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 505 records · Page 28Linked to original sources
PubMed1985

Oral contraceptive use and blood pressure in a German metropolitan population.

The relationship between blood pressure (BP) and oral contraceptive (OC) use in women has been examined with the data from the Munich Blood Pressure Study (MBS), a cross-sectional study with follow-up of a random sample of 3198 Munich citizens aged 30-69 (response rate 69.3%). Multiple linear and logistic regression analyses were run with BP as the dependent variable and age, OC use, obesity, alcohol consumption, and smoking habit as the independent variables. All second and third order interactions between the independent variables were tested during a backward stepping procedure. OC use appeared as a significant main effect in most of the analyses. The coefficient of the OC variable was about 3 in the linear regression analyses for both systolic BP and diastolic BP, indicating an increase of about 3 mmHg in the systolic and diastolic BP of the OC users. An analysis of the change in BP after one year in relation to change in OC user status has also been made. It was observed that women ceasing to use OC had a clear decrease in BP while those starting to use OC had on average an increase in BP.

Adult↗
PubMed1997

Regression analysis of the effect of full and partial lactation on post-partum amenorrhoea in lower middle class Indian females.

This study presents a simple regression analysis of the impact of full and partial breast feeding on post-partum amenorrhoea (PPA) in lower middle class Indian women. The study has been done on a sample of hospital based data collected in 1992. The analysis shows a highly significant correlation. Further, the impact of lactation on PPA was notably less in case with partial breast feeding as compared to those with full breast feeding.

Amenorrhea↗
PubMed2002

Using continuous PM2.5 monitoring data to report an air quality index.

As stated in 40 CFR 58, Appendix G (2000), statistical linear regression models can be applied to relate PM2.5 continuous monitoring (CM) measurements with federal reference method (FRM) measurements, collocated or otherwise, for the purpose of reporting the air quality index (AQI). The CM measurements can then be transformed via the model to remove any bias relative to FRM measurements. The resulting FRM-like modeled measurements may be used to provide more timely reporting of a metropolitan statistical area's (MSA's) AQI. Of considerable importance is the quality of the model used to relate the CM and FRM measurements. The use of a poor model could result in misleading AQI reporting in the form of incorrectly claiming either good or bad air quality. This paper describes a measure of adequacy for deciding whether a statistical linear regression model that relates FRM and continuous PM2.5 measurements is sufficient for use in AQI reporting. The approach is the U.S. Environmental Protection Agency's (EPA's) data quality objectives (DQO) process, a seven-step strategic planning approach to determine the most appropriate data type, quality, quantity, and synthesis for a given activity. The chosen measure of model adequacy is r2, the square of the correlation coefficient between FRM measurements and their modeled counterparts. The paper concludes by developing regression models that meet this desired level of adequacy for the MSAs of Greensboro/Winston-Salem/High Point, NC; and Davenport/Moline/Rock Island, IA/IL. In both cases, a log transformation of the data appeared most appropriate. For the data from the Greensboro/Winston-Salem/High Point MSA, a simple linear regression model of the FRM and CM measurements had an r2 of 0.96, based on 227 paired observations. For the data from the Davenport/Moline/Rock Island MSA, due to seasonal differences between CM and FRM measurements, the simple linear regression model had to be expanded to include a temperature dependency, resulting in an r2 of 0.86, based on 214 paired observations.

Air Pollutants↗
PubMed1995

Basic statistics for clinicians: 4. Correlation and regression.

Correlation and regression help us to understand the relation between variables and to predict patients' status in regard to a particular variable of interest. Correlation examines the strength of the relation between two variables, neither of which is considered the variable one is trying to predict (the target variable). Regression analysis examines the ability of one or more factors, called independent variables, to predict a patient's status in regard to the target or dependent variable. Independent and dependent variables may be continuous (taking a wide range of values) or binary (dichotomous, yielding yes-or-no results). Regression models can be used to construct clinical prediction rules that help to guide clinical decisions. In considering regression and correlation, clinicians should pay more attention to the magnitude of the correlation or the predictive power of the regression than to whether the relation is statistically significant.

