TY - JOUR

T1 - Regression Models for the Field Electron Emission Signal

AU - Egorov, N. V.

AU - Varayun’, M. I.

AU - Bure, V. M.

AU - Antonov, A. Yu

N1 - Funding Information: This study was supported by the Russian Foundation for Basic Research, project no. 20-07-01086. Publisher Copyright: © 2020, Pleiades Publishing, Ltd. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/11

Y1 - 2020/11

N2 - Abstract: The field electron emission signal is described using the regression approach with three models. Each regression function has its own theoretical justification. The three-parameter models make it possible to take into account the deviations of the I‒V characteristics from a straight in the Fowler–Nordheim coordinates in both the high- and low-voltage region. For clear comparison, investigated data samples are obtained in the numerical experiment with specified signal parameters. A special noise model is considered, in which the use of conventional linearization over the parameters seems fair. Attention is paid to checking the regression residuals for normality of their distribution. The parameters of the proposed models are cross estimated and their statistical significance with a confidence level of 95% is verified. It is shown that, for each set of experimental data, a separate model may be necessary. The adjusted coefficient of determination is used as a measure of the dependence of the response on the factor.

AB - Abstract: The field electron emission signal is described using the regression approach with three models. Each regression function has its own theoretical justification. The three-parameter models make it possible to take into account the deviations of the I‒V characteristics from a straight in the Fowler–Nordheim coordinates in both the high- and low-voltage region. For clear comparison, investigated data samples are obtained in the numerical experiment with specified signal parameters. A special noise model is considered, in which the use of conventional linearization over the parameters seems fair. Attention is paid to checking the regression residuals for normality of their distribution. The parameters of the proposed models are cross estimated and their statistical significance with a confidence level of 95% is verified. It is shown that, for each set of experimental data, a separate model may be necessary. The adjusted coefficient of determination is used as a measure of the dependence of the response on the factor.

KW - field electron emission

KW - I–V characteristic

KW - least squares method

KW - regression models

KW - statistical significance

UR - http://www.scopus.com/inward/record.url?scp=85098224812&partnerID=8YFLogxK

U2 - 10.1134/S1027451020060294

DO - 10.1134/S1027451020060294

M3 - Article

AN - SCOPUS:85098224812

VL - 14

SP - 1394

EP - 1402

JO - ПОВЕРХНОСТЬ. РЕНТГЕНОВСКИЕ, СИНХРОТРОННЫЕ И НЕЙТРОННЫЕ ИССЛЕДОВАНИЯ

JF - ПОВЕРХНОСТЬ. РЕНТГЕНОВСКИЕ, СИНХРОТРОННЫЕ И НЕЙТРОННЫЕ ИССЛЕДОВАНИЯ

SN - 1027-4510

IS - 6

ER -