Alanine aminotransferase (ALT) and aspartate aminotransferase (AST) are among the common biomarkers which have been investigated in serum of patients suffering from end-stage renal disease (ESRD) and infections of hepatitis B virus (HBV) and hepatitis B virus (HBC). The present study aimed to statistically investigate whether serum levels of those enzymes and their ratio (AST/ALT) vary between hepatitis B and C patients with or without ESRD. Serum levels of AST and ALT were measured in 228 subjects of both genders, and those subjects were included in these groups: HBV and HCV patients, patients suffering from comorbidity of HBV/ESRD and HCV/ESRD as well as healthy subjects representing a control group. Means of serum level of ALT and AST for both genders in all patient groups were higher than that of control group and higher than the upper limit of ALT and AST reference intervals. MANOVA results revealed that group effect on the three variables, AST, ALT and AST/ALT, was significant (p < 0.05). The highest mean difference for ALT, AST and AST/ALT variables were, respectively, control and HBV/ESRD comorbidity groups; control and HCV/ESRD comorbidity groups; control and HBV infection groups. Moreover, it was found that the effect of the interactions between the three independent variables (group, age and gender) was not significant in all patient groups. Patients suffering from viral hepatitis and kidney failure disease will suffer from severe liver failure in an early time.

Keywords:AST, ALT, ESRD, HCV, HBV, MANOVA 

The measurement errors problem is endemic in many econometric studies, and one of the oldest known statistical problems. Instrumental variable (IV) method is one of the popular solutions adopted to deal with the mismeasured variables in statistical and econometric analyses. This paper proposes an efficient IV estimator to the parameters of the simple regression model where both variables are subject to measurement errors. The proposed IV is defined using simple mathematical transformation of the manifest independent variable (mismeasured variable). The proposed method is straightforward, and easy to implement. The theoretical superiority of the proposed estimator over the existing IV based estimators due to Wald (1940), Bartlett (1949), and Durbin (1954) is established by analytical comparison and geometric expositions. Simulation based numerical comparisons of the proposed estimator with four different existing estimators are also included.

This paper proposes an estimation method based on the reflection of the (manifest) explanatory variable to estimate the parameters of a simple linear regression model when both response and explanatory variables are subject to measurement error (ME). The reflection method (RM) uses all observed data points, and does not exclude or ignore part of the data or replace them by their ranks. The RM is straightforward, and easy to implement. We show that the RM is equivalent or asymptotically equivalent to the orthogonal regression (OR) method. Simulation studies show that the RM produces estimators that are nearly asymptotically unbiased and efficient under the assumption that the ratio of the error variances equals one. Moreover, it allows to define the sum of squares of errors uniquely, the same way as in the case of no measurement error. Simulation based numerical comparisons of the RM with the ordinary least square (OLS) and OR methods are also included.