Data Interpretation, Statistical↗
PubMed1978

Age at menopause in relation to reproductive history in Japanese, Caucasian, Chinese and Hawaiian women living in Hawaii.

A multiple regression analysis was undertaken to examine the relationship between age at menopause and selected biological and sociological variables in the reproductive history of Caucasian, Japanese, Chinese and part-Hawaiian post-menopausal women living in Hawaii. The analysis was conducted using the medical history records of 196 Caucasian, 181 Japanese, 72 Chinese and 60 Hawaiian women. Age at menarche, parity and months spent breast-feeding were found to have no significant effect on age at menopause. Regression models were not found to be heterogeneous among ethnic groups and no substantial interaction of ethnic group was found with age at menarche, parity or months spent breast-feeding.

Asian People↗
PubMed1982

Outcome of delivery subsequent to induced vacuum-aspiration abortion in parous women.

In a historical prospective study covering 1970-1978, the authors evaluated the outcome of delivery to 429 parous women subsequent to a legally induced first-trimester vacuum-aspiration abortion during 1970-1975 in Uppsala County, Sweden. This outcome was compared with the outcome of delivery to 391 randomly chosen matched parous women and that of all parous women in Sweden in 1975. Confounding variables were controlled for in multiple regression analysis using infant birth weight and gestational duration as dependent variables. In this analysis, no harmful effects of vacuum-aspiration abortion were found. Pre-term deliveries and low birth weight infants did not occur more frequently after such abortions. The study did not disclose any association between vacuum-aspiration abortion in parous women and an unfavorable outcome of subsequent delivery.

Abortion, Induced↗
PubMed1994

HIV-1 infection among lower class commercial sex workers in Chiang Mai, Thailand.

OBJECTIVE: To determine risk factors for HIV-1 infection in female commercial sex workers (CSW) in northern Thailand. METHODS: A cross-sectional survey of female CSW from 11 sex establishments frequented by military conscripts that included an interview and serological testing for HIV-1. RESULTS: The HIV-1 seroprevalence in 230 CSW was 65%; the rate was lower among CSW from Chiang Mai than from rural areas. Multivariate logistic regression analysis for HIV-1 included the following significant factors: non-urban location of the sex establishment, ethnic Thai lowlander, lower price, history of genital warts and dysuria. Condom use, number of partners and duration of employment were not significantly associated with HIV-1 prevalence after adjustment for other risk factors. CONCLUSIONS: The high level of HIV-1 seroprevalence in this sample demonstrates the risk of transmission in lower cost commercial sex encounters in northern Thailand. Non-Thais (ethnic Hill tribes and Burmese) had lower HIV-1 prevalence than ethnic Thais. Type of establishment ('direct' brothel-based or 'indirect' establishments) was not predictive of HIV-1 seroprevalence. However, rural establishments were less vigilant in promoting condom use, suggesting the need for renewed efforts to enforce the Ministry of Public Health's '100% Condom Campaign' in commercial sex establishments.

Adolescent↗
PubMed1991

Cognitive orientation and genital infections in young women.

The purpose was to explore the psychological determinants of common genital infections in young women. The study was done in the framework of the cognitive orientation theory which assumes that cognition guides behavior and provides predictions of behaviors and psychophysiological phenomena. We expected that beliefs of four types (about self, norms, goals, and general) would predict the occurrence and/or frequency of 17 gynecological symptoms (e.g., itching, swelling, different vaginal discharges, abscesses). The subjects were 195 female volunteers, undergraduates, about 23 years old, without gross gynecological disorders, mostly (87.7%) unmarried, mostly (83.6%) having had intercourse. They were administered anonymously questionnaires about demographic variables, frequency and treatment of gynecological symptoms and 3 urological ones (for control), and about cognitive orientation that referred to pretested themes (e.g., assertiveness, hypochondriasis). Stepwise discriminant and regression analyses showed that the belief types enabled predicting the occurrence and frequency of all symptoms, with a mean 34.5% improvement over the 50% chance level, accounting for 45.7-67.2% of the variance. Also the urological symptoms were predicted although at a lower level. Discussion focuses on the specificity of cognitive-motivational determinants and their role in producing conditions favoring physical pathology.

