Showing papers on "Confidence interval published in 1989"

Design and analysis of phase I clinical trials.

Abstract: The Phase I clinical trial is a study intended to estimate the so-called maximum tolerable dose (MTD) of a new drug. Although there exists more or less a standard type of design for such trials, its development has been largely ad hoc. As usually implemented, the trial design has no intrinsic property that provides a generally satisfactory basis for estimation of the MTD. In this paper, the standard design and several simple alternatives are compared with regard to the conservativeness of the design and with regard to point and interval estimation of an MTD (33rd percentile) with small sample sizes. Using a Markov chain representation, we found several designs to be nearly as conservative as the standard design in terms of the proportion of patients entered at higher dose levels. In Monte Carlo simulations, two two-stage designs are found to provide reduced bias in maximum likelihood estimation of the MTD in less than ideal dose-response settings. Of the three methods considered for determining confidence intervals--the delta method, a method based on Fieller's theorem, and a likelihood ratio method--none was able to provide both usefully narrow intervals and coverage probabilities close to nominal.

A prospective study of nutritional factors and hypertension among US men.

Abstract: The relation of various nutritional factors with hypertension was examined prospectively among 58,218 predominantly white US female registered nurses, aged 34-59 years. In 1980, all women completed an independently validated dietary questionnaire. During 4 years of follow-up, 3,275 women reported a diagnosis of hypertension; the validity of the self-report was shown in a subsample. Age, relative weight, and alcohol consumption were the strongest predictors for the development of hypertension. Dietary calcium and magnesium had independent and significant inverse associations with hypertension. For women with a calcium intake of at least 800 mg/day, the relative risk of hypertension was 0.78 (95% confidence interval, 0.69-0.88) when compared with an intake of less than 400 mg/day. The relative risk for magnesium intake of 300 mg/day or more compared with an intake of less than 200 mg/day was 0.77 (95% confidence interval, 0.67-0.88). For women with high intakes of both calcium and magnesium compared with those having low intakes of both, the relative risk of hypertension was 0.65 (95% confidence interval, 0.53-0.80). No independent associations with hypertension were observed for intakes of potassium, fiber, and saturated and polyunsaturated fatty acids. These prospective findings add to the growing evidence to support the need for randomized trials to determine whether there is a protective role of dietary calcium and magnesium in the regulation of blood pressure.

The risk of breast cancer after estrogen and estrogen-progestin replacement.

Abstract: To examine the risk of breast cancer after non-contraceptive treatment with estrogen, we conducted a prospective study of 23,244 women 35 years of age or older who had had estrogen prescriptions filled in the Uppsala region of Sweden. During the follow-up period (mean, 5.7 years) breast cancer developed in 253 women. Compared with other women in the same region, the women in the estrogen cohort had an overall relative risk of breast cancer of 1.1 (95 percent confidence interval, 1.0 to 1.3). The relative risk increased with the duration of estrogen treatment (P = 0.002), reaching 1.7 after nine years (95 percent confidence interval, 1.1 to 2.7). Estradiol (used in 56 percent of the treatment periods in the cohort) was associated with a 1.8-fold increase in risk after more than six years of treatment (95 percent confidence interval, 0.7 to 4.6). No increase in risk was found after the use of conjugated estrogens (used in 22 percent of the treatment periods) or other types, mainly estriols (used in...

Risk factors for human immunodeficiency virus infection in intravenous drug users.

