Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Statistical Regression”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,027 records · Page 57Linked to original sources
PubMed1991

Age structure and sex-biased mortality among Herero pastoralists.

Details of the population pyramid of living Herero and Mbanderu of Botswana suggest that infant and childhood mortality of males has been substantially greater than that of females. Direct tests from reproductive histories show that the hazard ratio is approximately 3 to 1 in favor of female survival in infancy and 2 to 1 in childhood. This biased mortality began in about 1960 in concert with recovery from infertility. A model of asymmetric fitness benefits between siblings is weakly supported. Logistic regression shows that heterogeneity among mothers explains much of the mortality of children under 2 years of age. A direct test for heterogeneity provides strong support for the hypothesis. Field methods appropriate for anthropologists are contrasted with those that are standard in demography. Finally, a contrast between these data and those from south Asia suggests that strong sex preferences may exist without being culturally articulated. Cultural norms do not necessarily coincide with behavior.

Age Factors↗
PubMed2005

Body composition in children with galactosaemia.

Body composition in classical galactosaemia has not been studied. Patients with classical galactosaemia, an inherited disorder of galactose metabolism caused by deficiency of galactose-1-phosphate uridyltransferase (GALT, EC 2.7.7.10), might be at risk for an abnormal body composition because of intrinsic factors related to galactosaemia and/or diet-related factors. The aim of this study was to evaluate the body composition of children with classical galactosaemia. The studied population was a previously reported group of classical galactosaemia patients (13 male and 27 female, ages 3-17 years) with decreased height, weight, weight-for-height and insulin-like growth factor-I (IGF-I) Z-scores. Body composition data were obtained by dual-energy X-ray absorptiometry (DXA). In order to correct for height, fat mass (FM) and lean tissue mass (LTM) were divided by squared height. Mid-parental target height Z-scores were assessed and compared to actual height Z-scores. Linear and multiple regression analysis were done to investigate the relationship between body composition and IGF-I, dietary intake and growth data. We found decreased height Z-scores when compared to mid-parental target height Z-scores. Mean scores for FM and LTM (both adjusted for height) were decreased. LTM (adjusted for height) and height Z-score were correlated with IGF-I Z-score. FM (adjusted for height) was correlated with soy intake. No correlation was found between soy intake and IGF-I Z-score. In this limited group of patients, height is decreased and body composition is abnormal. The decreased levels of IGF-I and/or soy nutrition might play a role in these findings.

Absorptiometry, Photon↗
PubMed2006

[Characteristics of candidates for surgical sterilization and factors associated with type of procedure].

In 1999 the Municipal Health Department in Ribeirão Preto, São Paulo, Brazil, implemented the provision of surgical contraceptive methods according to prevailing legal requirements. This study aimed to characterize the candidates for surgical sterilization and study the variables associated with the type of procedure. A total of 95 candidate patient records were studied, and statistical logistic regression analysis and Fisher's exact test were performed considering a significance level of ? = 0.05. Most candidates had stable partners, low schooling, and low income, were satisfied with their number of children, and had already tried to limit the number of children using reversible contraceptives. Mean age was 34.2 years, 45.3% underwent female sterilization, 35.8% underwent vasectomy, and 18.9% did not submit to any procedure. The odds of a man older than 35 having a vasectomy were 6.1 times that of a younger man (OR = 6.1; 95%CI: 2.4-16.4). More married men submitted to vasectomy than men who cohabited (OR = 4.0; 95%CI: 1.5-12.4). Women with four or more children were more likely to undergo sterilization than those with fewer children (OR = 3.1; 95%CI: 1.1-8.5).

Adult↗
PubMed1991

Pooling data for stability studies: testing the equality of batch degradation slopes.

Pharmaceutical products are routinely monitored for their stability over time. Stability studies generally consist of a random sample of dosage units (e.g., tablets, capsules, vials) from a batch or several batches placed in a storage room and periodically assayed for their drug content. The degradation of the drug product is modeled, and according to the Guideline for Submitting Documentation for Stability Studies of Human Drugs and Biologics (Food and Drug Administration, 1987), the shelf-life is calculated as the time point at which the lower 95% confidence limit about the fitted regression line crosses the lowest acceptable limit for drug content (frequently 90% of the labeled amount). When multiple batches are manufactured, preliminary testing for any batch differences (both slope and intercept) should precede pooling stability data from all batches in the analysis. The Guideline recommends a level of significance of .25 for such preliminary testing based on the work described by Bancroft (1964, Biometrics 20, 427-442). Using such a large significance level helps ensure that the power of the test for the batch differences is sufficiently high. This paper presents an approach whereby the power of the test is fixed and the significance level of the test needed to obtain this power is calculated from the data. If the observed significance level does not achieve the calculated significance level, then the data can be pooled. Examples will illustrate the relative performance of the FDA guideline and the proposed procedure.

