Test Statistic Auto- and Cross-correlation Effects on Monitor False Alert and Missed Detection Probabilities

2017 ◽  
Author(s):  
Boris Pervan ◽  
Samer Khanafseh ◽  
Jaymin Patel
Keyword(s):  
Cross Correlation ◽  
Correlation Effects ◽  
Test Statistic ◽  
Detection Probabilities

scholarly journals MAX-DOAS formaldehyde slant column measurements during CINDI: intercomparison and analysis improvement

2013 ◽  
Vol 6 (1) ◽  
pp. 167-185 ◽  
Author(s):  
G. Pinardi ◽  
M. Van Roozendael ◽  
N. Abuhassan ◽  
C. Adams ◽  
A. Cede ◽  
...  
Keyword(s):  
Cross Sections ◽  
Cross Correlation ◽  
Optical Absorption Spectroscopy ◽  
Integration Time ◽  
Measuring Instruments ◽  
Absorption Cross ◽  
Correlation Effects ◽  
Data Set ◽  
Random Uncertainties ◽  
Ring Effect

Abstract. We present intercomparison results for formaldehyde (HCHO) slant column measurements performed during the Cabauw Intercomparison campaign of Nitrogen Dioxide measuring Instruments (CINDI) that took place in Cabauw, the Netherlands, in summer 2009. During two months, nine atmospheric research groups simultaneously operated MAX-DOAS (MultiAXis Differential Optical Absorption Spectroscopy) instruments of various designs to record UV-visible spectra of scattered sunlight at different elevation angles that were analysed using common retrieval settings. The resulting HCHO data set was found to be highly consistent, the mean difference between instruments generally not exceeding 15% or 7.5 × 1015 molec cm−2, for all viewing elevation angles. Furthermore, a sensitivity analysis was performed to investigate the uncertainties in the HCHO slant column retrieval when varying key input parameters such as the molecular absorption cross sections, correction terms for the Ring effect or the width and position of the fitting interval. This study led to the identification of potentially important sources of errors associated with cross-correlation effects involving the Ring effect, O4, HCHO and BrO cross sections and the DOAS closure polynomial. As a result, a set of updated recommendations was formulated for HCHO slant column retrieval in the 336.5–359 nm wavelength range. To conclude, an error budget is proposed which distinguishes between systematic and random uncertainties. The total systematic error is estimated to be of the order of 20% and is dominated by uncertainties in absorption cross sections and related spectral cross-correlation effects. For a typical integration time of one minute, random uncertainties range between 5 and 30%, depending on the noise level of individual instruments.

scholarly journals Influence of cross-correlation effects on the optical quantities of rough films

2008 ◽  
Vol 16 (11) ◽  
pp. 7789 ◽  
Author(s):  
Daniel Franta ◽  
Ivan Ohlídal ◽  
David Necas
Keyword(s):  
Cross Correlation ◽  
Correlation Effects

Cross-Correlation Effects on NMR Lineshapes and Peptide Conformation

1996 ◽  
Vol 110 (1) ◽  
pp. 26-38 ◽  
Author(s):  
Miroslava Čuperlović ◽  
William E. Palke ◽  
J.T. Gerig ◽  
G.A. Gray
Keyword(s):  
Cross Correlation ◽  
Peptide Conformation ◽  
Correlation Effects

Calculation of pulse-wave velocity using cross correlation—Effects of reflexes in the arterial tree

1991 ◽  
Vol 17 (5) ◽  
pp. 461-469 ◽  
Author(s):  
Morten Benthin ◽  
Philip Dahl ◽  
Robert Ruzicka ◽  
Kjell Lindström
Keyword(s):  
Pulse Wave Velocity ◽  
Wave Velocity ◽  
Cross Correlation ◽  
Pulse Wave ◽  
Correlation Effects ◽  
Arterial Tree

scholarly journals The non-stationary bivariate INAR under an unconstrained inter correlation structure

2018 ◽  
Vol 52 (1) ◽  
pp. 19-41
Author(s):  
YUVRAJ SUNECHER ◽  
NAUSHAD MAMODE KHAN ◽  
VANDNA JOWAHEER
Keyword(s):  
Time Series ◽  
Method Of Moments ◽  
Cross Correlation ◽  
Conditional Likelihood ◽  
Time Varying ◽  
Correlation Effects ◽  
Estimation Of Parameters ◽  
Simulation Experiments ◽  
Regression Effects ◽  
Time Varying Covariates

It is commonly observed in medical and financial studies that large volume of time series of count data are collected for several variates. The modelling of such time series and the estimation of parameters under such processes are rather challenging since these high dimensional time series are influenced by time-varying covariates that eventually render the data non-stationary. This paper considers the modelling of a bivariate integer-valued autoregressive (BINAR(1)) process where the innovation terms are distributed under non- stationary Poisson moments. Since the full and conditional likelihood approaches are cumbersome in this situation, a Generalized Quasi-likelihood (GQL) approach is proposed to estimate the regression effects while the serial and time-dependent cross correlation effects are handled by method of moments. This new technique is assessed over several simulation experiments and the results demonstrate that GQL yields consistent estimates and is computationally stable since few non-convergent simulations are reported.

Sign in / Sign up

Export Citation Format

Share Document