Abstract: To identify risk factors for human immunodeficiency virus (HIV) infection in intravenous drug users, we undertook a study of the seroprevalence of HIV antibody in 452 persons enrolled in a methadone-treatment program in the Bronx, New York. The seroprevalence of HIV was 39.4 percent overall, 49.1 percent in blacks, 41.8 percent in Hispanics, and 17.2 percent in non-Hispanic whites (P less than 0.001 for all comparisons). The presence of HIV antibody was associated with the number of injections per month (P less than 0.001), the percentage of injections with used needles (P less than 0.001), the average number of injections with cocaine per month (P less than 0.001), and the percentage of injections with needles that were shared with strangers or acquaintances (P less than 0.001), a practice that was more common among blacks and Hispanics than among whites. The number of heterosexual sex partners who used intravenous drugs was associated with HIV infection in women (P less than 0.004) and was the only risk factor found for users who had not injected drugs after 1982 (P less than 0.05). The presence of HIV antibody was independently associated with being black or Hispanic (adjusted odds ratio, 4.56; 95 percent confidence interval, 2.65 to 8.14), a more recent year of the last injection of drugs (adjusted odds ratio, 1.24; 95 percent confidence interval, 1.13 to 1.35), the percentage of injections of drugs that took place in "shooting galleries" (adjusted odds ratio, 1.49; 95 percent confidence interval, 1.19 to 1.88), having sex partners who used intravenous drugs (adjusted odds ratio 1.24; 95 percent confidence interval, 1.06 to 1.45), and low income (adjusted odds ratio, 1.55; 95 percent confidence interval, 1.10 to 2.17). We conclude that differences in both the social setting of drug use and behavior related to injection carry different risks for infection with HIV and may explain, in part, the higher seroprevalence of HIV among blacks and Hispanics. In addition, we found that heterosexual activity was an independent risk factor for drug users.

Weight, diet, and the risk of symptomatic gallstones in middle-aged women.

Abstract: To assess the risk factors for symptomatic gallstones, 88,837 women in the Nurses' Health Study cohort (age range, 34 to 59 years) were followed for four years after completing a detailed questionnaire about food and alcohol intake in 1980. A total of 433 cholecystectomies and 179 cases of newly symptomatic, unremoved gallstones, diagnosed by ultrasonographic examination or x-ray films, were reported during the four-year follow-up. The age-adjusted relative risk for very obese women, who had a Quetelet index of relative weight (weight in kilograms divided by the square of the height in meters) of more than 32 kg per square meter, was 6.0 (95 percent confidence interval, 4.0 to 9.0), as compared with women whose relative weight was less than 20 kg per square meter. For slightly overweight women (relative weight, 24 to 24.9 kg per square meter), the relative risk was 1.7 (95 percent confidence interval, 1.1 to 2.7). Overall, we observed a roughly linear relation between relative weight and the risk of gallstones. Among the 59,306 women whose relative weight was less than 25 kg per square meter, a high energy intake (greater than 8200 J per day), as compared with a low energy intake (less than 4730 J per day), was associated with an increased incidence of symptomatic gallstones (relative risk, 2.1; 95 percent confidence interval, 1.4 to 3.3), and an alcohol intake of at least 5 g per day was associated with a decreased incidence as compared with abstention (relative risk, 0.6; 95 percent confidence interval, 0.4 to 0.8). Parity did not appear to be an important risk factor after an adjustment was made for relative weight. These data support a strong association between obesity and symptomatic gallstones and suggest that even moderate overweight may increase the risk.

Classical confidence intervals and Bayesian probability estimates for ends of local taxon ranges

Abstract: The observed local range of a fossil taxon in a stratigraphic section is almost certainly a truncated version of the true local range. True endpoints are parameters that may be estimated using only the assumption that fossil finds are distributed randomly between them. If thickness is rescaled so that true endpoints lie at 0 and 1, the joint distribution of gap lengths between fossil finds is given by the Dirichlet distribution. Observed ends of the range are maximum likelihood estimators of true endpoints, but they are biased seriously. Extension of the observed range at each end by a distance equal to the average gap length yields unbiased point estimators. Classical statistics can generate confidence intervals for ends of the taxon range; but with Bayesian inference, the probability that true endpoints lie in a certain region can be stated. For a 95% confidence level (classical) or a 95% probability (Bayesian), the range extensions exceed the observed range if the range is established on less than six finds; if only two finds are used, such range extensions are an order of magnitude longer than the observed range. Evidently the standard biostratigraphic practice that identifies zonal boundaries as horizons rather than confidence intervals may not be justified at the resolution of typical fossiliferous sections.

Mathematics and the Gender Gap: A Meta-Analysis of Recent Studies on Sex Differences in Mathematical Tasks.

Abstract: This paper is a meta-analysis of studies that have taken place between 1974 and mid-1987 on sex differences in mathematical tasks. The methods used are estimations of (a) parameters for a random effects model and (b) coefficients for a linear regression equation, all based on effect sizes calculated from each study. These results are compared with meta-analyses of the studies on quantitative skill collected by Maccoby and Jacklin. These comparisons, together with ad hoc comparisons of Scholastic Aptitude Test effect sizes over the years, yield two conclusions. First, the average sex difference is very small; a confidence interval for it covers zero, though the interval lies mainly on the side of male advantage. Second, sex differences in performance are decreasing over the years.

