Juan Carlos Abril

Without Statistics it would be impossible to give a satisfactory explanation to a large number of human events, and without it, it would be absolutely impossible to foresee them in all their scope, to guide the criteria with which they are to be judged, to take in time the most conducive measures to avoid or accelerate them, to keep them unchanged or to modify them. It is our main goal to analyze some of the current contents of many initial courses of Statistics as they should be changed and be updated immediately. A very important point to take into account is that this type of course is usually in some cases the first and sometimes the only course of statistics that students see during their degree training. We have the responsibility to offer the best and most up to date material, thus fulfilling the premise that universities should always be at the forefront of knowledge.

Este trabajo se inicia con un breve estudio de la evolucion de las tecnicas para analizar series de tiempo. Lego se pasa al analisis de la correlacion serial, los modelos ARMA, ARIMA y otros no estacionarios hasta alcanzar los metodos de Box y Jenkins de identificacion, estimacion, control y prediccion. Se sigue con un estudio econometrico de las series cronologicas. Luego se presenta el analisis en el dominio de las frecuencias. A continuacion el estudio se centra en el enfoque de espacio de estado con aplicaciones del filtro y suavizador de Kalman. Finalmente se estudia el problema de la volatilidad, tanto en el enfoque de los modelos ARCH-GARCH (y sus variantes) como de los modelos de volatilidad estocastica. En todos los casos se presentan ejemplos practicos con uso intensivo de paquetes de computacion muy actuales.

We generate a time series with the following characteristics using Monte Carlo methods: a) series with distributions that are a combination of the two normal distributions with different variances, b) series that satisfy volatility models, c) series that satisfy an AR(1) model but with contaminated errors which follow the same distribution as the mixes given in a) and d) series that follow the same distribution as the mixes given in a) but with conditional heterocedasticity. We can see from the analysis that identifying the actual generation mechanism of the series in practise is difficult. In fact, the processes resulting from distribution mixes are very similar to the ones that satisfy the volatility scheme. We use the usual tools in the identification phase of any time series, such as series diagrams, histograms, the corresponding sampling distributions, correlograms, and partial correlograms, as well as the corresponding theoretical considerations.

The stylized facts of macroeconomic time series can be presented by fitting structural time series models. Within this framework, we study the behaviour of the gross national product of Argentina in the long run and provide a method for modelling this behaviour, which in turn is equivalent to establishing the stylized facts associated with these time series. We analyse the annual data of the gross national product and the gross national product per capita of Argentina from 1875 to 1999. The study of these variables allows, among other things, to know the changes that have been taking place in the economy. The evolution of these variables in time tells us, roughly, if there was progress or not.

Continuando una línea de investigación iniciada en 1998, en el presente trabajo se realiza un estudio estadístico bivariado de series de radiación promedio y temperatura promedio diarias empleando la metodología del análisis estructural, introducidos por estadísticos comtemporáneos. Se presenta un modelo de correlación entre ambas series para poder generar sintéticamente valores de radiación diarios a partir de valores de temperaturas diarias, efectuando pronósticos con una alta confiabilidad (95%).Following a research line that began in 1998, in this paper a statistical bivariate correlation between diary average radiation an temperature study is done by using the structural analysis methodology, introduced by actual contemporary statisticians. A correlation model between the two variables is presented to generated syntethic diary radiation values from diary temperature values, being able to make forecasting with a high confidential level (95%).Tema 11: Radiación solar y clima.Asoc...

El Profesor James Durbin ha fallecido en la tarde del sábado 23 de Junio de 2012, en Londres, a la edad de 88 años. El Profesor Durbin fue una de las figuras más importantes de la Estadística. Sus contribuciones cubren áreas de muestreo, teoría de las distribuciones, estadística no paramétrica, procesos estocásticos, y por sobre todo series de tiempo y econometría. Por su trascendencia científica, sus aportes a la Estadística y por la gran amistad de más de 38 años que me unía a él, presento este homenaje en donde se resaltan la trayectoria y la personalidad del Profesor Durbin, y sus importantes contribuciones a la ciencia.Professor James Durbin has died in the afternoon of Saturday June 23, 2012, in London, at the age of 88. He was one of the most important figures of Statistics. His contributions cover areas of sampling, theory of distributions, nonparametric statistics, stochastic processes, and above all time series and econometrics. For his scientific significance, his contrib...

El Mercado Eléctrico Mayorista (MEN) en la Argentina está regulado por ley. Según la normativa vigente, el MEN es el ámbito donde se encuentran en tiempo real la oferta y la demanda de energía eléctrica de la República Argentina. Todos los generadores de energía deben ...

