José A. Menéndez

An algorithm for isotonic median regression

Abstract In this paper we give an algorithm for computing the solutions of the Isotonic median regression problem, equivalent to the calculation of the maximum likelihood estimate for the parameter θ=(θ 1 ,…,θ k ) , where θ1 is the location parameter of the bilateral exponential distribution, under the assumption θ 1 ⩽θ 2 ⩽…⩽θ k .

Temporal retinal sensitivity in mesopic adaptation

Citation information: Matesanz BM, Issolio L, Arranz I, de la Rosa C, Menéndez JA, Mar S & Aparicio JA. Temporal retinal sensitivity in mesopic adaptation. Ophthalmic Physiol Opt 2011, 31, 615–624. doi: 10.1111/j.1475‐1313.2011.00859.x

Quantitative and functional influence of surround luminance on the letter contrast sensitivity function.

Aim:  To determine the influence of surround luminance on the letter contrast sensitivity function.

The influence of spectral power distribution on contrast sensitivity

The influence of lighting of different spectral power distribution on letter contrast sensitivity has been studied. The different spectral power distributions were obtained by filtering or dimming tungsten halogen lamps. Measurements were made on 20 young and healthy individuals (25 eyes) whose monocular contrast sensitivities were measured with a natural pupil. Sixteen combinations of test and surround luminance with high or low correlated colour temperatures were studied in such a way that the influence of test luminance, surround luminance or colour temperature of both visual fields could be independently studied. Both test luminance and surround luminance influenced contrast sensitivity but correlated colour temperature did not.

Bootstrap adjusted estimators in a restricted setting

In the context of a normal model, where the mean is constrained to a polyhedral convex cone, a new methodology has been developed for estimating a linear combination of the mean components. The method is based on an application of adapted parametric bootstrap procedures to reduce the bias of the maximum likelihood estimator. The proposed method is likely to lead to estimators with low mean squared error. Simulation results which support this argument are included.

Light adaptation in letter contrast sensitivity: The influence of optical and neural mechanisms

This work discusses the relative significance of optical and neural mechanisms in letter contrast sensitivity under different conditions of environmental lighting. A study was carried out on 26 eyes with normal ocular health. Sixteen lighting conditions were obtained by combining different test luminances (from 10 cd/m2 to 600 cd/m2) and surround luminances (from 1 cd/m2 to 600 cd/m2). The results reveal a significant influence of optical factors (pupil size variations and glare effects) on contrast sensitivity when surround luminance changes, and a dominance of neural effects when test luminance changes. Furthermore, test size and illumination conditions are identified for which letter threshold contrasts are not sensitive to surround luminance changes.

The Selection of the Shrinkage Region in Small Area Estimation

In this article we consider general mixed models to derive small area estimators. The fixed part of the models links the area parameters to the auxiliary variables using a shrinkage region. We show how the selection of the shrinkage region depends on two main factors: the inter-area variation and the correlation coefficient of the auxiliaries with the response.

Equivalence of likelihood ratio tests and obliquity

This paper shows how in a normal population, when the mean holds restrictions given by a right cone, the likelihood ratio test (LRT) for testing a face of that cone is equivalent to another test which is also the LRT for testing the linear subspace associated to the above face against a right cone defined only by those restrictions taking part in the definition of the subspace. Obliqueness is introduced and the equivalence with strict acuteness of a cone is proved, becoming useful to explain the dominance or equivalence of the LRT for testing a face of a cone.

Methodology to evaluate glare effects in corrected ammetropic subjects

Light originated at a glare source and entering the eye, produces a veiling luminance that causes contrast decrease in retinal images and this effect could differ if the subject wears lenses or not. In this work the glare effects in subjects wearing lenses is studied inducing ammetropies in emmetropes. Contrast thresholds of sinusoidal patterns of 2 cpd and 0.5 cd/m² are evaluated without and with glare, the glare source being steady, at 12o and producing 60 lx at the cornea. To exemplify the use of this methodology, 2 emmetropes under 8 different conditions are considered: naked eye; 3 control conditions (wearing neutral lenses) and 4 ammetropic conditions, inducing low (±2 D) and medium (±5 D) myopia and hyperopia with positive and negative contact lenses and correcting them with adequate ophthalmic lenses. The contrast threshold differences between the naked eye and the other 7 conditions are statistically not significant without glare and significant (up to more than 100%) with glare, independently of lens power and probably due to ectopic scattering and multiple reflections. The method proposed enables the determination of the glare effects if lenses are worn though a greater population is required to attain conclusive data.