At BioScience Laboratories, we believe the accurate interpretation of study results is critically important to a study's value, and the results from studies conceived including a statistical design are more accurate and precise than are those studies with no preconsideration of an analytical approach. Hence, we promote statistical design at the beginning of the study development process. Just as a single type of microbiological evaluation is not valid for every product, statistical analysis, too, must be specifically designed in order to allow for smaller sample sizes, unambiguous results, and lower overall cost.
BioScience Laboratories statistical methods include:
Parametric and Nonparametric Statistical Methods, including determinations of sample size requirements, detectable limits, etc.
In-Depth Statistical Analysis of data from one of our studies, or those from your on-going clinical studies in the field.
Statistical Interpretation grounded in microbiology and/or skin biotechnology.
Analysis of data from studies comparing formulations to generate relative ranking of performance.
Sample Size Determination for a surgical hand scrub per the Tentative Final Monograph (TFM) protocol for Effectiveness Testing of a Surgical Hand Scrub (FR 59:116, 17 June 94, p.
Sample Size Determination for a surgical hand scrub:
Tentative Final Monograph (TFM) protocol for Effectiveness Testing of a Surgical Hand Scrub (FR 59:116, 17 June 94, p. 31446).
N > 2S2(Zα/2 + Zβ)2/D2
Where:
N = Sample size per product configuration arm
S = Estimate of variance =0.53
Zα/2 = 0.05 level of significance (two-tail) = 1.96, Type I error (probability of stating a significant effect exists when one does not)
Zβ = 0.842 level of significance for Type II (beta) error (probability of stating no significant effect exists when one does)
D = Detectable difference (sensitivity) = 0.5
