indicating Method (SIM), establishing precision is just as critical as proving accuracy. While accuracy measures how close you are to the true value, precision measures the closeness of agreement between a series of measurements obtained from multiple samplings of the same homogeneous sample. It proves that your lab results are consistent and reproducible, even when different days or different analysts are involved.

Repeatability (Intra-day Precision)

Repeatability expresses the precision under the same operating conditions over a short interval of time (typically within one day). It is often referred to as intra-day precision.

How to perform the study: Standard practice involves analyzing a minimum of nine determinations covering the specified range of the method. A common protocol includes:

• Three different concentration levels (e.g., 80%, 100%, and 120% of the target dose).

• Three replicates at each of those levels, all performed on the same day.

How to calculate: The primary metric for precision is the Relative Standard Deviation (%RSD).

1. Calculate the mean (x̄) of your replicates.

2. Calculate the standard deviation (SD).

3. Apply the %RSD formula: %RSD = (SD / x̄) × 100.

For a method to be considered precise in a pharmaceutical setting, the %RSD should typically be less than 2.0%.

Intermediate Precision (Inter-day Precision)

Intermediate precision (or inter-day precision) evaluates the impact of variations within a single laboratory, such as testing on different days, using different equipment, or involving different analysts.

How to perform the study: The same concentrations used in the repeatability study are analyzed again on three different days. This ensures that "random" factors—like slight temperature fluctuations in the lab or different batches of mobile phase—do not compromise the result.

Statistical evaluation (ANOVA): To calculate if the variation between days is significant, scientists use One-Way Analysis of Variance (ANOVA). This provides two critical values:

1. Within-Day Mean Square (WMS): Measures the internal consistency of samples on the same day.

2. Between-Day Mean Square (BMS): Measures the consistency of the averages from one day to the next.

The F-test calculation: The "F-value" is the ratio used to determine if the inter-day differences are statistically acceptable: F_calc = BMS / WMS. If your calculated F-value is less than the tabulated F-value (at a 95% confidence level, α = 0.05), then there is no significant difference between intra-day and inter-day variability, confirming the method is robust and precise.

Precision in the Context of Stress Testing

While formal precision is a requirement for registration dossiers, it is handled slightly differently during early forced degradation research. Because stress-testing methods are often "investigational" screening tools rather than final control methods, a more abbreviated validation is sometimes acceptable.

In these cases, repeatability can be evaluated by preparing a smaller set (e.g., 5 to 10) of assay samples and using simple standard deviation to confirm the method can reliably track the 10% to 30% loss of API typically targeted in forced degradation.

Summary of Acceptance Criteria

Calculating precision ensures that the stability data is not a result of analytical noise. By combining %RSD for daily consistency and ANOVA for inter-day reliability, scientists can report the degradation profile of a drug with confidence, ensuring that patient safety data is based on a solid, reproducible methodology.