Search

Biosimilars are medical products that are developed as copies of already established, large molecule drugs (biologics). For gaining approval, sponsors have to confirm that the proposed biosimilar has the same efficacy and safety as the originator product. This comparability exercise includes also, in most cases, that large clinical trials are conducted in patients. However, even with the evidence gained during the clinical studies, there is still some uncertainty if patients who were already treated with the originator can be switched to the biosimilar or if even multiple switches between the biosimilar and the originator are acceptable. A simple way to address the question of switchability is the estimation of so-called mixed and self-carryover effects, which are carryover effects that not only depend on the treatment in the current period, but also on the treatment in the previous period. In this paper, we determine universally optimal designs for the estimation of mixed-carryover effects in a linear model with treatment, period, subject and self-carryover as nuisance parameters., Discussion Paper / SFB823;3/2018

Biosimilars are copies of biological medicines that are developed by a competitor after the patent for the originator drug has expired. Extensive clinical trials are required to show therapeutic equivalence between the biosimilar and its reference product before a biosimilar can be sold on the market. However, even after more than 10 years of experience with biosimilars in Europe, there is still some uncertainty if the patients who are already taking the reference product can switch between the biosimilar and its reference product. One convenient way to assess the impact of switches is the analysis of mixed and self carryover effects: if the products are switchable, there should not be any difference in the carryover effects. This paper determines a series of simple designs which are highly efficient for the comparison of the mixed and self carryover effects of two treatments. The proof of efficiency is not straightforward because the information matrix of the efficient designs is not completely symmetric., Discussion Paper / SFB823;8/2018

We determine optimal crossover designs for the estimation of direct treatment effects in a model with mixed and self carryover effects. The model also assumes that the errors within each experimental unit are correlated following a stationary firrst-order autoregressive process. The paper considers situations where the number of periods for each experimental unit is at least four and the number of treatments is greater or equal to the number of periods., Discussion Paper / SFB 823;51/2013

In this paper we investigate the problem of designing experiments for weighted least squares analysis in the Michaelis Menten model. We study the structure of exact D-optimal designs in a model with an autoregressive error structure. Explicit results for locally D-optimal are derived for the case where 2 observations can be taken per subject. Additionally standardized maximin D-optimal designs are obtained in this case. The results illustrate the enormous difficulties to find exact optimal designs explicitly for nonlinear regression models with correlated observations., Discussion Paper / SFB 823;04/2012

Ziel unseres Projektes ist die statistische Analyse der bisher wenig erforschten asymmetrischen inkrementellen Blechumformung (AIBU). Ein elementares Problem hierbei ist die Quanti zierung der Qualität eines gefertigten Bauteils. Da der AIBU-Prozess ein inkrementeller Prozess ist, spielt die Qualität der gesamten dreidimensionalen Geometrie des Fertigteils eine Rolle. Nur wenn sie gänzlich quanti ziert werden kann, ist eine Untersuchung der Prozessdynamik möglich. Die dreidimensionale Vermessung des Fertigteils ist jedoch mit den herkömmlichen (taktilen) Messmethoden nur schwer möglich, daher stellen wir in diesem Diskussionspapier ein Verfahren zur Aufbereitung von optischen Messdaten vor, welches eine solche Analyse ermöglicht. Hierbei wird die Geometrie der Bauteile zunächst optisch komplett vermessen. Aufbauend auf diesen Messungen werden in einem mehrstu figen Ansatz die Messdaten mittels statistischer Methoden aufbereitet, um Artefakte heraus zu filtern, Ober- und Unterseiten zu trennen und schließlich auch die Wandstärken zu bestimmen. Kennt man die exakte Geometrie des Fertigteils und dessen Wandstärke über die gesamte Oberfläche, können hieraus leicht Qualitätskennzahlen errechnet werden. In Kapitel 2 werden zunächst die prozesstechnischen Grundlagen der AIBU und deren Prozessparameter und Einflussfaktoren eingeführt. In Kapitel 3 wird das in diesem Papier verwendete Experiment und die Messmethodik erklärt. Das Kapitel 4 befasst sich dann detailliert mit den einzelnen Schritten der Messdatenaufbereitung. Das letzte Kapitel diskutiert die Reproduzierbarkeit und Verlässlichkeit der vorgestellten Methode., Discussion Paper / SFB 823;51/2011

Kunert and Martin (2000) determined optimal and efficient block designs in a model for fi eld trials with interference effects, for block sizes up to 4. In this paper we use Kushner's method (Kushner, 1997) of fi nding optimal approximate designs to extend the work of Kunert and Martin (2000) to optimal designs with five or more plots per block. We give an overall upper bound a_(t,b,k) for the trace of the information matrix of any design and show that an universally optimal approximate design will have all its sequences from merely four di fferent equivalence classes. We further determine the efficiency of a binary type I orthogonal array under the general phi_p-criterion. We find that these designs achieve high efficiencies of more than 0.94.