The Risk of Breast Cancer after Irradiation of the Thymus in Infancy

Abstract: It is well established that exposure to ionizing radiation during or after puberty increases a woman's risk for breast cancer, but it is less clear whether exposure to ionizing radiation very early in life is also carcinogenic. We studied the incidence of breast cancer prospectively in a cohort of 1201 women who received x-ray treatment in infancy for an enlarged thymus gland and in their 2469 nonirradiated sisters. After an average of 36 years of follow-up, there were 22 breast cancers in the irradiated group and 12 among their sisters, yielding an adjusted rate ratio of 3.6 (95 percent confidence interval, 1.8 to 7.3). The estimated mean absorbed dose of radiation to the breast was 0.69 Gy. The first breast cancer was diagnosed 28 years after irradiation. The dose-response relation was linear (P less than 0.0001), with a relative risk of 3.48 for 1 Gy of radiation (95 percent confidence interval, 2.1 to 6.2) and an additive excess risk of 5.7 per 10(4) person-years per gray (95 percent confidence interval, 2.9 to 9.5). We conclude that exposure of the female breast to ionizing radiation in infancy increases the risk of breast cancer later in life.

Meta-analytic Evidence Against Prophylactic Use of Lidocaine in Acute Myocardial Infarction

Abstract: • Although lidocaine prophylaxis reduces the incidence of ventricular fibrillation during acute myocardial infarction (AMI), randomized control trials (RCTs) have not demonstrated any significant mortality effect of this therapy. We conducted a meta-analysis of 14 RCTs of lidocaine prophylaxis during AMI to detect any mortality effect. Six prehospital- and eight hospital-phase RCTs that randomized totals of 7656 and 1407 patients, respectively, were selected and reviewed in a blinded fashion. Mortality data were evaluated according to therapy type, reporting interval, and patient category. The prehospital-phase RCTs showed no meaningful mortality effect (risk difference, 0.0184; 95% confidence interval, −0.048 to +0.012). The hospital-phase RCTs showed a statistically significant increase in mortality during the treatment period for lidocaine recipients (risk difference, 0.029; 95% confidence interval, +0.004 to +0.055). These results confirm that lidocaine administered to monitored patients during the prehospital phase of AMI will not reduce mortality by a clinically important amount and suggest that lidocaine administered in the hospital phase of monitored, uncomplicated AMI may increase mortality among recipients with proved AMI. ( Arch Intern Med. 1989;149:2694-2698)

Risk factors for gliomas and meningiomas in males in Los Angeles County.

Abstract: Detailed job histories and information about other suspected risk factors were obtained during interviews with 272 men aged 25-69 with a primary brain tumor first diagnosed during 1980-1984 and with 272 individually matched neighbor controls. Separate analyses were conducted for the 202 glioma pairs and the 70 meningioma pairs. Meningioma, but not glioma, was related to having a serious head injury 20 or more years before diagnosis [odds ratio (OR) = 2.3; 95% confidence interval (CI) = 1.1-5.4], and a clear dose-response effect was observed relating meningioma risk to number of serious head injuries (P for trend = 0.01; OR for greater than or equal to 3 injuries = 6.2; CI = 1.2-31.7). Frequency of full-mouth dental X-ray examinations after age 25 related to both glioma (P for trend = 0.04) and meningioma risk (P for trend = 0.06). Glioma, but not meningioma risk, related to duration of prior employment in jobs likely to involve high exposure to electric and magnetic fields (P for trend = 0.05). This risk was greatest for astrocytoma (OR for employment in such jobs for greater than 5 years = 4.3; CI = 1.2-15.6). More glioma cases had worked in the rubber industry (discordant pairs 6/1) and more worked in hot processes using plastics (9/1). More meningioma cases had jobs that involved exposure to metal dusts and fumes (discordant pairs 13/5), and six of these cases and two controls worked as machinists. Finally, there was a protective effect among glioma pairs relating to frequency of use of vitamin C and other vitamin supplements (P for trend = 0.004); the OR for use at least twice a day was 0.4 (CI = 0.2-0.8).

