PMID- 24143037
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20211021
IS  - 0167-9473 (Print)
IS  - 0167-9473 (Linking)
VI  - 55
IP  - 1
DP  - 2011 Jan 1
TI  - Understanding and comparisons of different sampling approaches for the Fourier 
      Amplitudes Sensitivity Test (FAST).
PG  - 184-198
AB  - Fourier Amplitude Sensitivity Test (FAST) is one of the most popular uncertainty 
      and sensitivity analysis techniques. It uses a periodic sampling approach and a 
      Fourier transformation to decompose the variance of a model output into partial 
      variances contributed by different model parameters. Until now, the FAST analysis 
      is mainly confined to the estimation of partial variances contributed by the main 
      effects of model parameters, but does not allow for those contributed by specific 
      interactions among parameters. In this paper, we theoretically show that FAST 
      analysis can be used to estimate partial variances contributed by both main 
      effects and interaction effects of model parameters using different sampling 
      approaches (i.e., traditional search-curve based sampling, simple random sampling 
      and random balance design sampling). We also analytically calculate the potential 
      errors and biases in the estimation of partial variances. Hypothesis tests are 
      constructed to reduce the effect of sampling errors on the estimation of partial 
      variances. Our results show that compared to simple random sampling and random 
      balance design sampling, sensitivity indices (ratios of partial variances to 
      variance of a specific model output) estimated by search-curve based sampling 
      generally have higher precision but larger underestimations. Compared to simple 
      random sampling, random balance design sampling generally provides higher 
      estimation precision for partial variances contributed by the main effects of 
      parameters. The theoretical derivation of partial variances contributed by 
      higher-order interactions and the calculation of their corresponding estimation 
      errors in different sampling schemes can help us better understand the FAST 
      method and provide a fundamental basis for FAST applications and further 
      improvements.
FAU - Xu, Chonggang
AU  - Xu C
AD  - Department of Entomology and Center for Quantitative Sciences in Biomedicine, 
      North Carolina State University, Raleigh, NC 27695, USA.
FAU - Gertner, George
AU  - Gertner G
LA  - eng
GR  - R01 AI054954/AI/NIAID NIH HHS/United States
PT  - Journal Article
PL  - Netherlands
TA  - Comput Stat Data Anal
JT  - Computational statistics & data analysis
JID - 100960938
PMC - PMC3798038
MID - NIHMS482129
OTO - NOTNLM
OT  - Fourier Amplitude Sensitivity Test
OT  - Interactions
OT  - Random balance design
OT  - Sensitivity analysis
OT  - Simple random sampling
OT  - Uncertainty analysis
EDAT- 2011/01/01 00:00
MHDA- 2011/01/01 00:01
PMCR- 2013/10/17
CRDT- 2013/10/22 06:00
PHST- 2013/10/22 06:00 [entrez]
PHST- 2011/01/01 00:00 [pubmed]
PHST- 2011/01/01 00:01 [medline]
PHST- 2013/10/17 00:00 [pmc-release]
AID - 10.1016/j.csda.2010.06.028 [doi]
PST - ppublish
SO  - Comput Stat Data Anal. 2011 Jan 1;55(1):184-198. doi: 10.1016/j.csda.2010.06.028.