Analysis of Variance↗
PubMedDate not supplied

Relationship between biomedical catheter surface properties and lubricity as determined using textural analysis and multiple regression analysis.

In this study, the surface properties of and work required to remove 12 commercially available and developmental catheters from a model biological medium (agar), a measure of catheter lubricity, were characterised and the relationships between these properties were examined using multiple regression and correlation analysis. The work required for removal of catheter sections (7 cm) from a model biological medium (1% w/w agar) were examined using tensile analysis. The water wettability of the catheters were characterised using dynamic contact angle analysis, whereas surface roughness was determined using atomic force microscopy. Significant differences in the ease of removal were observed between the various catheters, with the silicone-based materials generally exhibiting the greatest ease of removal. Similarly, the catheters exhibited a range of advancing and receding contact angles that were dependent on the chemical nature of each catheter. Finally, whilst the microrugosities of the various catheters differed, no specific relationship to the chemical nature of the biomaterial was apparent. Using multiple regression analysis, the relationship between ease of removal, receding contact angle and surface roughness was defined as: Work done (N mm)=17.18+0.055 Rugosity (nm)-0.52 Receding contact angle ( degrees ) (r=0.49). Interestingly, whilst the relationship between ease of removal and surface roughness was significant (r=0.48, p=0.0005), in which catheter lubricity increased as the surface roughness decreased, this was not the case with the relationship between ease of removal and receding contact angle (r=-0.18, p>0.05). This study has therefore uniquely defined the contributions of each of these surface properties to catheter lubricity. Accordingly, in the design of urethral catheters, it is recommended that due consideration should be directed towards biomaterial surface roughness to ensure maximal ease of catheter removal. Furthermore, using the method described in this study, differences in the lubricity of the various catheters were observed that may be apparent in their clinical use.

Biocompatible Materials↗
PubMed1990

Predictors of failed attempted abortion with the antiprogestin mifepristone (RU 486).

The experience of 271 patients who received mifepristone (RU 486) in experimental protocols from July 1984 to January 1989 was analyzed by logistic regression methods. The regimen used was the strongest predictor of failure, followed by Quetelet's index and initial beta-human chorionic gonadotropin level. The relative risk of failure was 2.3 times with 7-day regimens and 6.3 times with the other regimens that obtained with regimens of 600 mg given once or twice. The relative risk of failure increased with increasing Quetelet's index; women in the top quartile were 2.9 times more likely to fail to abort than were women in the bottom quartile. The risk of failure increased with increasing initial beta-human chorionic gonadotropin level; those with an initial level greater than 19,800 mIU/ml were 2.8 times more likely to fail to abort than were women with an initial value less than or equal to 6350 mIU/ml. Body mass appears to influence the likelihood of abortion with mifepristone.

Abortifacient Agents↗
PubMed1989

The effect of patient charges on the utilisation of prescription medicines.

This study is a time-series regression analysis of National Health Service (NHS) prescription drug utilisation. The monthly volume of items dispensed with and without charge in England (1969-1986) form the dependent variables for model estimation. The main finding is that, for items that incur a charge, increases in the real value of the prescription charge are associated with reductions in prescription drug utilisation. The charge-volume elasticity (1969-1986) is estimated at -0.33, rising to -0.64 in the later sub-period (1978-1986). OTC products display a positive cross-price elasticity (+0.22) with chargeable items, but they are less clearly substitutes for prescriptions exempt from charge. One of the main predictors for exempt prescriptions is the number of elderly in the population. The study concludes that the evaluation of the prescription charge policy requires more detailed study of both the incidence of the charge effect and the possible costs and health consequences of reduced utilisation due to the charge.

Demography↗
PubMed2003

Can symptoms predict endoscopic findings in GERD?