Analgesic Use and Chronic Renal Disease

Abstract: To examine the use of analgesics as a cause of chronic renal disease, we performed a multicenter case–control study of 554 adults with newly diagnosed kidney disease (serum creatinine, ≥130 μmol per liter [1.5 mg per deciliter]) and 516 matched control subjects selected randomly from the same area of North Carolina. Histories of use of analgesics (phenacetin, acetaminophen, and aspirin) were obtained by telephone interview with the patients or their proxies. Daily users of analgesics had significantly more renal disease than infrequent users (odds ratio, 2.79; 95 percent confidence interval, 1.85 to 4.21). The risk of renal disease was highest in daily users of phenacetin (odds ratio, 5.11; confidence interval, 1.76 to 14.9, after adjustment for the effects of other analgesics). The risk of renal disease was also increased in daily users of acetaminophen; after adjustment for the use of aspirin and phenacetin, the odds ratio was 3.21 (confidence interval, 1.05 to 9.80). There was no increased ris...

The Absence of a Relation between the Periconceptional Use of Vitamins and Neural-Tube Defects

Abstract: Whether taking multivitamins or folate around the time of conception can reduce a woman's risk of having a child with a neural-tube defect is controversial. To investigate this question, we examined the periconceptional use of vitamin supplements by women who had a conceptus with a neural-tube defect (n = 571), women who had had a stillbirth or a conceptus with another malformation (n = 546), and women who had had a normal conceptus (n = 573). Women with conceptuses with neural-tube defects were identified either prenatally or postnatally and were matched to control mothers for gestational age. To minimize recall bias, we interviewed nearly all the women within five months of the diagnosis of a birth defect or the birth of the infant (mean, 84 days); information on vitamin use was obtained by an interviewer who was unaware of the outcome of pregnancy. The rate of periconceptional multivitamin use among the mothers of infants with neural-tube defects (15.8 percent) was not significantly different from the rate among mothers in either the abnormal or the normal control group (14.1 percent and 15.9 percent, respectively). After adjustment for potential confounding factors, the odds ratio for having an infant with a neural-tube defect among women classified as having had full supplementation with multivitamins was 0.95 as compared with the mothers of the abnormal infants (95 percent confidence interval, 0.78 to 1.14) and 1.00 as compared with the mothers of normal infants (95 percent confidence interval, 0.83 to 1.20). There were no differences among the groups in the use of folate supplements. The adjusted odds ratio for having an infant with a neural-tube defect among those receiving the recommended daily allowance of folate was 0.97 as compared with the mothers of abnormal infants (95 percent confidence interval, 0.79 to 1.18) and 0.98 as compared with the mothers of normal infants (95 percent confidence interval, 0.80 to 1.20). We conclude that the periconceptional use of multivitamins or folate-containing supplements by American women does not decrease the risk of having an infant with a neural-tube defect.

The performance of the two‐stage analysis of two‐treatment, two‐period crossover trials

Abstract: In the two-treatment, two-period crossover trial, patients are randomly allocated either to one group that receives treatment A followed by treatment B, or to another group that receives the treatments in the reverse order. Grizzle first proposed a two-stage procedure for analysing the data from such a trial. This paper examines the long-run sampling properties of this procedure, in terms of mean square error of point estimates, coverage probability of confidence intervals and actual significance level of hypothesis tests for the differences between the effects of the two treatments. The advantages of incorporating baseline observations into the analysis are also explored. Because the preliminary test for carryover is highly correlated with the analysis of data from the first period only, actual significance levels are higher than nominal levels even when there is no differential carryover. When carryover is present, the nominal level very seriously understates the actual level, and this becomes even worse when baseline observations are ignored. Increasing sample size only exacerbates the problem since this adverse behaviour then occurs at smaller values of the carryover effect. It is concluded that the two-stage analysis is too potentially misleading to be of practical use.

