Subjective assessment of frequency distribution histograms and consequences on reference interval accuracy for small sample sizes: A computer‐simulated study

Abstract

Background: Inaccuracy in estimating reference intervals (RIs) is a problem with small sample sizes.Objectives: This study aimed to identify the most accurate statistical methods to estimate RIs based on sample size and population distribution shape. We also studied the accuracy of sample frequency distribution histograms to retrieve the original population distribution and compared strategies based on the histogram and goodness-of-fit test. Methods:The statistical methods that best enhanced accuracy were determined for various sample sizes (n = 20-60) and population distributions (Gaussian, log-normal, and left-skewed) were determined by repeated-measures ANOVA and posthoc analyses. Frequency distribution histograms were built from 900 samples of five different sizes randomly extracted from six simulated populations. Three reviewers classified the population distributions from visual assessments of a sample histogram, and the classification error rate was calculated. RI accuracy was compared among the strategies based on the histograms and goodness-of-fit tests. Results:The parametric, nonparametric, and robust methods enhanced lower reference limit estimation accuracy for Gaussian, log-normal, and left-skewed distributions, respectively. The parametric, nonparametric bootstrap, and nonparametric methods enhanced the upper limit estimation accuracy for Gaussian, log-normal, and left-skewed distributions, respectively. Regardless of sample size, sample histogram assessments properly classified the original population distribution 71% to 93.9% of the time, depending on the reviewers. In this study, the strategy based on histograms assessed by the statistician was significantly more precise and accurate than the strategy based on the goodness-of-fit test (P < 0.001). Conclusions:A strategy based on histograms might enhance the accuracy of RI estimations. However, relevant inter-reviewer variations in histogram interpretation were detected. Factors affecting inter-reviewer variations should be further explored.

Plasma chemistry reference intervals for adult multi‐drug‐resistance gene deficient Collies

“…Visual examination of histograms (created in SAS) was also conducted, although the Shapiro-Wilk test was used for the final determination of distribution as it is less subjective. 6 The bar for normality was set higher with α = 0.2 (P-value threshold) as normality tests may lack power for small sample sizes used in veterinary medicine. 7 Symmetry was tested with the Runs Test proposed by McWilliams in the Reference Value Advisor Tool with α = 0.05.…”

Oxidative Potential in Exhaled Air (OPEA) as a Tool for Predicting Certain Respiratory Disorders in the General Adult Population: Cross-Sectional Analysis Nested in the Swiss Health Study

“…The remaining participants constituted the reference sample. The OPEA distribution and the presence of outliers (i.e., results that were not supposed to belong to the reference population) were examined visually [ 23 ]. Outliers were managed using the Tukey method [ 24 ].…”

Assessment of survey radiography as a method of diagnosing bilateral laryngeal paralysis in dogs

“…The normality of continuous variables was assessed graphically. 22 Demographic data were described using the median (minimummaximum) because none of them were normally distributed. A Mann-Whitney test was used to compare continuous demographic variables (i.e., age and body weight) between the control group and dogs with laryngeal paralysis.…”

“…The normality of continuous variables was assessed graphically 22 . Demographic data were described using the median (minimum–maximum) because none of them were normally distributed.…”