Pharmaceutical Benefits Advisory Committee
Glossary of M terms
Glossary to accompany the November 1995 edition of the Guidelines for the Pharmaceutical Industry on Preparation of Submissions to the Pharmaceutical Benefits Advisory Committee: including major submissions involving economic analyses
The therapy which most prescribers will replace with the proposed drug.
The indication likely to account for the largest proportion of patients treated with the proposed drug.
An analytical technique that examines the extra costs and outcomes caused by producing and providing one extra unit of a resource.
Marginal benefit (utility)
The extra benefit (utility) caused by providing one extra unit of a resource.
The extra cost of producing one extra unit of a resource.
The maximum amount that an individual is willing to pay for one extra unit of a resource or for the extra outcome(s) resulting from its provision.
Markov chain process
An iterative decision analysis model that represents the changes in the proportions of individuals who are in different discrete health states based on constant probabilities of remaining in each state or transiting to another state at the end of each successive time period.
Mask/masking (see blind/blinding)
A measure of central tendency. The arithmetic average which is computed by adding all the individual values in the group and dividing by the number of values in the group.
The procedure of applying a standard scale to a variable or a set of values.
A measure of central tendency. The exact midpoint of a distribution of data that is ordered from highest to the lowest value.
Meta-analysis (Appendix G)
The systematic, organised, and structured evaluation of a problem of interest using information from all relevant independent randomised trials. It includes a qualitative component (application of predetermined criteria of scientific rigour, eg Appendix B) and a quantitative component (statistical combination of the data which can be pooled).
Modelled economic evaluation
Economic evaluation using modelling when trial data are insufficient.
An analytical technique using simulated processes to explain the impact of one or more factors on a number of outcomes.
Monte Carlo simulation
Computer experiments of complex relationships that simulate and analyse sequences of events using random numbers controlled by a specified distribution function.
The simultaneous comparison of more than two sets of results from one trial. The statistical analysis should be adjusted to account for the increasing chance that a result will have a p-value less than 0.05.