PubMed Health⌕ Search

Biomedical subjects

Y Hochberg

Publications and source records attributed to Y Hochberg.

11 recordsLinked to original sources
PubMed1996

Multiple test procedures for dose finding.

The problem of identifying the lowest dose level for which the mean response differs from that at the zero dose level is considered. A general framework for stepwise testing procedures that use contrasts among the dose level means is proposed. Using this framework, several new procedures are derived. These and some existing procedures, including that of Williams (1971, Biometrics 27, 103-117; 1972, Biometrics 28, 519-531), are compared analytically and by an extensive simulation study for the normal theory balanced one-way layout case. It is pointed out that the procedures based on the so-called step and basin contrasts proposed by Ruberg (1989, Journal of American Statistical Association 84, 816-822) have excessively high type I familywise error rates (FWEs) and, hence, they should not be used. Some findings of the simulation study are as follows: For monotone dose mean configurations, Williams' procedure and two step-down test procedures based on Helmert and linear contrasts offer the best performance. For nonmonotone dose mean configurations, the performance of Williams' procedure does degrade somewhat, but the other two procedures are still the best. For more complex designs, a simple step-down test procedure that uses any alpha-level tests (not necessarily t-tests) to compare each dose level with the zero dose level controls the FWE and is the only alternative available, but its power is rather low, especially under nonmonotone configurations. Step-up procedures are generally dominated by step-down procedures when the same contrasts are used although the differences are not great.

Animals↗
PubMed1995

Mathematical formulae for the prediction of the residual beta cell function during the first two years of disease in children and adolescents with insulin-dependent diabetes mellitus.

On the basis of a retrospective study of 71 children followed for 24 months after diagnosis of type I insulin dependent diabetes a fitted mathematical model was constructed for the prediction of the course of beta cell function from the time of diagnosis. Two equations were derived, one for the maximal basal (B-max) and the other for the maximal i.v. glucagon stimulated peak C-peptide (P-max) levels reached during the remission period. The prognostic variables selected for analysis were: peak C-peptide levels at diagnosis (Po), age sex, degree of obesity, pubertal rating, the presence of islet cell antibodies (ICA) and levels of GHb. Multivariate analysis of the data showed that Po (p = 0.0006), puberty (p = 0.041). obesity (p = 0.0021), sex (p = 0.031), ICA (p = 0.0045) and GHb(p = 0.0066) significantly contributed to the prediction formula obtained for B-max whereas the contribution of the above variables for P-max were: Po (p = 0.0019), puberty (p = 0.0187), obesity (p = 0.0058), sex (p = 0.0598), ICA (p = 0.0187) and GHb (p = 0.0027). The residuals of the observed values from the values fitted by the predicted equations served to define two separate groups demonstrating distinct differences in the natural course of beta cell function in type I diabetes. This fitted model may thus be useful in distinguishing between newly diagnosed young patients who will undergo remission, requiring lower insulin doses, and those who have little chance for remission. It might also be helpful in the selection of patients most likely to benefit from immunosuppression or modulation, to maximize the benefit to risk ratio for such patients.

Adolescent↗
PubMed1990

More powerful procedures for multiple significance testing.

The problem of multiple comparisons is discussed in the context of medical research. The need for more powerful procedures than classical multiple comparison procedures is indicated. To this end some new, general and simple procedures are discussed and demonstrated by two examples from the medical literature: the neuropsychologic effects of unidentified childhood exposure to lead, and the sleep patterns of sober chronic alcoholics.

Alcoholism↗
PubMed1989

The antihypertensive effect of atenolol and bopindolol in the elderly.