The stylized facts of macroeconomic time series can be presented by fitting structural time series models. Within this framework, we study the behaviour of the gross national product of Argentina in the long run and provide a method for modelling this behaviour, which in turn is equivalent to establishing the stylized facts associated with these time series. We analyse the annual data of the gross national product and the gross national product per capita of Argentina from 1875 to 1999. The study of these variables allows, among other things, to know the changes that have been taking place in the economy. The evolution of these variables in time tells us, roughly, if there was progress or not.

In this work a general method is developed for handling non-Gaussian observations in linear state space time series models and this is applied to the special case in which the observations come from exponential family distributions. The method is based on the idea of estimating the state vector by its posterior mode. Let ∼ be the vector ) ,..., ( 1 〈 ∼〈 ∼〈 n and let ) | ( n Y p ∼ be the conditional density of ∼ given the whole sample n Y . The posterior mode estimate (PME) of ∼ is defined to be the value ∼̂ of ∼ that maximises ) | ( n Y p ∼ . When the model is linear and Gaussian, ) | ( ˆ n Y E ∼ Ζ ∼ . When the observations are non-Gaussian, however, ) | ( n Y E ∼ is generally difficult or impossible to compute and to use the mode instead is a natural alternative. More than that, it can be argued that in the non-Gaussian case the PME is preferable to ) | ( n Y E ∼ since it is the value of ∼ which is the most probable given the data. In this respect it can be thought of analogous to ...

The aim of the study was to compare the radiological results at maturity of patients with Legg-Calve-Perthes disease, treated either by a uniform conservative treatment or by an adductor longus tenotomy. The study cohort comprised 349 hips, mean age 4.4 years. Patients were classified in two different groups depending on the treatment performed. The conservative group (Group I) consisted of 318 hips that had been treated by physical therapy and abduction cast/brace, with a mean age 4.3 years (range 1-10). The tenotomy group (Group II) consisted of 31 hips (treated conservatively but developed an adduction contracture limited to 30°), which had been treated by adductor longus tenotomy with a mean age of 6.2 years (range 2-9). Hip range of motion and radiographic studies were performed at the time of admission. The extent of femoral epiphyseal involvement was assessed at each follow-up by the method of Herring. The final outcomes were assessed at skeletal maturity according to the Stulberg classification system. Only one patient (two hips) from Group II experienced an improvement in abduction, which was maintained throughout the follow-up until complete the healing of Legg-Calvé-Perthes disease was achieved. In the remaining 29 hips, we observed a progressive loss of ROM previous to 4.3 months from the tenotomy. According to the Stulberg classification, we did not find differences between both groups at final follow-up (p > 0.05). These preliminary data suggest that the isolated tenotomy of the adductor longus tendon does not modify the natural evolution of Legg-Calvé-Perthes disease.

... 440 JUAN CARLOS ABRIL ... y que ya por terminar, pero sin agotar por supuesto la cantidad de referencias que podríamos citar, José Ángel Valente posee un ... época data también la traducción de El empleo del tiempo, de Michel Butor, un autor del nouveau roman que entonces ...

Controversy exists regarding the possibility of predicting hip reducibility in the congenitally dislocated hip, with arthrography still regarded as the gold standard in this situation. This study aims at assessing the degree of concordance between ultrasonography and arthrography in the detection of anatomic elements obstructing hip reduction. Forty-nine hips were studied both by ultrasonography and arthrography. Three anatomic sources of obstruction to reduction were assessed in each hip: ligamentum teres hypertrophy, inverted labrum, and the presence of soft tissue in the acetabulum. For each variable, congruence between ultrasound and arthrography was measured by kappa analysis. Values > 0.40 expressed sufficient concordance, and they were detected with regard to inverted labrum and the presence of soft tissue in the acetabulum. The results of this study suggest that ultrasonography may be considered a reliable technique for the prediction of the main causes of obstruction in the congenitally dislocated hip, such as inverted labrum and soft tissue in the acetabulum.

The problem of unit roots in time series has become the centre of many papers in theoretical and applied econometric. It has its own interest for theoretical researchers due to the asymptotic effects over the properties of estimators and tests statistics. For the applied work, establishing the presence of unit roots is still the cornerstone of the analysis of possible

Abstract. First we obtain a convenient way of expressing the determinant of the difference between an identity matrix and some products of Toeplitz matrices. Then, using these results, we show that for a large number of normal processes there exist some quadratic forms whose matrices are of Toeplitz type such that their joint density admits an Edgeworth expansion.

