PMID- 31228287
OWN - NLM
STAT- MEDLINE
DCOM- 20191111
LR  - 20191111
IS  - 1939-165X (Electronic)
IS  - 0275-6382 (Linking)
VI  - 48
IP  - 2
DP  - 2019 Jun
TI  - Reference interval estimation of small sample sizes: A methodologic comparison 
      using a computer-simulation study.
PG  - 335-346
LID - 10.1111/vcp.12725 [doi]
AB  - BACKGROUND: According to the ASVCP and other guidelines, samples should comprise 
      at least 120 individuals for reference interval (RI) estimation. Unfortunately, 
      this minimum sample size is difficult to achieve in veterinary medicine. Several 
      statistical methods are described to determine RIs from small sample sizes, but 
      it is unclear which method provides the best accuracy. OBJECTIVES: This study 
      aimed to compare statistical strategies for estimating RIs and determine which 
      strategy best enhances accuracy when the sample size is between 20 and 120. 
      METHODS: Different sample size groups (n = 120, 100, 80, 60, 40, and 20) were 
      randomly selected 50 times from simulated Gaussian, log-normal, and left-skewed 
      populations of 5000 total values. RIs were calculated using seven different 
      statistical strategies comprising robust, parametric, nonparametric, and 
      bootstrap methods, alone or in combination. RI accuracy was compared among these 
      strategies at each sample size. The strategy that was significantly more accurate 
      than others in the largest number of comparisons was considered as the one that 
      best-enhanced RI accuracy. RESULTS: The strategies that best-enhanced RI accuracy 
      included using the parametric method when the Shapiro-Wilk P > 0.2 and, 
      otherwise, using the nonparametric method to determine the upper and lower RI 
      limits when there were between 60 and 100 reference individuals, and finding the 
      lower RI limit when there were 40 reference individuals. The Box-Cox 
      transformation parametric method best-enhanced RI accuracy of the upper RI limit 
      when there were 40 reference individuals, and the nonparametric method 
      best-enhanced RI accuracy of both RI limits when there were 20 reference 
      individuals. CONCLUSIONS: Using the parametric method when the Shapiro-Wilk 
      P > 0.2, and the nonparametric method in other instances, will likely enhance RI 
      accuracy when there are between 40 and 100 reference individuals. For smaller 
      samples, the nonparametric method might be preferred.
CI  - (c) 2019 American Society for Veterinary Clinical Pathology.
FAU - Le Boedec, Kevin
AU  - Le Boedec K
AD  - Centre Hospitalier Veterinaire Fregis, Arcueil, France.
LA  - eng
PT  - Comparative Study
PT  - Journal Article
DEP - 20190622
PL  - United States
TA  - Vet Clin Pathol
JT  - Veterinary clinical pathology
JID - 9880575
SB  - IM
MH  - Animals
MH  - *Computer Simulation
MH  - Normal Distribution
MH  - Reference Values
MH  - Sample Size
OTO - NOTNLM
OT  - Gaussian distribution
OT  - Shapiro-Wilk test
OT  - bootstrap
OT  - nonparametric method
OT  - parametric method
OT  - robust method
EDAT- 2019/06/23 06:00
MHDA- 2019/11/12 06:00
CRDT- 2019/06/23 06:00
PHST- 2018/03/13 00:00 [received]
PHST- 2018/10/02 00:00 [revised]
PHST- 2018/10/08 00:00 [accepted]
PHST- 2019/06/23 06:00 [pubmed]
PHST- 2019/11/12 06:00 [medline]
PHST- 2019/06/23 06:00 [entrez]
AID - 10.1111/vcp.12725 [doi]
PST - ppublish
SO  - Vet Clin Pathol. 2019 Jun;48(2):335-346. doi: 10.1111/vcp.12725. Epub 2019 Jun 
      22.