Nowadays the term dose-response is used in many different contexts and many different scientific disciplines including agriculture, biochemistry, chemistry, environmental sciences, genetics, pharmacology, plant sciences, toxicology, and zoology. In the 1940 and 1950s, dose-response analysis was intimately linked to evaluation of toxicity in terms of binary responses, such as immobility and mortality, with a limited number of doses of a toxic compound being compared to a control group (dose 0). Later, dose-response analysis has been extended to other types of data and to more complex experimental designs. Moreover, estimation of model parameters has undergone a dramatic change, from struggling with cumbersome manual operations and transformations with pen and paper to rapid calculations on any laptop. Advances in statistical software have fueled this development. Key Features: Provides a practical and comprehensive overview of dose-response analysis. Includes numerous real data examples to illustrate the methodology. R code is integrated into the text to give guidance on applying the methods. Written with minimal mathematics to be suitable for practitioners. Includes code and datasets on the book's GitHub: https://github.com/DoseResponse. This book focuses on estimation and interpretation of entirely parametric nonlinear dose-response models using the powerful statistical environment R. Specifically, this book introduces dose-response analysis of continuous, binomial, count, multinomial, and event-time dose-response data. The statistical models used are partly special cases, partly extensions of nonlinear regression models, generalized linear and nonlinear regression models, and nonlinear mixed-effects models (for hierarchical dose-response data). Both simple and complex dose-response experiments will be analyzed.

Nowadays the term dose-response is used in many different contexts and many different scientific disciplines including agriculture, biochemistry, chemistry, environmental sciences, genetics, pharmacology, plant sciences, toxicology, and zoology. In the 1940 and 1950s, dose-response analysis was intimately linked to evaluation of toxicity in terms of binary responses, such as immobility and mortality, with a limited number of doses of a toxic compound being compared to a control group (dose 0). Later, dose-response analysis has been extended to other types of data and to more complex experimental designs. Moreover, estimation of model parameters has undergone a dramatic change, from struggling with cumbersome manual operations and transformations with pen and paper to rapid calculations on any laptop. Advances in statistical software have fueled this development. Key Features: Provides a practical and comprehensive overview of dose-response analysis. Includes numerous real data examples to illustrate the methodology. R code is integrated into the text to give guidance on applying the methods. Written with minimal mathematics to be suitable for practitioners. Includes code and datasets on the book's GitHub: https://github.com/DoseResponse. This book focuses on estimation and interpretation of entirely parametric nonlinear dose-response models using the powerful statistical environment R. Specifically, this book introduces dose-response analysis of continuous, binomial, count, multinomial, and event-time dose-response data. The statistical models used are partly special cases, partly extensions of nonlinear regression models, generalized linear and nonlinear regression models, and nonlinear mixed-effects models (for hierarchical dose-response data). Both simple and complex dose-response experiments will be analyzed.

Many real-world problems are inherently hierarchically structured. The use of this structure in an agent's policy may well be the key to improved scalability and higher performance on motor skill tasks. However, such hierarchical structures cannot be exploited by current policy search algorithms. We concentrate on a basic, but highly relevant hierarchy - the mixed option' policy. Here, a gating network first decides which of the options to execute and, subsequently, the option-policy determines the action. Using a hierarchical setup for our learning method allows us to learn not only one solution to a problem but many. We base our algorithm on a recently proposed information theoretic policy search method, which addresses the exploitation-exploration trade-off by limiting the loss of information between policy updates.

Wissenschaftlicher Aufsatz aus dem Jahr 2011 im Fachbereich BWL - Unternehmensfuhrung, Management, Organisation, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Sprache: Deutsch, Abstract: Diverse Studien zeigen, dass zwischen 40 und 90 Prozent aller neu eingefuhrten Produkte, je nach Branche, nach der Markteinfuhrung scheitern (Gourville, 2006, S. 100). Ernst (2001, S. 2f) beziffert die Misserfolgsquote bei der erfolgreichen Umsetzung und Markteinfuhrung innovativer Produkte sogar auf 50 bis 80 Prozent. Vor diesem Hintergrund gewinnt das Marketing von Innovationen - unternehmensintern wie auch unternehmensextern - immer mehr an Bedeutung. Der Innovationskommunikation fallt hierbei eine Schlusselrolle zu, da uber dieses Instrument die Innovation nicht nur an den potentiellen Anwender, sondern auch an Kooperationspartner etc. herangetragen wird. Im Rahmen dieses Aufsatzes wird zunachst der theoretische Hintergrund zu Innovationskommunikation aufgezeigt. Daruber hinaus wird detailliert auf die externe Innovationskommunikation eingegangen, welche die Verbreitung von Innovationen uber Kommunikationskanale und die Erfolgsfaktoren fur die Kommunikation von Innovationen umfasst. Darauf basierend wurde eine empirische Erhebung durchgefuhrt, welche die Innovationskommunikation uber das Internet und Web 2.0 zum Gegenstand hat. Als Untersuchungsobjekt wurden insgesamt 21 deutsche und auslandische Unternehmen ausgewahlt, die unterschiedlichen Branchen angehoren, ihren Schwerpunkt aber jeweils in der industriellen Fertigung besitzen. Untersucht wurden die Innovationskommunikation anhand der Kriterien Vermittlungsbotschaft, Personifizierung, Gestaltung der Website sowie Integration von sozialen Medien. Die Ergebnisse der Auswertung werden in mehreren Teilergebnissen im Detail dargestellt.