Showing papers by "Ralph B. D'Agostino published in 1990"

A Suggestion for Using Powerful and Informative Tests of Normality

Abstract: For testing that an underlying population is normally distributed the skewness and kurtosis statistics, √b 1 and b 2, and the D'Agostino–Pearson K 2 statistic that combines these two statistics have been shown to be powerful and informative tests. Their use, however, has not been as prevalent as their usefulness. We review these tests and show how readily available and popular statistical software can be used to implement them. Their relationship to deviations from linearity in normal probability plotting is also presented.

Relation of pooled logistic regression to time dependent Cox regression analysis: the Framingham Heart Study.

Abstract: A standard analysis of the Framingham Heart Study data is a generalized person-years approach in which risk factors or covariates are measured every two years with a follow-up between these measurement times to observe the occurrence of events such as cardiovascular disease. Observations over multiple intervals are pooled into a single sample and a logistic regression is employed to relate the risk factors to the occurrence of the event. We show that this pooled logistic regression is close to the time dependent covariate Cox regression analysis. Numerical examples covering a variety of sample sizes and proportions of events display the closeness of this relationship in situations typical of the Framingham Study. A proof of the relationship and the necessary conditions are given in the Appendix.

Changes in risk factors and the decline in mortality from cardiovascular disease. The Framingham Heart Study.

Abstract: A decline in mortality from cardiovascular disease over the past 30 years has been well documented, but the reasons for the decline remain unclear. We analyzed the 10-year incidence of cardiovascular disease and death from cardiovascular disease in three groups of men who were 50 to 59 years old at base line in 1950, 1960, and 1970 (the 1950, 1960, and 1970 cohorts) in order to determine the contribution of secular trends in the incidence of cardiovascular disease, risk factors, and medical care to the decline in mortality. The 10-year cumulative mortality from cardiovascular disease in the 1970 cohort was 43 percent less than that in the 1950 cohort and 37 percent less than that in the 1960 cohort (P = 0.04 by log-rank test). Among the men who were free of cardiovascular disease at base line, the 10-year cumulative incidence of cardiovascular disease declined approximately 19 percent, from 190 per 1000 in the 1950 cohort to 154 per 1000 in the 1970 cohort (0.10 less than P less than 0.20 by chi-square test), whereas the 10-year rate of death from cardiovascular disease declined 60 percent (relative risk for the 1950 cohort as compared with the 1970 cohort, 2.53; 95 percent confidence interval, 1.22 to 5.97). Significant improvements were found in risk factors for cardiovascular disease among the men initially free of cardiovascular disease in the 1970 cohort as compared with those in the 1950 cohort, including a lower serum cholesterol level (mean +/- SD, 5.72 +/- 0.98 mmol per liter [221 +/- 38 mg per deciliter], as compared with 5.90 +/- 1.03 mmol per liter [228 +/- 40 mg per deciliter]) and a lower systolic blood pressure (mean +/- SD, 135 +/- 19 mm Hg, as compared with 139 +/- 25 mm Hg), better management of hypertension (22 percent vs. 0 percent were receiving antihypertensive medication), and reduced cigarette smoking (34 percent vs. 56 percent). We propose that these improvements may have had more pronounced effects on mortality from cardiovascular disease than on the incidence of cardiovascular disease in this population. Our data suggest that the improvement in cardiovascular risk factors in the 1970 cohort may have been an important contributor to the 60 percent decline in mortality in that group as compared with the 1950 cohort, although a decline in the incidence of cardiovascular disease and improved medical interventions may also have contributed to the decline in mortality.

Aortic calcified plaques and cardiovascular disease (the Framingham study)

Abstract: The relation between the presence of calcified plaques in the thoracic aorta, as detected on chest x-rays, and the development of cardiovascular disease is examined during 12 years of follow-up of the Framingham cohort (n = 5,209). The prevalence of aortic calcified plaques approximately doubled with each decade of age, with only a trivial male predominance. Its presence was associated with a twofold increase in risk of cardiovascular death in men and women younger than age 65, even after other risk factors were taken into account. Similar increases in risk were found for coronary artery disease, stroke and intermittent claudication among middle-aged women. In middle-aged men these risks were less marked. The predictive value of aortic calcified plaques generally diminished with age. Risk of sudden coronary death in men with calcified plaques in the thoracic aorta ranged from a sevenfold increase at age 35 to no excess risk at age 70 years. These results support the view that atherosclerosis is a generalized process. The finding of aortic calcified plaques in a relatively young subject on a routine chest x-ray should be regarded as a sign for potential development of clinically manifest atherosclerotic disease in the cardiac, cerebral and peripheral arterial circulation.

