A piecewise-constant Markov model and the effects of study design on the estimation of life expectancies in health and ill health

van den Hout, Ardo; Matthews, Fiona E.
April 2009
Statistical Methods in Medical Research;Apr2009, Vol. 18 Issue 2, p145
Academic Journal
Multi-state models are frequently applied to describe transitions over time between three states: healthy, not healthy and death. The three-state model can be used to estimate life expectancies in health and ill health. In this article, continuous-time Markov models are specified for the transitions between the three states. Transition intensities are regressed on age as a time-dependent covariate. The covariate is handled in a piecewise-constant fashion where the time interval between two consecutive observations is divided into subintervals of fixed and equal lengths. Study design choices such as sample size, length of follow-up, and time intervals between observations are investigated in a simulation study. The effects on parameter estimation are discussed as well as the effects on the estimation of life expectancies. In addition, data taken from the UK Cognitive Functioning and Ageing Study are analysed.


Related Articles

  • Women continue to enjoy longer life.  // Personnel Today;11/29/2005, p59 

    This article reports that women will continue to outlive men in Great Britain as the lifespan increases. According to figures from the government's actuary department, boys and girls born in 2004 can expect, on average, to live until they are 77 and 81 years of age, respectively. This contrasts...

  • Relating changes in life expectancy to changes in mortality. Alho, Juha M.; Alho, J M // Demography;Nov1989, Vol. 26 Issue 4, p705 

    I address the problem of what can be said of changes in mortality rates, if one knows how life expectancies change. I note a general formula relating life expectancies in different ages to mortality and prove that if mortality changes over time following a proportional-hazard model, then there...

  • On the decomposition of changes in expectation of life and differentials in life expectancy. Pollard, J. H. // Demography;May1988, Vol. 25 Issue 2, p265 

    The projection of mortality rates requires inter alia close examination of the mortality experience of a population over a long period of time and will usually also involve the analysis of mortality trends by cause of death. In two of the more important recent contributions, techniques were...

  • Hormesis in Caenorhabditis elegans dauer-defective mutants. Cypser, James R.; Johnson, Thomas E. // Biogerontology;Aug2003, Vol. 4 Issue 4, p203 

    We have shown that increased longevity and stress resistance can be induced by sub-lethal exposure to stressors (hormesis). Here we ask whether genes of the dauer formation pathway that are known to modulate life span in Caenorhabditis elegans are required for this hormesis. We find that...

  • 100.  // Better Nutrition;Mar2005, Vol. 67 Issue 3, p16 

    The article reports that life expectancy at birth could reach 100 in the next 60 years. Worldwide, life expectancy for those living in developed countries has more than doubled over the past 200 years.

  • Constant global population with demographic heterogeneity. Cohen, Joel E. // Demographic Research;Jan/Jun2008, Vol. 18, p409 

    To understand better a possible future constant global population that is demographically heterogeneous, this paper analyzes several models. Classical theory of stationary populations generally fails to apply. However, if constant global population size P(global) is the sum of all country...

  • Smoking more harmful to women. Pati, Anita // GP: General Practitioner;4/29/2005, p20 

    The article presents a research which states that smoking cuts the life expectancy of a 30-year-old woman by seven years and shaves five and a half years off the life of a 30-year-old man. The figures come from life insurance data published by the Actuarial Profession's Continuous Mortality...

  • OPTIMUM VALUES OF LIFE TABLE FUNCTIONS. Mitra, S. // Canadian Studies in Population;1977, Vol. 4, p61 

    It is known that the function I, has a steep negative slope at age zero and the steepness continues to diminish till It becomes smallest at some age and begins to increase thereafter. Similarly, the force of mortality μx assumes a minimum value and the life expectancy &ering;x attains a...

  • Health Expectancy in Canada, Late 1970s: Demographic, Regional, and Social Dimensions. Wilkins, Russell; Adams, Owen B. // American Journal of Public Health;Sep83, Vol. 73 Issue 9, p1073 

    Based on estimates of activity restriction from the Canada Health Survey. institutional data on long-term care, and survival data from vital statistics, we have calculated an index of health expectancy (life expectancy in each state or health), and a summary of these indices which we have called...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics