Reliable 3D surface acquisition, registration and validation using statistical error models

2002 ◽  
Author(s):  
J. Guehring
Keyword(s):  
Statistical Error ◽  
Error Models ◽  
3D Surface

scholarly journals Comparison and evaluation of statistical error models for scRNA-seq

2021 ◽  
Author(s):  
Saket Choudhary ◽  
Rahul Satija
Keyword(s):  
Linear Models ◽  
Negative Binomial ◽  
Statistical Error ◽  
Rna Seq ◽  
Multiple Sources ◽  
Error Models ◽  
Wide Range ◽  
Data Driven Approach ◽  
Downstream Analysis ◽  
Experimental Processing

Heterogeneity in single-cell RNA-seq (scRNA-seq) data is driven by multiple sources, including biological variation in cellular state as well as technical variation introduced during experimental processing. Deconvolving these effects is a key challenge for preprocessing workflows. Recent work has demonstrated the importance and utility of count models for scRNA-seq analysis, but there is a lack of consensus on which statistical distributions and parameter settings are appropriate. Here, we analyze 58 scRNA-seq datasets that span a wide range of technologies, systems, and sequencing depths in order to evaluate the performance of different error models. We find that while a Poisson error model appears appropriate for sparse datasets, we observe clear evidence of overdispersion for genes with sufficient sequencing depth in all biological systems, necessitating the use of a negative binomial model. Moreover, we find that the degree of overdispersion varies widely across datasets, systems, and gene abundances, and argues for a data-driven approach for parameter estimation. Based on these analyses, we provide a set of recommendations for modeling variation in scRNA-seq data, particularly when using generalized linear models or likelihood-based approaches for preprocessing and downstream analysis.

Background subtraction in STEM energy-loss mapping

1984 ◽  
Vol 42 ◽  
pp. 568-569
Author(s):  
R.D. Leapman ◽  
K.E. Gorlen ◽  
C.R. Swyt
Keyword(s):  
Energy Loss ◽  
Signal To Noise Ratio ◽  
Statistical Error ◽  
Scanning Transmission Electron Microscope ◽  
Reference Image ◽  
Inverse Power Law ◽  
Transmission Electron ◽  
Least Squares Fit ◽  
Scanning Transmission ◽  
Single Number

The determination of elemental distributions by electron energy loss spectroscopy necessitates removal of the non-characteristic spectral background from a core-edge at each point in the image. In the scanning transmission electron microscope this is made possible by computer controlled data acquisition. Data may be processed by fitting the pre-edge counts, at two or more channels, to an inverse power law, AE-r, where A and r are parameters and E is energy loss. Processing may be performed in real-time so a single number is saved at each pixel. Detailed analysis, shows that the largest contribution to noise comes from statistical error in the least squares fit to the background. If the background shape remains constant over the entire image, the signal-to-noise ratio can be improved by fitting only one parameter. Such an assumption is generally implicit in subtraction of the “reference image” in energy selected micrographs recorded in the CTEM with a Castaing-Henry spectrometer.

Identification in Dynamic Shock-Error Models

1979 ◽  
Author(s):  
Agustin Maravall ◽  
Klaus Neumann ◽  
Ulrich Steinhardt
Keyword(s):  
Error Models

scholarly journals University of Kiel Radiocarbon Measurements II

Radiocarbon ◽  
1967 ◽  
Vol 9 ◽  
pp. 257-260
Author(s):  
H. Willkomm ◽  
H. Erlenkeuser
Keyword(s):  
Proportional Counter ◽  
Atmospheric Pressure ◽  
Statistical Error ◽  
Quartz Tube ◽  
Sensitive Volume ◽  
Concrete Wall ◽  
Lead Shield ◽  
Double Ring

Most of the measurements reported here have been obtained with the 4.5-L CO2 counter previously described (Kiel I; Erlenkeuser, 1965). A few samples have been dated with a 3-L proportional counter. The copper counter is surrounded by 28 GM counters in the form of a double ring. The total assembly is shielded by 10 cm of old lead. Neither an inner lead shield between counter and anticoincidence ring nor screening of sensitive volume by a quartz tube-as in the 4.5-L counter-has been used. Background of the small counter is 17.20 cpm or The 0.95 x NBS value is 9.5 cpm at 400 torr. Within statistical error background does not depend on atmospheric pressure. The 3-L counter is placed under a concrete wall, 2.5 m in length and 9.4 m in height.

Study on Optimization of the Number of DF Stations

2014 ◽  
Vol 709 ◽  
pp. 485-490
Author(s):  
Xiang Wu ◽  
Jun Jun Zong ◽  
Xun Xue Cui ◽  
Chuan Xu Liu
Keyword(s):  
Maximum Likelihood ◽  
Maximum Likelihood Estimation ◽  
Likelihood Estimation ◽  
Direction Finding ◽  
Location Error ◽  
Location Accuracy ◽  
Error Models ◽  
Reasonable Number ◽  
Simulation Results

Reasonable number of direction finding station is examined in multi-station bearing-crossing location. Though it is believed that increasing the number of station is helpful to improve the location accuracy, In the paper, the maximum likelihood estimation (MLE) as an example. The algorithms and the location error models are given. The simulation results show that the location accuracy will be improved quickly with the increase of the number of the measuring participants, but the improvement will be sharply slowed down if too many station involved, which also boost the complexity of location.

Statistical error in calculating the nuclide composition of low-burnup fuel

Atomic Energy ◽  
2005 ◽  
Vol 98 (2) ◽  
pp. 83-88 ◽  
Author(s):  
A. M. Degtyarev ◽  
A. A. Myasnikov
Keyword(s):  
Statistical Error ◽  
Nuclide Composition
Sign in / Sign up

Export Citation Format

Share Document