BACKGROUND: It is difficult to decide which patients with reflux symptoms require endoscopy. The aim of this study was to develop a scoring system to predict esophageal findings at endoscopy. METHODS: A consecutive sample of 1011 adult patients scheduled for upper endoscopy were asked to complete a validated symptom questionnaire. The endoscopy reports were abstracted. Individual logistic regression models were developed to predict esophagitis, Barrett's esophagus (long and short segment) and esophageal stricture, including Schatzki's ring. RESULTS: Reflux esophagitis was independently associated with heartburn frequency (p<0.0001) but not severity or duration (p>0.05). Barrett's esophagus was associated with the duration of acid regurgitation (p<0.005) but not with frequency or severity (p>0.05). Strictures were associated with dysphagia severity (p<0.0001) and duration (p<0.0001) but not frequency (p>0.05). At a sensitivity of 80%, the models had a specificity of 49% for esophagitis, 57% for Barrett's esophagus, and 68% for strictures. At a specificity of 80%, the sensitivities were 51% for esophagitis, 62% for Barrett's esophagus and 71% for strictures. CONCLUSIONS: Endoscopic findings were associated with distinct attributes of reflux symptoms. Symptoms are only modestly predictive of findings at endoscopy.

Barrett Esophagus↗
PubMed1996

The safety effects of child-resistant packaging for oral prescription drugs. Two decades of experience.

OBJECTIVE: To evaluate the effectiveness of child-resistant packaging in reducing the mortality rate for children younger than 5 years from the unintentional ingestion of oral prescription drugs. DESIGN: Annual mortality rates for children younger than 5 years associated with the unintentional ingestion of oral prescription drugs are constructed for 1964 through 1992. The effect of child-resistant packaging on the child mortality rate during the postintervention period (1974 through 1992) is evaluated with a multivariate time series regression model. The analysis controls for changes in the consumption of oral prescription drugs over time and for long-term safety trends. SETTING: United States. SUBJECTS: Children younger than 5 years. MAIN OUTCOME MEASURE: Estimated reductions in the child mortality rate associated with the use of child-resistant packaging. RESULTS: After controlling for covariates, the use of child-resistant packaging was associated with an annual reduction in the oral prescription drug-related mortality rate of 1.40 (95% confidence interval, 0.85-1.95) deaths per million children younger than 5 years. This suggests a reduction of about 460 child deaths from 1974, the year oral prescription drugs became subject to child-resistant packaging requirements, through 1992-a mortality rate reduction of about 45% from levels projected without the child-resistant requirements. CONCLUSION: Child-resistant packaging reduces child mortality from the unintentional ingestion of oral prescription drugs.

Administration, Oral↗
PubMed2003

Separation of individual-level and cluster-level covariate effects in regression analysis of correlated data.

The focus of this paper is regression analysis of clustered data. Although the presence of intracluster correlation (the tendency for items within a cluster to respond alike) is typically viewed as an obstacle to good inference, the complex structure of clustered data offers significant analytic advantages over independent data. One key advantage is the ability to separate effects at the individual (or item-specific) level and the group (or cluster-specific) level. We review different approaches for the separation of individual-level and cluster-level effects on response, their appropriate interpretation and give recommendations for model fitting based on the intent of the data analyst. Unlike many earlier papers on this topic, we place particular emphasis on the interpretation of the cluster-level covariate effect. The main ideas of the paper are highlighted in an analysis of the relationship between birth weight and IQ using sibling data from a large birth cohort study.

Birth Weight↗
PubMed1991

Analysis of longitudinal data with unmeasured confounders.

Confounding in longitudinal or clustered data creates special problems and opportunities because the relationship between the confounder and covariate of interest may differ across and within individuals or clusters. A well-known example of such confounding in longitudinal data is the presence of cohort and period effects in models of aging in epidemiologic research. We first formulate a data-generating model with confounding and derive the distribution of the response variable unconditional on the confounder. We then examine the properties of the regression coefficient for some analytic approaches when the confounder is omitted from the fitted model. The expected value of the regression coefficient differs in across- and within-individual regression. In the multivariate case, within- and between-individual information is combined and weighted according to the assumed covariance structure. We assume compound symmetry in the fitted covariance matrix and derive the variance, bias, and mean squared error of the slope estimate as a function of the fitted within-individual correlation. We find that even in this simplest multivariate case, the trade-off between bias and variance depends on a large number of parameters. It is generally preferable to fit correlations somewhat above the true correlation to minimize the effect of between-individual confounders or cohort effects. Period effects can lead to situations where it is advantageous to fit correlations that are below the true correlation. The results highlight the trade-offs inherent in the choice of method for analysis of longitudinal data, and show that an appropriate choice can be made only after determining whether within- or between-individual confounding is the major concern.