Steroid Treatment of Laryngotracheitis: A Meta-Analysis of the Evidence From Randomized Trials

Abstract: The use of adrenocorticoids to reduce the morbidity associated with laryngotracheitis (croup) remains controversial despite ten published reports of randomized trials involving 1,286 patients. To determine whether, viewed in aggregate, these studies demonstrate a significant benefit of steroid treatment for this disorder, a meta-analysis of the nine methodologically satisfactory trials was performed. Clinical improvement 12 and 24 hours posttreatment and incidence of endotracheal intubation were evaluated. For each end point, an estimate of the overall effect was obtained by calculating a typical odds ratio and 95% confidence interval. This analysis indicates that the use of steroids in children hospitalized with croup is associated with a significantly increased proportion of patients showing clinical improvement 12 hours (odds ratio = 2.25, 95% confidence interval = 1.66, 3.06) and 24 hours (odds ratio = 3.19, 95% confidence interval = 1.70, 5.99) posttreatment and a significantly reduced incidence of endotracheal intubation (odds ratio = 0.21, 95% confidence interval = 0.05, 0.84). Higher initial doses of steroid (greater than or equal to 125 mg of cortisone or greater than or equal to 100 mg of hydrocortisone) were associated with a larger proportion of patients improved 12 hours posttreatment than was seen with lower doses. These results support the use of steroids in the treatment of hospitalized children with croup and, in the absence of a randomized clinical trial of sufficient size, provide the most reliable estimate of the impact of steroid therapy on the morbidity associated with croup. In addition, the results of this meta-analysis may be used to estimate the number of subjects who would be required to conduct a randomized clinical trial of steroids for the treatment of croup.

Stress and relapse of breast cancer.

Abstract: To elucidate the association between stressful life events and the development of cancer the influence of life stress on relapse in operable breast cancer was examined in matched pairs of women in a case-control study. Adverse life events and difficulties occurring during the postoperative disease free interval were recorded in 50 women who had developed their first recurrence of operable breast cancer and during equivalent follow up times in 50 women with operable breast cancer in remission. The cases and controls were matched for the main physical and pathological factors known to be prognostic in breast cancer and sociodemographic variables that influence the frequency of life events and difficulties. Severely threatening life events and difficulties were significantly associated with the first recurrence of breast cancer. The relative risk of relapse associated with severe life events was 5.67 (95% confidence interval 1.57 to 37.20), and the relative risk associated with severe difficulties was 4.75 (1.58 to 19.20). Life events and difficulties not rated as severe were not related to relapse. Experiencing a non-severe life event was associated with a relative risk of 2.0 (0.62 to 7.47), and experiencing a non-severe difficulty was associated with a relative risk of 1.13 (0.38 to 3.35). These results suggest a prognostic association between severe life stressors and recurrence of breast cancer, but a larger prospective study is needed for confirmation.

Duplex and color Doppler sonographic evaluation of vasculogenic impotence

Abstract: One hundred eighty patients with suspected vasculogenic impotence were evaluated with conventional penile duplex sonography with spectral analysis and color Doppler imaging. Measurements of mean peak systolic and end-diastolic velocities were obtained from the cavernosal arteries before and after intracavernosal injections of papaverine. Sixty-one patients were examined with dynamic cavernosography and cavernosometry, and 12 patients were studied with selective internal pudendal and penile arteriography. All five patients with abnormal arteriography had mean peak systolic velocities in the cavernosal arteries of less than or equal to 25 cm/sec (sensitivity, 100%; 95% confidence interval, 48-100%) after the injection of papaverine. Six of the seven patients with normal arteriography had mean peak systolic velocities of greater than 25 cm/sec (specificity, 85.7%; 95% confidence interval, 42-100%) after injection of papaverine. By using data from a receiver-operating-characteristic curve, we determined that end-diastolic velocities in the cavernosal arteries of greater than or equal to 5 cm/sec after the injection of papaverine correctly identified patients with excessive venous leakage on cavernosometry; the sensitivity was 90% (95% confidence interval, 77-97%) and the specificity was 56% (95% confidence interval, 30-80%). The addition of color Doppler sonography made the detection of vessels easier and the correction of the Doppler angle more accurate, resulting in more rapid and accurate acquisition of data. Penile duplex sonography with spectral analysis and color Doppler imaging are sensitive and noninvasive means of examining patients with potential vasculogenic impotence.

