Purpose
The paper aims to develop a method for improving the accuracy of smart sensors (deemed as digital measuring instruments) by organizing combined measurements and processing their results by the parametric adjustment method at heterogeneous dispersion of the random error of the applied regression model.
Design/methodology/approach
When carrying out combined measurements, the problem of joint processing of measurement results of functionally related quantities must be solved. The function type can be known in advance or obtained experimentally. The number of combined measurements exceeds the number of unknown measured quantities. The redundant measurements can improve the accuracy of estimates of measured values but lead to inconsistency of the measurement results. The problem of inconsistency is solved by the parametric adjustment method, which is rather widely used mainly in the field of geodetic measurements, wherein the parametric equations are linear and the measured quantities are additive.
Findings
The proposed method allows to reduce the uncertainty of type B of a measurement result, caused by the maximum permissible error of a digital measuring instrument, by 1.2–4 times in comparison with the direct estimation method.
Originality/value
A compact description of the parametric adjustment method in matrix form is given. Recommendations are given on shaping a sensitivity matrix of functions for the proposed method. The geometric interpretation of the proposed method is considered. The results of the proposed method experimental testing are given when evaluating resistance values.
In 1944, Levinson and Sanford created a scale to measure anti-Semitism. Their data showed that the scale had sound psychometric qualities, with a reliability of .96 to .98. Shaw and Wright later stated that the scale was too long for use in some research studies. In the current study, a shorter version (32 items; 38.5% reduction) was created and examined. A high level of internal consistency reliability (r(tt) = .98) was maintained. A test-retest reliability coefficient of .91 was obtained over four weeks. A minimum residual factor analysis with Tandem Criteria rotation found two factors. This shortened Levinson and Sanford Anti-Semitism Scale could be used in research situations with less administration and scoring time. The shorter version still requires further research in terms of validity and social desirability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.