A New Method for Investigating the Relation between Change and Initial Value in Longitudinal Blood Pressure Data: II. Comparison with Other Methods

Abstract

Whether initial value affects blood pressure change or not is of interest in longitudinal blood pressure studies. The change/initial value relationship is. however, biased by the regression towards the mean phenomenon, as blood pressure measurements contain random errors (short-term intn-individual variation and measurement errors). Two methods (here called C and D) of avoiding this bias have earlier been proposed and used in population studies in South Wales and Framingham, with conflicting results. In the preceding paper a new method of avoiding the bias has been presented. In the present paper a comparison of the new method with the two earlier is made by applying them to the same data set. Method C indicates, as in South Wales, a highly significant positive relationship, while method D (as in Framingham) and the new method give a regression coefficient close to zero. The structure of the three methods is analysed. Method C is shown to be valid only under very restricted conditions and is best avoided. Method D gives a fairly accurate result, but underestimates the coefficient by approximately 30% in this case. The new method proposed seems to be the best method hitherto for this kind of analysis.

Get full access to this article

View all access options for this article.

References

1. Blomqvist, N. : On the relation between change and initial value. J Am Stat Ass 72, dec 1977.

2. Evans, J. G. & Rose, G. :Hypertension. Br Med Bull 27: 37–42, 1971.

3. Feinleib, M., Halperin, M. & Garrison, R. J.: Relationship between blood pressure and age. Regression analysis of longitudinal data. Paper presented at the 97th Annual Meeting of the American Public Health Association, Philadelphia, November 10-14, 1969.

4. Garside, R. F. : Letters to the editor. On the analysis of repeated measurements of the same subjects. J Chron Dis 16:445–446, 448–449, 1963.

5. Garside, R. F. :Letters to the editor. On the analysis of repeated measurements of the same subjects. J Chron Dis 16: 1219–1220, 1963.

6. Gerende, L. J.: Some methodological problems of the blood pressure data in the Framingham Study. Ph.D. Thesis. University of Michigan, 1962.

7. Grimby. G. , Bjure, J. , Aurell, M. , Ekström-Jodal, B. , Tibblin. G. & Wilhelmsen. L. :Work capacity and physiologic responses to work. Am J Card 30: 37–41, 1972.

8. Grimby. G. , Wilhelmsen, L. , Ekström-Jodal, B. , Aurell, M. , Bjure, J. & Tibblin, G. :Aerobic power and related factors in a population study of men aged 54. Scand J Clin Lab Invest 26: 289–294, 1970.

9. Harris, R. E. : Long term studies of blood pressure recorded annually, with implications for the factors underlying essential hypertension. Trans Assoc Life Ins Med Dir Amer 51:130–149. 1967.

10.

10. Miall. W. E. & Lovell, H. G. : Relation between change of blood pressure and age. Br hled J ii: 660–664, 1967.

11.

11. Oldham, P. D. :A note on the analysis of repeated measurements of the same subjects. J Chron Dis 15: 969–977, 1962.

12.

12. Oldham, P. D. : Letters to the editor. On the analysis of repeated measurements of the same subjects. J Chron Dis 16:447–448, 449–450, 1963.

13.

13. Oldham, P. D. :Letters to the editor. On the analysis of repeated measurements of the same subjects. J Chron Dis 16: 1217–1219, 1963.

14.

14. Ragland, R. & Costiloe, J. P. :Letters to the editor. On the repeated measurements of the same subjects. J Chron Dis 16: 1215–1216, 1963.

15.

15. Svärdsudd, K. & Blomqvist, N. :A new method for investigating the relation between change and initial value in longitudinal blood pressure data. I. Description and application of the method. Scand J Soc Med 2: 85, 1978.

16.

16. Tibblin, G. : High blood pressure in men aged 50. A population study of Men Born in 1913. Acta Med Scand Suppl. 470, 1967.

17.

17. Tibblin. G. :A population study of 50-year-old men. An analysis of the non-participation group. Acta Med Scand 178: 453–459, 1965.