Hearing Impairment as a Determinant of Function in the Elderly

Abstract: This clinical, practice-based study explores the research question: Is there a relationship between hearing loss and functional disturbance in elderly patients? We analyzed the impact of hearing impairment on 153 patients over 65 years of age screened in primary care practice. Functional and psychosocial impairment were measured using the Sickness Impact Profile (SIP), a standardized measure for assessing sickness related dysfunction. Hearing level was determined with pure tone audiometry. Multiple linear regression was used to adjust for patient case-mix differences and other clinical variables. After adjustment, a 10 dB increase in hearing loss was found to result in a 2.8 point increase in Physical SIP scores (95% confidence interval = 1.8-3.8), a 2.0 point increase in psychosocial SIP scores (95% confidence interval = 0.8-3.2) and a 1.3 point increase in overall SIP scores (95% confidence interval = 0.1-2.5). Poor hearing was associated with higher SIP scores and increased dysfunction. Thus, hearing impairment is an important determinant of function in the elderly.

Consumption of fermented milk products and breast cancer: a case-control study in The Netherlands.

Abstract: In a case-control study in The Netherlands, we observed a significantly lower consumption of fermented milk products (predominantly yogurt and buttermilk) among 133 incident breast cancer cases as compared to 289 population controls (mean +/- SD among users only, 116 +/- 100 versus 157 +/- 144 g/day; P less than 0.01). The age-adjusted odds ratio of daily consumption of 1.5 glasses (greater than or equal to 225 g) of fermented milk versus none was 0.50 (95% confidence interval, 0.23-1.08). When fermented milk was entered as a continuous variable (per g) in either age-adjusted or multivariate analysis, the odds ratio expressed per 225 g was 0.63 (multivariate-adjusted 95% confidence interval, 0.41-0.96). After multivariate adjustment for intake of fat and other confounders, a statistically significant decrease in breast cancer risk was also observed for increasing intake of Gouda cheese. The multivariate-adjusted odds ratio expressed per 60 g of this fermented product was 0.56 (95% confidence interval, 0.33-0.95). For daily intake of milk, no statistically significant differences were observed between cases and controls. These results support the hypothesis that high consumption of fermented milk products may protect against breast cancer.

Snoring as a risk factor for sleep-related brain infarction.

Abstract: We studied 177 consecutive male patients aged 16-60 years with brain infarction verified by neuroradiology and analyzed the time of onset of stroke symptoms related to sleep and the role of possible or known risk factors for brain infarction. Brain infarction occurred relatively more often during the first 30 minutes after awakening than at any other time. In multiple stepwise logistic regression analyses, snoring was the only independent risk factor differentiating stroke occurring during sleep and stroke occurring either during sleep or during the first 30 minutes after awakening from stroke occurring at other times of the day. The risk ratios were 2.65 (95% confidence interval 1.32-5.29, p less than 0.005) and 3.16 (95% confidence interval 1.61-6.22, p less than 0.001), respectively. Other factors tested were age, arterial hypertension, diabetes mellitus, smoking, alcohol consumption, and body mass index. Arterial hypertension seemed to have an additive effect on the independent risk caused by snoring.

Prospective Study of Oral Contraceptive Use and Risk of Breast Cancer in Women

Abstract: In 1976, 118,273 female nurses 30-55 years of age with no history of cancer completed a questionnaire regarding possible risk factors. By 1986, after 1,137,415 person-years of follow-up, we had documented 1,799 newly diagnosed cases of breast cancer. Compared with the risk of breast cancer for nonusers of oral contraceptives, the multivariate relative risks were 1.07 (95% confidence interval, 0.97-1.19) for all users, 1.06 (95% confidence interval, 0.96-1.18) for past users, and 1.53 (95% confidence interval, 1.06-2.19) for current users--women who used oral contraceptives up to 2 years before diagnosis of breast cancer. We conclude that overall past use of oral contraceptives is not associated with a substantial increase in the risk of breast cancer. Although we did not find women who used oral contraceptives before the first pregnancy to have an increased risk of breast cancer, the number of women who used oral contraceptives for a long duration in early reproductive life was too small to permit firm conclusions regarding the risk in this subgroup.

Prediction intervals - a review

Abstract: This review covers some known results on prediction intervals for univariate distributions. Results for parametric continuous and discrete distributions as well as those based on distribution-free methods are included. Prediction intervals based on Bayesian and sequential methods are not covered. Methods of construction of prediction intervals and other related problems are discussed.