Analysis of Variance↗
PubMed2001

To offer or not to offer: the role of price in employers' health insurance decisions.

OBJECTIVE: To estimate the effect of changes in price on employers' decisions to offer health insurance. DATA SOURCES/STUDY SETTING: A 1993 survey of 22,347 private employers in ten states was used. STUDY DESIGN: Probit regression was used to estimate the probability of offering insurance as a function of the price and employer characteristics. For employers who did not offer insurance, a price cannot be directly observed. We estimated price for nonofferors using reported quotes received by recent shoppers and a selection model to correct for differences between recent shoppers and nonshoppers. PRINCIPAL FINDINGS: Changes in price affect decisions to offer insurance; however, even a 40 percent reduction in premiums would lead to only a 2 to 3 percentage point increase in the share of employers offering insurance. Employers of low-wage workers are substantially less likely to offer health insurance than other employers. CONCLUSIONS: Policies to reduce the number of uninsured that focus on increasing the supply of employment-based insurance are unlikely to have the intended effect unless coupled with policies to help low-wage workers afford insurance.

Data Collection↗
PubMed1993

Influence of maternal age, birth-to-conception intervals and prior perinatal factors on perinatal outcomes.

This study evaluated the influence of prior perinatal factors on birth weight, length of gestation, and maternal pregravid and postpartum weights in subsequent pregnancies. The study sample included 47 women each with first, second and third pregnancies. Mean pregravid weight increased by 5.2 lb between the first and second pregnancies and by 4.4 lb between the second and third pregnancies. Total weight gain averaged 31 lb for the first pregnancy and 28.4 and 28.3 lb for the second and third pregnancies, respectively. Mean birth weight increased by 111 g between the first and second pregnancies and by 199 g between the second and third pregnancies. Mean gestational age was similar for all three pregnancies, averaging 39.5 weeks. Using stepwise forward multiple regression analyses, we determined that birth weight and length of gestation are both influenced significantly by prior birth weight and length of gestation; subsequent pregravid weight is influenced significantly by prior rate of gain, pregravid weight and postpartum weight; and postpartum weight is significantly influenced by prior rate of gain and birth weight. Comparisons across three pregnancies for the same woman showed that differences in birth-to-conception interval were not associated with higher postpartum weight or subsequent pregravid weight. These data indicate that in healthy, nonsmoking, low-risk women, the maternal and infant outcomes of pregnancies are significantly influenced by prior outcomes but not by either short birth-to-conception interval or greater maternal age.

Adult↗
PubMed1995

Discontinuity indices: a tool for epidemiological studies on breastfeeding.

BACKGROUND: The Discontinuity Index (DI), which measures the percentage of infants who were exclusively breastfed (EBF) at the beginning of a given age interval and had abandoned this mode of feeding at its end, and the relative weight of this discontinuation, was introduced and employed in the National Survey on Breast Feeding and Infant Feeding Practices carried out in Cuba in 1990. The aim of this article is to illustrate, through a specific example, the quality of DI as a simple procedure for assessing breastfeeding trends. METHODS: The prevalence of EBF in the 14 provinces of Cuba at discharge from the maternity services and at 30, 60, 120, and 180 days of age, was obtained using data from a national sample of 6661 infants (4820 urban and 1791 rural) which were processed by means of a logistic regression model. Cumulative DI were calculated for the intervals 0-30, 0-60, 0-120 and 0-180 days, and partial DI for the terms 30-60, 60-120 and 120-180 days, for each province and for the whole country. RESULTS: Cumulative DI show the progress of cessation of breastfeeding and are strongly influenced by previous intervals. The Eastern provinces showed the lowest figures at most of the terms. Discontinuation during the first month of life was particularly high in two Western provinces. Partial DI are more specific and allow discrimination of the intervals at which EBF discontinuation is more frequent. The highest values were observed between 4 and 6 months. CONCLUSIONS: Discontinuity indices are useful complements to prevalence rates in epidemiological studies of breastfeeding. The separate analysis of discontinuation in different periods can be highly useful when comparing trends and in the study of the impact of breastfeeding promotion programmes focused on different age intervals.

Age Factors↗
PubMed1991

Dynamics of spread of HIV-I infection in a rural district of Uganda.