The problem of unit roots has been the centre of attention of many works on theoretical and applied statistics and econometrics. This subject has its own intrinsic interest because of the various implications on the properties of the tests and estimators. For the applied worker, establishing the presence of unit roots remains a keystone in the analysis of possible cointegrated systems: firstly, as a preliminary tool to test the integration of the variables of interest and secondly as a cointegration test on its own. On this work, we start with the model ,1 , 2, , , 1 yy t n tt t =ρ +ε = − "

The aim of this study was to determine the benefits of cystography in the management of a simple bone cyst, its implication in the final result of the treatment after corticoid intracystic injections, and the presence of secondary effects. We retrospectively reviewed 42 patients diagnosed with a simple bone cyst. Cystography was performed before the corticoid injection. The presence or absence of loculation intracyst and the existence and number of venous outflows were determined. According to the venous drainage, cysts were classified as type 0 when a venous outflow did not exist and as type 1 when there was a rapid venous outflow (<3 min). The treatment protocol included a maximum of three corticoid injections at an interval of 6 months. Healing of the cyst was determined on the basis of Neer's criteria. Secondary effects and surgical complications were assessed. Cystography studies showed a unicameral bone cyst with absent loculation in 16 cases (37.3%), whereas the lesion showed multiloculation in 26 cases (62.7%). There was no statistical difference between loculation intracyst (present or absent) and the final outcomes of the 42 cysts treated with a steroid injection (P=0.9). Cystography showed a negative venogram in 10 cases (23.8%), whereas the cysts showed a rapid venous outflow in 32 cases (76.2%). On the basis of Neer's classification, all patients with a negative venogram achieved complete healing of the cyst. Patients with a rapid venous outflow achieved complete healing in 14 cases (Neer I). In two patients, the healing was incomplete at the end of the follow-up period (Neer IV). In most cases (21 cysts), healing was partial (Neer II). Five patients showed a recurrence after initial healing of the cyst (Neer III) (P<0.05). The number or the size of veins did not affect healing of a bone cyst (P=0.6). Two patients with a rapid venous outflow showed a generalized hypertrichosis after the first injection of corticosteroids. Sex and age at the initiation of the first injection were not significant factors of healing (P=0.4). The average follow-up time was 59 months (24-60 months). Cystography provides morphological and functional information of simple bone cyst. It is a useful test before the administration of percutaneous injections of sclerosing substances. It facilitates the differentiation of cysts that may achieve complete healing (negative venogram) from those that tend to show recurrence (rapid venous outflow). Therapeutic material should be introduced slowly and a second trocar should always be placed to decrease the risk of migration in cysts with communication with the venous system.

Management of osteochondritis dissecans of the femoral condyle in children remains uncertain. The aim of this study was to determine the presence of a perilesional sclerotic ring in radiologic examination and to establish its value for prognosis. We retrospectively reviewed 85 patients diagnosed with osteochondritis dissecans. The population was distributed according to the grade of perilesional radiologic sclerosis: stage 0, patients who did not show a sclerotic rim in the anteroposterior and the lateral views; stage I, patients with marginal sclerosis only in 1 radiologic view; stage II, patients with sclerosis in both views. Patients were also distributed in different age groups: group 1, children under 12 years of age; group 2, children between 12 and 15 years of age; and group 3, children more than 15 years of age. These groups were correlated with the stage of perilesional sclerosis. Radiologic results were analyzed according to the Hughston scale after conservative or surgical treatment of the lesion. Lesions without perilesional sclerosis (stage 0) were cured in all the cases, with good results by means of conservative treatment (P<0.05). In patients with stage I or II perilesional sclerosis, the percentage of healing was smaller; in these cases, surgical treatment improved the results compared with those in which conservative treatment was used (P<0.05). Children under 12 years of age showed less perilesional sclerosis and more tendencies to spontaneous healing than those more than 15 years of age. In these patients, radiologic sclerosis is greater (P<0.05). The presence of a sclerotic rim in the osteochondritis dissecans lesions of the knees in children is considered a prognostic indicator of the process. Lesions without sclerosis show a tendency toward spontaneous recovery with conservative treatment. Lesions with perilesional sclerosis show worse evolution, and treatment with perforations is still essential for enhancement of healing. Prognostic study, Level II (retrospective study).

Chronic recurrent multifocal osteomyelitis (CRMO) is a disease of children and young adults. Clinically, the disease is characterized by the insidious onset of local pain and swelling in affected bones. Its course is one of intermittent periods of exacerbation and remission with successive bones affected. The pathogenesis of CRMO remains unknown, although an autoinflammatory disorder may be the cause, with inflammation of bone. This lesion is radiologically characterized as multiple lucencies surrounded by defined zones of patchy but dense sclerosis, cortical thickening from periosteal new bone formation, and increased bone size with different bones involved. Multiple therapeutic regimens had shown only a partial or temporary response. Because indomethacin has been successfully applied in inhibition of ossification and inflammatory processes, we initiated therapy with indomethacin in patients with CRMO. We report on the cases of 5 patients who responded dramatically to treatment with indomethacin. All underwent progressive clinical improvement (mean, 2.8 months). Radiological lesions disappeared after a mean period of 10.5 months. In 1 case where treatment was started late, small osteolytic zones persisted but with no clinical consequences. There were no additional recurrences or new bones affected during follow-up period (mean, 4 years). Our observation indicates that indomethacin may be an effective treatment for CRMO.