Conclusion I - basics: -good acceptance of organic and conventional food by young children Conclusion II - further aim: -nutrition behaviour shows some hints at preferences, but food characteristics seem to be the main drivers for sensory preference Conclusion III - main results - weaning food history gives some hints at influence on later preferences, but breastfeeding history shows no apparent influence on preferences at ages of 2-7 years

Preference testing is a good method for this age-group to get a decision from children. Children have fun in tasting samples and give serious answers [shown with mimic and gestic]. Preference testing with young children should only be applied, if differences in samples are big enough. Recommendation: First Sensory Profiling [panel], then difference testing [children]. Summarized, evaluation shows no generally differences in the 4 chosen breast-feeding history types. In this study many other connections with answers of questionnaires and DONALD-data are possible, partly already done or will be evaluated in future. It seamed that the cultivation method [organic or conventional] is not responsible for the child perception.

In the common linear and quadratic regression model with an autoregressive error structure exact D-optimal designs for weighted least squares analysis are determined. It is demonstrated that for highly correlated observations the D-optimal design is close to the equally spaced design. Moreover, the equally spaced design is usually very efficient, even for moderate sizes of the correlation, while the D-optimal design obtained under the assumptions of independent observations yields a substantial loss in efficiency. We also consider the problem of designing experiments for weighted least squares estimation of the slope in a linear regression and compare the exact D-optimal designs for weighted and ordinary least squares analysis. AMS Subject Classification: 62K05

Shear forming is a versatile process for manufacturing complex lightweight components which are required in increasing numbers by many different industries. Inherent advantages of the process are simple tooling, low tool costs, good external and internal surface quality, close dimensional accuracy, and good mechanical properties of the components. In times of free market economy, it is necessary to on the one hand fulfill the increasing demands toward the quality characteristics and on the other hand to reduce the development time needed to manufacture such a high quality component. Since shear forming is a complex and sensitive process in terms of deformation characteristics this is not an easy task. To assess the overall quality of a component several, mutually contradictory, quality characteristics have to be considered simultaneously. While conventionally each characteristic is considered separately, in this paper, a statistical approach is presented which copes with the above mentioned demands and provides the opportunity for an efficient, multivariate optimisation of the process. With a minimum of statistically planned experiments, mathematical models are derived which describe the influence of the machine parameters and their interactions on quantitative as well as qualitative component characteristics. A multivariate optimisation procedure based on the concept of desirabilities is used to find the best compromise between the mutually contradictory quality characteristics. With this statistical approach a workpiece for electrical industry is manufactured which requires a very good surface quality and close geometrical tolerances.

The response from a factorial experiment carried out in a time sequence may be affected by uncontrollable variables that are highly correlated with the time in which they occur. In such a situation, one possibility is to randomize the run order of the experiment. Another possibility is to use a systematic run order that is robust against time-trends. Since randomized run orders make the time trend part of the error, it can be hoped that systematic run orders will be more effective to identify truly active factors. In this paper, a imulation study is used to compare the performances of the randomized and the systematic run orders. The response from an experiment where we have observed a strong time-trend is used to demonstrate the influence of a realistic time trend on the run orders under consideration. The performance of the run orders is then measured by taking the probabilities of false rejection and the probabilities of detection of active contrasts. Our results show that the randomized run order managed to keep the nominal level, while the systematic did not. Additionally, when there were active factors, then the systematic run orders did not achieve more power than did the randomized run order.

The response from a factorial experiment carried out in a time sequence may be affected by uncontrollable variables that are highly correlated with the time in which they occur. In such a situation, one possibility is to randomize the run order of the experiment. Another possibility is to use a systematic run order that is robust against time-trends. Since randomized run orders make the time trend part of the error, it can be hoped that systematic run orders will be more effective to identify truly active factors. In this paper, a simulation study is used to compare the performances of the randomized and the systematic run orders. The response from an experiment where we have observed a strong time-trend is used to demonstrate the in uence of a realistic time trend on the run orders under consideration. The performance of the run orders is then measured by taking the probabilities of false rejection and the probabilities of detection of active contrasts. Our results show that the randomized run order managed to keep the nominal level, while the systematic did not. Additionally, when there were active factors, then the systematic run orders did not achieve more power than did the randomized run order.