OBJECTIVE: To define the geographical distribution of HIV infection and the community characteristics associated with HIV prevalence in a rural population of Uganda. DESIGN: Seroprevalence survey and interviews of the population aged 13 years and older in 21 randomly selected clusters. SETTING: Rural population of Rakai district, south west Uganda. SUBJECTS: 1292 adults, of whom 594 men and 698 women gave a blood sample and answered the questionnaire. MAIN OUTCOME MEASURES: HIV status determined by ELISA and western blotting in relation to community characteristics. RESULTS: The weighted seroprevalence of HIV for the district was 12.6% with prevalence by cluster varying from 1.2% to 52.8%. Seroprevalence was highest in main road trading centres (men 26%, women 47%), intermediate in rural trading villages on secondary roads (men 22%, women 29%), and lowest in rural agricultural villages (men 8%, women 9%). For both men and women, multiple regression showed a strong negative association between cluster seroprevalence and the proportion of the population employed in agriculture (beta = -0.677 for men, -0.807 for women). Among women, cluster seroprevalence increased with a higher proportion of the population reporting multiple sex partners (beta = 0.814), external travel (beta = 0.579), and injections (beta = 0.483). CONCLUSIONS: Community characteristics, particularly the proportion of the population in agriculture, are associated with HIV prevalence and can be used for targeting interventions. The seroprevalences of HIV suggest spread of infection from main road trading centres, through intermediate trading villages, to rural agricultural villages.

Adolescent↗
PubMed1999

Segregation analysis of attention deficit hyperactivity disorder.

We performed segregation analysis on 495 nuclear families, ascertained for the father's substance abuse diagnosis, in an attempt to determine the role of genetic and other influences in determining the variability of DSM-III-R-defined attention deficit hyperactivity disorder (ADHD). For our analyses, ADHD was treated as a quantitative variable, utilizing the semicontinuous scale provided by the 15-item symptom count within DSM-III-R. Analyses consisted of both class A and class D regressive models for which covariate effects (socioeconomic status) and sex dependence were estimated. Segregation analysis of the quantitative trait (ADHD symptom count) in the entire data set supported a transmissible non-Mendelian major effect. Models which were sex-dependent and included covariate effects provided the best fit to the data. In addition, similar analyses were performed on a 130-nuclear family subgroup of the data set in which at least one of the members of the nuclear family met DSM-III-R diagnostic criteria for ADHD. The sex-dependent Mendelian codominant model was best supported by the data, while other models could be rejected. Incorporating covariate effects did not provide a better fit for the data. Thus, this study is consistent with Mendelian transmission of ADHD symptom count in a clinically relevant population. Overall, our results support the presence of a heritable continuous trait of which ADHD represents an extreme.

Analysis of Variance↗
PubMed1996

MIXREG: a computer program for mixed-effects regression analysis with autocorrelated errors.

MIXREG is a program that provides estimates for a mixed-effects regression model (MRM) for normally-distributed response data including autocorrelated errors. This model can be used for analysis of unbalanced longitudinal data, where individuals may be measured at a different number of timepoints, or even at different timepoints. Autocorrelated errors of a general form or following an AR(1), MA(1), or ARMA(1,1) form are allowable. This model can also be used for analysis of clustered data, where the mixed-effects model assumes data within clusters are dependent. The degree of dependency is estimated jointly with estimates of the usual model parameters, thus adjusting for clustering. MIXREG uses maximum marginal likelihood estimation, utilizing both the EM algorithm and a Fisher-scoring solution. For the scoring solution, the covariance matrix of the random effects is expressed in its Gaussian decomposition, and the diagonal matrix reparameterized using the exponential transformation. Estimation of the individual random effects is accomplished using an empirical Bayes approach. Examples illustrating usage and features of MIXREG are provided.

Adolescent↗
PubMed1989

Incidence and duration of breast-feeding in Mexican-American infants, 1970-1982.

The Mexican-American component of the Hispanic Health and Nutrition Examination Survey (HHANES-MA) was used to examine the breast-feeding behavior of 2402 infants born between 1970 and 1982. The proportion of infants ever breast-fed increased substantially in recent years. Weighted proportions were 30.7% for 1970-1974, 38.1% for 1975-1978, and 47.6% for 1979-1982. By use of logistic regression models, children born into households with a college-educated head were shown to be more likely to be breast-fed than were other children; breast-feeding was also positively associated with birth weight. Infants in households for which the preferred interview language was Spanish were more likely to be breast-fed than were infants living in households for which the interview was conducted in English. Analysis of the factors influencing the distribution of weaning times among infants was less definitive because reported weaning times are heaped on multiples of 3 mo. The gathering of current-status, or status quo, information on infant feeding is urged for data collection in future studies.

Birth Weight↗