Body Fat Distribution and Breast Cancer in the Framingham Study

Abstract: We examined the relation between central body fat distribution and breast cancer in a prospective cohort of women who participated in the Framingham Study. At the baseline examination in 1948, a total of 2,201 women aged 30-62 years were analyzed. An index of central to peripheral body fat (the central adiposity ratio) was calculated from the sum of the trunkal skinfolds (chest, subscapular, and abdominal) divided by the sum of the extremity skinfolds (triceps and thigh). These skinfolds were measured at the fourth examination in 1954. The cohort was followed for up to 28 years and yielded 106 cases of breast cancer. When divided into quartiles based on the central adiposity ratio, only women in the fourth quartile (those with the highest central to peripheral body fat distribution) demonstrated an increased risk for breast cancer. The age- and adiposity-adjusted relative risk estimate for having an increased central adiposity ratio (fourth quartile) compared to lower central adiposity ratios was 1.8 (95% confidence interval, 1.2-2.6). Adjustment for potential confounders of height, parity, and education did not appreciably alter this estimate (1.7, 1.1-2.5). There was no association between degree of adiposity, as measured by the sum of the five skinfolds or by body mass index (weight in kg divided by height in m2), and subsequent breast cancer. The results of this study suggest that increased central to peripheral body fat distribution predicts breast cancer risk independently of the degree of adiposity and may be a more specific marker of a premalignant hormonal pattern than degree of adiposity.

How important is functional status as a predictor of service use by older people

Abstract: In studies of older people, it is often assumed that biophysical, or functional, status is the primary determinant of formal service use. This article reports baseline data from a longitudinal study of a community-based, linked random sample of frail elders (n = 635) and their informal caregivers (n = 429) to investigate the relative contribution of social circumstances to the use of community-based formal services. Elder respondents were categorized into three groups defined by their primary source of care: (a) informal only, (b) mixed help with predominantly informal care, (c) mixed help with predominantly formal services. Of the respondents, 79% received most of their help from informal caregivers, whereas 21% relied on formal services for most of their assistance. A series of logistic regression models were developed to identify variables that discriminated between major sources of care. The social factor of living alone is the consistent predictor of reliance on formal services. Only for those elders...

Efficacy and tolerability of lovastatin in a six-month study: analysis by gender, age and hypertensive status.

Abstract: This study reports the results of a 6-month, open-label multicenter study of the efficacy and tolerability of lovastatin, a 3-hydroxy-3-methylglutaryl coenzyme A (HMG CoA) reductase inhibitor, in the management of nonfamilial primary hypercholesterolemia. The study enrolled 489 patients with elevated total serum cholesterol levels, whose lipids were not controlled sufficiently by diet. There was good representation of gender (48.3% women and 51.7% men), age (mean 57, range 25 to 83) and hypertension status (55.4% normotensive and 43.6% hypertensive) in the sample. Within 1 month of lovastatin therapy, total cholesterol was reduced 19% (from a mean of 269 to 217 mg/dl, low-density lipoprotein (LDL) cholesterol was reduced 27% (191 to 140 mg/dl), high-density lipoprotein (HDL) cholesterol increased 6% (42.6 to 45.1 mg/dl), the ratio of total cholesterol to HDL was reduced 24% (6.7 to 5.1) and the ratio of LDL to HDL was reduced 30% (4.7 to 3.3). These results were consistent across age group, gender and hypertension status, and were maintained for a period of 6 months of therapy. Lovastatin was generally well tolerated. Of the 489 patients enrolled, 449 (92%) completed 6 months of therapy. Only 21 (4%) withdrew because of adverse experience regardless of cause. None of the few serious adverse experiences (e.g., myocardial infarction) could be attributed to the drug. Abnormal laboratory values during the 6 months of therapy were within expectations. Seventy-four patients had at least 1 abnormal value during 6 months of treatment. Of these, 42 had at least 1 mild to moderate creatine phosphokinase elevation during this period. Only 1 patient had an adverse change on ophthalmologic examination: a posterior subcapsular opacity in both eyes just visible on 6-month examination.