Adult↗
PubMed1993

Some factors affecting birth weights in Morogoro, Tanzania.

Three hundred and thirty two pregnant women who were attending three antenatal clinics in Morogoro Municipality in Tanzania were followed in their third trimester of pregnancy in a study which aimed at finding if there was any association between weight gain in third trimester and birth weight of singleton deliveries. The relationship between weight and gestational period, age of the mother, parity and maternal weight near term were also studied. Univariate regression analysis showed that there was a strong positive correlation between birth weight and gestational period. Correlation was also found between birth weight and age of the mother, parity and weight near term, while a week correlation was found between birth weight and maternal weight gain in the third trimester. Multiple regression analysis showed that only the gestation period and weight near term were independently related to birth weight. Despite low maternal weight gain, birth weight was not affected, this shows that there might be some physiological adaptation which come into play to protect the foetus where a woman is subjected to inadequate nutrition during pregnancy.

Adaptation, Physiological↗
PubMed1984

A population study on the relationship between blood pressure and the excretion of urinary cations.

The relationships between blood pressure and the 24-h excretion of three urinary cations (Ca2+, K+, and Na+) were investigated in a random sample of 528 adults (greater than or equal to 20 years) inhabitants of two Belgian towns. In these adults both systolic and diastolic blood pressures were strongly and independently correlated with age and body weight. Systolic pressure in women was significantly and positively related to pulse rate. After adjusting for age and body weight, systolic and diastolic pressures in men were significantly (p less than 0.001 and p less than 0.01, respectively) and negatively correlated with urinary potassium excretion. Diastolic pressure in men was weakly (p less than 0.05 after adjusting for body weight, age, and urinary potassium excretion) but positively correlated with calcium excretion. In a subsample of 162 premenopausal women, blood pressure was higher in current contraceptive pill users than in women not taking oral contraceptives. In 56 current pill users there was a positive association between systolic pressure and 24-h urinary sodium (p less than 0.01 after adjusting for age, body weight, and pulse rate). The present study indicates that urinary potassium is a consistent and negative predictor of both systolic and diastolic pressures in adult men, whose diastolic pressure is weakly and positively associated with urinary calcium. The positive association between systolic pressure and urinary sodium in current users of contraceptive pills may suggest that their blood pressure becomes responsive to their usual salt intake.

Adult↗
PubMed1986

Time to conception after IUD removal: importance of duration of use, IUD type, pelvic inflammatory disease and age.

Some investigations of IUD use have demonstrated impaired ability to become pregnant after removal, while others have not. None of these studies, however, have adequately considered such potentially influencing variables as age and a history of pelvic inflammatory disease (PID). To study the effect of length of IUD use, IUD type and the modifying influences of age and PID history on time required to conceive, we followed women trying to become pregnant after removal of their IUD. Five hundred forty women in Ljubljana, Yugoslavia who were first fitted with an IUD between 1964 and 1972 and had their IUD removed in order to become pregnant were followed through 1980. We found no relationship between the duration of IUD use or type of IUD used, but increasing age and a history of PID each decreased the monthly probability of conception. These findings, along with other recent work, indicate that IUDs are a safe and efficacious contraceptive for women at low risk for sexually transmitted diseases.

Adult↗
PubMed2004

Differential gene expression detection using penalized linear regression models: the improved SAM statistics.

