Data Analysis of Ambulatory Blood Pressure Readings
The nature of ambulatory blood pressure (BP) monitoring is such that exploratory data analysis is both useful and necessary. In any study using ambulatory monitoring there are many sources of uncontrolled variability, including individual levels of BP, individual diurnal patterns of BP, individual physical activity patterns, individual mental activity (psychological) patterns, and artifactual readings. Failure to properly account for these sources of variation will typically obscure real effects in the data and can bias the estimates of the effects of primary interest. In this chapter we report our experience with the exploratory analysis which should precede the calculation of p values. Our experience has been primarily with large samples. When the sample size is large, computing resources can be severely strained and statistical significance (via a p value) takes a backseat to practical significance. We do not discuss the interpretation of significance tests in any detail but refer readers to the discussions by Ware, Mosteller, and Ingelfinger (1986) and Royall (1986).
KeywordsDiurnal Variation Blood Pressure Level Ambulatory Blood Pressure Ambulatory Monitoring Daily Activity Pattern
Unable to display preview. Download preview PDF.
- Becker, R.A., & Chambers, J. M. (1984). S: An interactive environment for data analysis and graphics. Belmont, CA: Wadsworth.Google Scholar
- Cleveland, W. S. (1985). The elements of graphing data. Belmont, CA: Wadsworth.Google Scholar
- Draper, N. R., & Smith, H. (1981). Applied regression analysis. New York: Wiley.Google Scholar
- Millar-Craig, M. W., Mann, S., Balasubramanian, V., & Raftery, E. G. (1978). Blood pressure circadian rhythm in essential hypertension. Clinical Science and Molecular Medicine, 55, 391s.Google Scholar
- Royall, R. M. (1986). The effect of sample size on the meaning of significance tests. American Statistician, 40, 313–315.Google Scholar
- Snedecor, G. W., & Cochran, W. G. (1967). Statistical methods (6th ed.). Ames: Iowa State University Press.Google Scholar
- Ware, J. H., Mosteller, F., & Ingelfinger, J. A. (1986). P values. In J. C. Bailar, III, & F. Mosteller (Eds.), Medical uses of statistics. Waltham, MA: NEJM Books.Google Scholar