Design of Clinical Trials

The essential feature of controlled clinical trials is the random assignment of subjects to two or more treatment groups under investigation. The principle of randomization provides a protection against hidden biases and thus increases the validity of the trial’s findings.

In recent years, there has been an increasing interest, in the context of clinical trials research, in response-adaptive designs. This is because response-adaptive designs are sequential procedures that can skew, along the experiment, the allocation probabilities of statistical units on the base of previous allocations and responses. In a clinical trial to compare two or more treatments, the experimenter faces two simultaneous goals: collecting evidence to determine the superior treatment, and skewing the allocations toward the superior treatment in order to reduce the proportion of patients that receive the worst treatment. The first is an inferential goal and concerns future patients’ interest; the second is an ethical responsibility and concerns the current study patients’ interest.

Methodologies & Results

In particular the group is involved in the study of:

  • urn models for response adaptive designs for targeting the best treatment;

  • response adaptive designs with prespecified allocations;

  • statistical properties of reinforced urn models.



Related Publications & Pre Prints

Aletti G., Ghiglietti A., Vidyashankar A.N. (2018)
Dynamics of an adaptive randomly reinforced urn.
Bernoulli, vol. 24, 3, 2204-2255.

Aletti G., Ghiglietti A., Rosenberger W.F. (2017)
Nonparametric covariate-adjusted response-adaptive design based on a functional urn model.
The Annals of Statistics, Forthcoming paper.

Aletti, G., Crimaldi, I., Ghiglietti A. (2017)
Networks of reinforced stochastic processes: asymptotics for the empirical means.
Technical report, arXiv:1705.02126.

Aletti, G., Crimaldi, I., Ghiglietti A. (2017)
Synchronization of reinforced stochastic processes with a network-based interaction.
The Annals of Applied Probability, vol. 27, 6, 3787-3844.

Ghiglietti A., Scarale M.G., Miceli R., Ieva F., Mariani L., Gavazzi C., Paganoni A.M., Edefonti V. (2017)
Urn models for response-adaptive randomized designs: a simulation study based on a non-adaptive randomized trial.
Technical report, MOX-report: 16/2017.

Ghiglietti A., Vidyashankar A.N., Rosenberger W.F. (2017)
Central limit theorem for an adaptive randomly reinforced urn model.
The Annals of Applied Probability, vol. 27, 5, 2956-3003.

Aletti G., Ghiglietti A. (2017)
Interacting generalized Friedman’s urn systems.
Stochastic Processes and their Applications, vol. 127, 8, 2650-2678.

Ghiglietti A., Paganoni A.M. (2016)
An urn model to construct an efficient test procedure for response adaptive designs.
Statistical Methods and Applications, vol. 25, 2, 211-226.

Ghiglietti A., Paganoni A.M. (2014)
Statistical properties of two-color randomly reinforced urn design targeting fixed allocations.
Electronic Journal of Statistics, vol. 8, 708-737.

Aletti G., Ghiglietti A., Paganoni A.M. (2013)
Randomly reinforced urn designs with prespecified allocations.
Journal of Applied Probability, vol. 50 no. 24 486-498.



Dr Andrea Ghiglietti, PhD Thesis in Mathematical Engineering (2014)
Statistical properties of urn models in response-adaptive designs.

Dr Andrea Ghiglietti, MD Thesis in Mathematical Engineering (2010)
Modelli d’urna per il disegno adattivo di esperimenti clinici.

Dr Giovanni Cassarini, BD Thesis in Mathematical Engineering (2009)
Disegni sperimentali adattivi per studi clinici: modelli d’urna a rinforzo aleatorio modificato.

Dr Francesco Mauri, Dr Luca Rezzonico, BD Thesis in Mathematical Engineering (2008)
Modelli adattivi negli studi clinici: analisi di un caso reale

Dr Stefano Baraldo e Dssa Laura Azzimonti, BD in Mathematical Engineering (2007)
Sistemi di urne interagenti e teoria dei valori estremi applicati alla modellizzazione della crescita tumorale: teoria e simulazioni.

Dr Valeria Vitelli, BD Thesis in Mathematical Engineering (2006)
Disegni sperimentali adattivi alla risposta nella ricerca clinica

Dr Valeria Pedrina, BD Thesis in Mathematical Engineering (2005)
Tecniche di randomizzazione negli studi clinici



  • SMSA 2017. Berlin, Germany, 20-24 February, 2017.
    Talk (Invited): A functional urn model for CARA designs.
  • mODa 2016. Hamminkeln Dingden, Germany, 13-17 June, 2016.
    Talk (Invited): Asymptotic Properties of an Adaptive Randomly Reinforced Urn model.
  • SIS 2016. Fisciano (Italy), 8-10 June, 2016.
    Talk: Adaptive Randomly Reinforced Urn design and its asymptotic properties.
  • IWS 2015. Vienna (Austria), 21-25 September, 2015.
    Talk (Invited): An adaptive randomly reinforced urn model with random thresholds.
  • Statalk 2014. Milan (Italy), 24 April, 2015.
    Talk (Invited): Urns, Coins and Clinical Trials.
  • SIS 2014. Cagliari (Italy). June, 11-14, 2014
    Talk: Statistical properties of urn designs in clinical trials.
  • S.Co 2013. Milan (Italy), September 9-11, 2013
    Talk: Asymptotic statistical properties of a response adaptive design based on a two colours urn model.
  • mODa 2013. Lagow Lubusky (Poland), 10-14 June, 2013.
    Talk (Invited): Randomly reinforced urn designs whose allocation proportions converge to arbitrary prespecified values.
  • IWS 2013. Rimini (Italy), 21-25 May, 2013.
    Talk (Invited): Randomly reinforced urn designs with prespecified allocations.
  • SIS 2012. Rome (Italy), 20-22 June, 2012.
    Talk: Randomly reinforced urn designs whose allocation proportions converge to arbitrary prespecified values