The antihypertensive efficacy and tolerability of two betablockers: atenolol and bopindolol, was compared in a group of 30 elderly subjects aged 64.8 +/- 4.6 years. The daily dose of the two agents was relatively low. Atenolol 50-100 mg and bopindolol 0.5-1.0 mg sufficed to cause reduction of DBP to the target of less than or equal to 95 mm Hg, when applied as monotherapy. This was achieved in 75% of cases with bopindolol and in 93% of cases with atenolol. Atenolol, 50-100 mg/dd, lowered blood pressure from 173.7 +/- 13.2/103.7 +/- 3.0 (weekly) to 155.5 +/- 16.5/86.5 +/- 8.2 mm Hg (week 12) (P less than 0.005) while bopindolol, 0.5-1.0 mg, lowered blood pressure from 171.6 +/- 11.3/104.1 +/- 3.6 to 158.7 +/- 20.9/86.1 +/- 6.0 mm Hg (P less than 0.005). Heart rate was reduced from 80.5 (week 4) to 66.7 +/- 7.3 (week 12) by atenolol (P less than 0.0001), and from 83.7 +/- 11.8 (week 4) to 71.1 +/- 7.5 (week 12) by bopindolol (P less than 0.0001). Between treatment differences: comparisons yielded P values which were not sufficiently low to reject the null hypothesis of no difference between the two treatments. Well-being and short-term memory were not affected by either agent and tolerability of both drugs was good. These findings demonstrate that both bopindolol and atenolol are useful agents for control of hypertension in the elderly.

Adrenergic beta-Antagonists↗
PubMed1986

Alternative estimation procedures for Pr(X less than Y) in categorized data.

Consider two independent random variables X and Y. The functional R = Pr(X less than Y) [or gamma = Pr(X less than Y) - Pr(Y less than X)] is of practical importance in many situations, including clinical trials, genetics, and reliability. In this paper several approaches to estimation of gamma when X and Y are presented in discretized (categorical) form are analyzed and compared. Asymptotic formulas for the variances of the estimators are derived; use of the bootstrap to estimate variances is also discussed. Computer simulations indicate that the choice of the best estimator depends on the value of gamma, the underlying distribution, and the sparseness of the data. It is shown that the bootstrap provides a robust estimate of variance. Several examples are treated.

Analysis of Variance↗
PubMed1984

Studies on the level of natural antibodies reactive with various tumor cells during urethane carcinogenesis in BALB/c mice.

Serum from young normal BALB/c mice was found to contain IgM antibodies able to mediate complement-dependent lysis of certain syngeneic or allogeneic tumor target cells. The titer of such naturally occurring antitumor antibodies ( NATA ) was found to increase with aging. A longitudinal serological study comparing the cytotoxicity potential of NATA from normal and from urethan-treated BALB/c mice was performed. It was found that urethan-treated mice that did not develop primary lung-adenomas within the duration of the experiment had significantly lower NATA titers, against one out of 4 target cells assayed, than urethan-treated animals that developed lung adenomas. This difference was evident in two independent experiments. The results suggested that the lower NATA activity of the urethan-treated mice that did not develop tumors existed even before exposure to the carcinogenic insult. This raises the possibility that certain populations could be segregated according to their natural antibody profile into those individuals which will develop primary tumors within a certain period if exposed to a subthreshold amount of carcinogen, and those which will not.

Adenoma↗
PubMed1983

On improved calibrations of unknowns in a system of quality-controlled assays.

Two new estimators for calibrating unknowns from dose-response curves, in a system of quality-controlled assays, are examined. In contrast with the conventional estimator which uses only the results of the one assay in which the response of the unknown dose is measured, the new estimators also utilize the results of all other assays through the replications of the control samples in the system. The first estimator is based on maximizing the likelihood of the given system (with respect to the different dose-response parameters, the levels of the control samples and the levels of the unknowns) when response errors are normally distributed. The second estimator is a regression-like estimator obtained by subtracting from the conventional estimator its estimated regression on the deviation of the calibrated control levels in the given assay from their average values in the system. Evaluations of the reductions in bias and variance attained by the new estimators show when substantial reductions in mean square error can be expected. The new estimators are illustrated with a system of 22 hFSH radioimmunoassays.

Animals↗
PubMedDate not supplied

Age and sex dependency of the Achilles tendon reflex.

Achilles tendon reflex time was measured in normal subjects (1,837 females and 7,937 males). Values of half relaxation time showed a clear dependency on both age and sex. The reflex becomes slower with advancing age and was consistently slower in females. The results redefine the normal range of the Achilles tendon reflex. Regression lines of relaxation time on age were fitted for each sex separately. Lines representing linear regression, log-linear regression or quadratic regression were inferior to those described by linear splines. The gradual increase of Achilles tendon relaxation time with age was not due to unrecognized hypothyroidism or peripheral neuropathy. It is suggested that one cause of the progressive increment is diminution of sympathetic tone with age, and changes in the muscles themselves may also contribute.

Achilles Tendon↗