Shear forming is a versatile process for manufacturing complex lightweight components which are required in increasing numbers by many different industries. Inherent advantages of the process are simple tooling, low tool costs, good external and internal surface quality, close dimensional accuracy, and good mechanical properties of the components. In times of free market economy, it is necessary to on the one hand fulfill the increasing demands toward the quality characteristics and on the other hand to reduce the development time needed to manufacture such a high quality component. Since shear forming is a complex and sensitive process in terms of deformation characteristics this is not an easy task. To assess the overall quality of a component several, mutually contradictory, quality characteristics have to be considered simultaneously. While conventionally each characteristic is considered separately, in this paper, a statistical approach is presented which copes with the above mentioned demands and provides the opportunity for an efficient, multivariate optimisation of the process. With a minimum of statistically planned experiments, mathematical models are derived which describe the influence of the machine parameters and their interactions on quantitative as well as qualitative component characteristics. A multivariate optimisation procedure based on the concept of desirabilities is used to find the best compromise between the mutually contradictory quality characteristics. With this statistical approach a workpiece for electrical industry is manufactured which requires a very good surface quality and close geometrical tolerances.

In sensory experiments, often designs are used that are balanced for carryover effects. It is hoped that this controls for possible carryover effects, like, e.g., a lingering taste of the products. Proper randomization is essential to guarantee the usual model assumption of independent identically distributed (i.i.d.) errors. We consider a randomization procedure that permutes treatment labels and assessors. This restricted randomization leaves the neighbour structure unchanged and validates the assumption of i.i.d. errors if the design used is a Generalized Youden Design (GYD). However, the use of a neighbour balanced GYD may require too many assessors. The question arises, whether nearly balanced designs may be used without grossly violating the validity of the analysis. We therefore do a simulation study to assess the properties (under this restricted randomization) of nearly balanced designs like, e.g., the ones proposed by Périnel and Pag's (2004, Food Quality and Preference 15, 439-446). We observe that, if there are no carryover effects, the variance estimates for treatment contrasts are not significantly biased whenever we use designs that are nearly GYD. Additionally, designs that are nearly carryover balanced still produce conservative variance estimates, even in the presence of large carryover effects. In all, 'nearly neighbour balanced nearly GYD' as proposed by Périnel and Pag's (2004) appear to be useful in experimental situations where the use of GYD is too restrictive. It should be stressed, however, that these results are true only if randomization is used as a protection against effects unaccounted for in the statistical model.

The paper deals with a method for the analysis of highly fractionated factorial designs proposed by Raghavarao and Altan (2003). We show that the method will find "active" factors with almost any set of random numbers. Once that an alias set is found active, Raghavarao and Altan (2003) claim that their method can resolve the alias structure of the design and identify which of several confounded effects is active. We show that their method cannot do that. The error in Raghavarao and Altan's (2003) arguments lies in the fact that they treat a set of highly dependent (sometimes even identical) F-statistics as if they were independent.

The paper deals with a method for the analysis of highly fractionated factorial designs proposed by Raghavarao and Altan (2003). We show that the method will find "active" factors with almost any set of random numbers. Once that an alias set is found active, Raghavarao and Altan (2003) claim that their method can resolve the alias structure of the design and identify which of several confounded effects is active. We show that their method cannot do that. The error in Raghavarao and Altan's (2003) arguments lies in the fact that they treat a set of highly dependent (sometimes even identical) F-statistics as if they were independent.

The paper reports a robust parameter design experiment, where we have used Taguchi's product array and a combined array simultaneously. This was done as part of a research project dealing with experimental design to optimise the process of sheet metal spinning. We found that the classical analysis of the product array identified a control factor, which has an influence on the variance of the response. There were no indications of this effect in the combined array. A confirmation experiment supports the finding that this factor in fact is a control factor. It seems that its effect on the variance is due to several two- and three-factor interactions that were not large enough to be found in the combined array. In the authors' opinion this shows that the use of a product array and the classical analysis provides robustness against imprecise model assumptions.