1,720,970 research outputs found
Bayesian methodology for dynamic modelling
No full textWe describe a Bayesian methodology for fitting deterministic dynamic models, demonstrating how this can be used to estimate the uncertainty around model outputs. By its nature, Bayesian statistics allows all available sources of information to be incorporated: prior knowledge of the model parameter values and data corresponding to the model outputs, thus allowing for a thorough analysis of the uncertainty. The methodology is demonstrated with an example: a deterministic compartmental model of tuberculosis and HIV disease. We discuss how this method might be modified to allow a similar analysis of stochastic simulation models
Optimal pricing ladders for the sale of airline tickets
No full textPricing ladders are widely used in the airline industry to define the discrete set of prices that can be charged for seats on a flight. We consider the factors that affect the setting of these ladders for one-way economy tickets. The minimum and maximum fares are assumed to be fixed and we focus on maximising the revenue generated on a flight by changing the spacing of the intermediate fares. Three scenarios are
considered for the market: single flight with perfect market segmentation and imperfect market segmentation and multiple flights on one route
Prior and candidate models in the Bayesian analysis of finite mixtures
No full textThis paper discusses the problem of fitting mixture models to input data. When an input stream is an amalgam of data from different sources then such mixture models must be used if the true nature of the data is to be properly represented. A key problem is then to identify the different components of such a mixture, and in particular to determine how many components there are. This is known to be a non-regular/non-standard problem in the statistical sense and is technically notoriously difficult to handle properly using classical inferential methods. We discuss a Bayesian approach and show that there is a theoretical basis why this approach might overcome the problem. We describe the Bayesian approach explicitly and give examples showing its application
Comparison of simulation output series using bootstrapping
No full textWe describe a method for comparing stochastic outputs of simulation models. The method is distribution-free and allows the comparison of sets of data with different numbers of data points. This makes it ideal for performing comparisons between simulation output and the real output of the system being modelled, when often there are many more data points available from the output of the simulation model than present in the real data. We calculate the two-sample Cramer-von Mises goodness-of-fit statistic between the two sets of data, using bootstrapping to find the distribution of the statistic, and so the probability that the two sets of data were drawn from the same distribution
Impact of combined vector-control and vaccination strategies on transmission dynamics of dengue fever: a model-based analysis
No full textDynamic pricing of airline tickets with competition
No full textCompetition has a huge influence on customer buying behaviour and will impact on the optimal price that companies should charge for goods or services. To date, many dynamic pricing models have not modelled competition explicitly. In this paper, we introduce pricing strategies that maximize revenue when selling an inventory of identical items by a fixed time and where there is a competing seller. The model used incorporates a probabilistic formulation of customer demand, which is influenced by the prices offered by the company and the competitor, and the time remaining until the end of the selling period. Calculus of variations is used to solve the problem and simple conditions are given that ensure the uniqueness of a solution. Illustrative examples are included. A practical implementation that uses dynamic updating is proposed and tested using simulated data, showing the effectiveness of the method
Maximizing revenue in the airline industry under one-way pricing
No full textThe paper describes a methodology that has been implemented in a major British airline to find the optimal price to charge for airline tickets under one-way pricing. An analytical model has been developed to describe the buying behaviour of customers for flights over the selling period. Using this model and a standard analytical method for constrained optimization, we can find an expression for the optimal price structure for a flight. The expected number of bookings made on each day of the selling period and in each fare class given these prices can then be easily calculated. A simulation model is used to find the confidence ranges on the numbers of bookings and these ranges can be used to regulate the sale of tickets. A procedure to update the price structure based on the remaining capacity has also been developed
Revenue management for perishable products using simulation
No full textWe describe a methodology to find the expected number of sales for a given stock of a perishable product, and hence the optimal pricing strategy, over a given finite selling period. The methodology uses a stochastic simulation model that provides confidence ranges on the numbers of sales over the selling period. These ranges are designed to provide warnings to users of unusual buying behaviour. An updating procedure is also described that allows us to quickly update the price structure during the selling period as information about cumulative sales becomes available. We present two examples showing how the optimal price structure is updated during the selling period based on the latest sales data
Incorporating household structure into a discrete event simulation model of tuberculosis and HIV
No full textHuman immunodeficiency virus (HIV) increases the risks of developing tuberculosis (TB) disease followinginfection, and speeds up disease progression. This has had a devastating effect on TB epidemics in sub-SaharanAfrica, where incidence rates have more than trebled in the past twenty years. Current control methods for TBdisease have failed to keep pace with this growth in TB, and there is an urgent need to find TB control strategiesthat are effective in high-HIV prevalent settings. This paper describes a discrete-event simulation model ofendemic TB that includes the effects of HIV and of household structure on the transmission dynamics of TB.Incorporating a social structure allows us to compare the effectiveness of contact-tracing interventions withtargeted case-finding at high risk groups. We describe the modeling of the household structure in some detail, asthis has applications to the modeling of other infectious diseases
- …