UNLABELLED: Differential gene expression detection using microarrays has received lots of research interests recently. Many methods have been proposed, including variants of F-statistics, non-parametric approaches and empirical Bayesian methods etc. The SAM statistics has been shown to have good performance in empirical studies. SAM is more like an ad hoc shrinkage method. The idea is that for small sample microarray data, it is often useful to pool information across genes to improve efficiency. Under Bayesian framework Smyth formally derived the test statistics with shrinkage using the hierarchical models. In this paper we cast differential gene expression detection in the familiar framework of linear regression model. Commonly used test statistics correspond to using least squares to estimate the regression parameters. Based on the vast literature of research on linear models, we can naturally consider other alternatives. Here we explore the penalized linear regression. We propose the penalized t-/F-statistics for two-class microarray data based on [Formula: see text] penalty. We will show that the penalized test statistics intuitively makes sense and through applications we illustrate its good performance. AVAILABILITY: Supplementary information including program codes, more detailed analysis results and R functions for the proposed methods can be found at http://www.biostat.umn.edu/~baolin/research CONTACT: baolin@biostat.umn.edu SUPPLEMENTARY INFORMATION: http://www.biostat.umn.edu/~baolin/research.

Cell Line, Tumor↗
PubMed1996

Standardisation or modelling of mortality rates.

STUDY OBJECTIVE: To compare the results obtained when estimating a standardised rate using the conventional technique of stratified analysis and using Poisson regression, and to evaluate the speed of the two techniques in making the calculation. DESIGN: Cross sectional study. SETTING AND PARTICIPANTS: The trend in motor vehicle accident mortality in males from 1985 to 1992 in Spain was compared using stratified analysis and Poisson regression. In the stratified analysis the calculations were made using a specially designed spreadsheet while in the Poisson regression the statistical program used was EGRET. RESULTS: The stratified analysis took two hours and the Poisson regression 15 minutes to complete. In the stratified analysis a single estimate for each year was obtained, whereas the model of Poisson regression that best fitted the data included an interaction term between age and year. CONCLUSION: Poisson regression can be considered a serious alternative to stratified analysis when the objective is to compare mortality rates standardised by one or two variables.

Accidents, Traffic↗
PubMed1985

Infection with Chlamydia trachomatis in female college students.

Chlamydia trachomatis was isolated from genital specimens from 21 (4.9%) of 431 female college students. Antibody to C. trachomatis was found in the genital secretions of 52 (11.9%) of 437 women. Multiple logistic regression analysis showed race, number of sexual partners, and use of barrier methods of contraception to be predictive of infection with C. trachomatis. Logistic regression analysis found race, number of sexual partners, use of barrier methods of contraception, and presence of cervical erythema to be predictive of local chlamydial antibody. White participants were infected less often (12 of 388 (3.1%)) than black participants (9 of 43 (20.9%)) (p less than 0.001) and were less likely to have local chlamydial antibody. None of the sexually inexperienced women were infected or had local antibody. Among the sexually experienced women, chlamydial infection and local chlamydial antibody increased with increasing number of sexual partners only for women who were not using barrier methods of contraception. Sexually experienced women who used barrier methods of contraception (condom, diaphragm) were less likely to be infected (one of 105 (1.0%)) than were sexually experienced women who used other contraceptive measures or who did not use contraception (20 of 276 (7.2%)) (p = 0.031). Women who used barrier methods of contraception also were less likely to have local chlamydial antibody. Women with cervical erythema were more likely to have local chlamydial antibody (4 of 11 (36.4%)) than women without cervical erythema (48 of 426 (11.3%)). Vaginal colonization with other sexually transmitted microorganisms (Mycoplasma hominis, Ureaplasma urealyticum, Trichomonas vaginalis) was noted more often among women with chlamydial infection than among uninfected women.

Adult↗
PubMed1993

Factors associated with use of safer sex practices among college freshmen.

The purpose of this exploratory study was to examine the relationship of knowledge of AIDS, misconceptions about AIDS, knowledge of safer sex practices, perceived susceptibility, and future time perspective to the practice of safer sex behaviors in 352 single, sexually active, college freshmen. Data were analyzed using stepwise multiple regression analysis and discriminant analysis. There were too few black females for analysis. Future time perspective explained the most variance in safer sex practices for black males. Knowledge of AIDS, perceived susceptibility, misconceptions about AIDS, knowledge of safer sex practices, and future time perspective did not explain a significant amount of variance in use of safer sex practices for either white males or females. However, perceived susceptibility and future time perspective differentiated sexually active from nonsexually active white males and females.

Acquired Immunodeficiency Syndrome↗