Polynomial analysis is an extension of simple linear regression, where a model is used to allow for the existence of a systematic dependence of the dependent y variable (blood pressure) on the independent x variable (time) different from a linear dependence. Polynomial extension from the basic model can be done as follows:
y = a + bx (first order) linear relationship
y = a + bx + cx2 (second order) parabolic relationship
y = a + bx + cx 2+ dx3 (third order) hyperbolic relationship
y = a + bx + cx2 + dx 3 + ex 4 (fourth order) sinusoidal relationship
where a is the intercept and b, c, d, and e are the partial regression coefficients. Statistical software can be used to calculate for the data the regression line that provides the best fit for the data. In addition, regression lines of higher than 4 orders can be calculated. Fourier analysis is a more traditional way of analyzing these type of data, and is given by the function f(x) = p + q1 cos (x) + ..+qn cos n (x) + r1 sin (x) +..+ rn sin n (x) with p, q1…q n, and r1…rn = constants for the best fit of the given data.
As an example, ambulatory blood pressure monitoring (ABPM) using light weight automated portable equipment is given. ABPM has greatly contributed to our understanding of the circadian patterns of blood pressures in individual patients1 as well as to the study of effects of antihypertensive drugs in groups of patients.2 However, a problem is that ABPM data using mean values of arbitrarily separated daytime hours are poorly reproducible3,4, undermining the validity of this diagnostic tool. Previous studies have demonstrated that both in normo-5 and in hypertensive groups6 time is a more powerful source of variation in 24 hour ABPM data than were other sources of variation (between P<0.01 and <0.001 versus between not significant and <0.01). This reflects the importance of the circadian rhythm in the interpretation of ABPM data, and the need for an assessment that accounts for this very rhythm more adequately than does the means of separated daytime hours. We also demonstrated that polynomial curves can be produced of ABPM data from both normo-5 and hypertensive6 groups, and that these polynomial curves are within the 95% confidence intervals of the sample means. However, intra-individual reproducibility of this approach has not been assessed, and is a prerequisite for further implementing this approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Owens P, Lyons S, O’Brien E. Ambulatory blood pressure in hypertensive population: patterns and prevalence of hypertensive subforms. J Hypertens 1998; 16: 1735–45.
Zanchetti A. Twenty-four-hour ambulatory blood pressure evaluation of antihypertensive agents. J Hypertens 1997; 15: S21–5.
Omboni S, Parati G, Palatini P, Vanasia A, Muiesan ML, Cuspidi C, Mancia G. Reproducibility and clinical value of nocturnal hypotension: prospective evidence from the SAMPLE study. J Hypertens 1998; 16: 733 – 8.
Bleniaszewski L, Staessen JA, Byttebier G, De Leeuw PW, Van Hedent T, Fagard R. Trough-to-peak versus surface ration in the assessment of antihypertensive agents. Blood Press 1997; 4: 350–7.
Van de Luit L, Van der Meulen J, Cleophas TJ, Zwinderman AH. Amplified amplitudes of circadian rhythms and nighttime hypotension in patients with chronic fatigue syndrome; improvement by inopamil but not by melatonin. Eur J Intern Med 1998; 9: 99–103.
Van de Luit L, Cleophas TJ, Van der Meulen J, Zwinderman AH. Nighttime hypotension in mildly hypertensive patients prevented by beta-blockers but not by ACE-inhibitors or calcium channel blockers. Eur J Intern Med 1998; 9: 251–6.
O'Brien E, Atkins N, Staessen J. State of the market, a review of ambulatory blood pressure-monitoring devices. Hypertension 1995; 26: 835–42.
Hays WL. Curvilinear regression. In: Hays WL, Statistics, Holt, Rinehart and Winston, Inc, Chicago, 4th edition, 1988, pp 698–716.
SPSS. Statistical Software. Professional Statistics. Chicago, Ill, 2002.
Harvard Graphics-3. Statistical Software. Boston MA, Harvard, Inc, 2001.
Scheidel B, Lemmer B, Blume H. Influence of time of day on pharmacokinetics and hemodynamic effects of beta-blockers. In: Clinical Chronopharmacology. Munich, Germany: Zuckschwerdt Verlag, 1990; vol 6: 75–9.
Lemmer B, Scheidel B, Behne S. Chronopharmacokinetics and chronopharmacodynamics of cardiovascular active drugs: propranolol, organic nitrates, nifedipine. Ann NY Acad Sci 1991; 618: 166–71.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer Science + Business Media B.V.
About this chapter
Cite this chapter
(2009). Curvilinear Regression. In: Cleophas, T.J., Zwinderman, A.H., Cleophas, T.F., Cleophas, E.P. (eds) Statistics Applied to Clinical Trials. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-9523-8_15
Download citation
DOI: https://doi.org/10.1007/978-1-4020-9523-8_15
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-9522-1
Online ISBN: 978-1-4020-9523-8
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)