ABSTRACT
Measurement technologies are often affected by random errors, which make the estimates of parameters biased, and thus inconsistent. This problem appears in analytic chemistry, in environmental monitoring, in modeling astronomical data, in biometrics, and practically in all parts of reality. Moreover, some observations can be undetected, e.g., when the measured flux (light, magnetic) in the experiment falls below some flux limit. In econometrics, the errors can arise due to misreporting, miscoding by the collectors of the data, or by incorrect transformation from initial reports. Analytic chemists try to construct a calibration curve and to interpolate the correct unknown sample. However, even the calibration can be affected by measurement errors. The mismeasurements make the statistical inference biased, and they distort the trends in the data.
