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 811 records · Page 45Linked to original sources
PubMed1991

Regression with bivariate grouped data.

The problem of accounting for the grouping of continuous, bivariate data in regression analyses is considered. Reasons why grouping must be taken seriously are advanced, and a strategy for accounting for grouping is demonstrated. The specific model asserts that, in the absence of grouping, the data would be bivariate normal. This model is used to adjust estimates of parameters in a regression relating disease severity to a grouped exposure variable, using data on pneumoconiosis in English coal miners (Ashford, 1959, Biometrics 15, 573-581). The choice of computing methods is discussed and likelihood formulas are presented.

Algorithms↗
PubMed1993

[From multiple regression analysis to logistic model, proportional hazard model and log linear model. Its concept and application].

Recently logistic model, proportional hazard model and log linear model have been used frequently in the medical literatures. Here, each model is reviewed briefly from basics to its application, pointing out pitfalls in its application, some of which are common to any regression analysis. The logistic model is especially useful for the analysis of retrospective data where odds ratio is utilized to evaluate the outcome probability. On the other hand, proportional hazard model is useful when we analyze censored data, utilizing hazard function. Log linear model has been used where contingency table has more than three independent variables, the situation where its applicability in clinical medicine is wide. Familiarity with these statistical methods would enable us to evaluate data more effectively and efficiently and ultimately to read literature more easily.

Models, Statistical↗
PubMed1989

Prospective follow-up of cervical HPV infections: life table analysis of histopathological, cytological and colposcopic data.

A total of 532 women with established cervical HPV infection have been prospectively followed (without treatment) since 1981 for a mean of 45 (SD 21) months. The patients were examined by colposcopy, PAP smears and/or punch biopsy every 6 months. The life-table method was applied to analyze the clinical course (i.e. regression and progression) of the HPV lesions, stratified by their colposcopic pattern, PAP smear findings and grade of CIN. During the follow-up, 107 (41.8%) of 256 patients with HPV-NCIN lesion in the first punch biopsy, experienced spontaneous regression. The corresponding proportions for HPV-CIN I, HPV-CIN II and HPV-CIN III lesions were 31.1%, 34.2%, and 20.7%, respectively. In the overall comparison between these four groups, the heterogeneity in the probability of regression was statistically significant (p = 0.0005). Clinical progression was also associated significantly with the histological grade of the lesions in the first biopsy. Progression rate was only 5.8% for HPV-NCIN lesions, as compared to 12.3% for HPV-CIN I, 20% for HPV-CIN II, and 55.2% for HPV-CIN III. The probability of progression varied significantly between the four groups (p less than 0.00001). Cumulative proportion of regression was 46% for patients with PAP smear class I, 84% with class II, and 82% for those with class III, cells, i.e. PAP smear was not of value in predicting the regression. However, PAP smears predicted clinical progression (p = 0.006 overall).(ABSTRACT TRUNCATED AT 250 WORDS)

Actuarial Analysis↗
PubMed1992

Interrelations between growth, weaning and disease experience in Khartoum infants.

The monthly measurements of body weight and supine length from birth to 1 year of 203 infants in Khartoum were analysed to see whether growth characteristics affected the timing of weaning and the amount of illness experience. The study clearly shows that neonates who are long for their age tend to be weaned early, and this causes them to experience a greater average monthly 'illness experience' and slower subsequent growth. However, a multivariate analysis indicates that it is correlated environmental variables rather than length growth itself which primarily determines weaning age. Weight growth does not show these relationships but there is strong evidence that late weaning, independently of disease experience, promotes post-natal weight growth.

Body Height↗
PubMedDate not supplied

Gastric and lung cancer mortality in the Marche region of Italy, 1980-1983.

This paper describes patterns in gastric and lung cancer mortality in the Marche region of Italy and in its 24 Local Health Districts (LHD) over the period 1980-83. Mortality data were obtained from the magnetic tapes provided by the National Institute of Statistics. Linear regressions were tested with the aim to relate the AADRs with the proportion of the agricultural workers in the 1951, 1961 and 1971 census years. The results obtained show that, in the whole Marche region, mortality from lung cancer is first in male cancer mortality. However within the Region itself many LHDs had different patterns. Among the LHDs, gastric cancer rates were the highest in some northern mountain zones, and lung cancer rates in some central coastal zones. Statistical analyses emphasize the inverse relationship between the male 0-64 AADRs relative to gastric cancer and those of lung cancer in the 24 LHDs. Among these, the male gastric cancer 0-64 AADRs are significantly and directly related to the proportion of farm workers in 1971, and the female ones to the proportion of farm workers in all the three periods, which in turn are always inversely related to the 0-64 AADRs male lung cancer. The differences between the observed and expected death frequencies in the several LHDs stress the results obtained in the present study, which generally agree with those obtained in other studies regarding the same and neighbouring areas and with those reported by the international literature.

Agricultural Workers' Diseases↗
PubMed2005

Exploring the overall and specific crash severity levels at signalized intersections.

Many studies have shown that intersections are among the most dangerous locations of a roadway network. Therefore, there is a need to understand the factors that contribute to injuries at such locations. This paper addresses the different factors that affect crash injury severity at signalized intersections. It also looks into the quality and completeness of the crash data and the effect that incomplete data has on the final results. Data from multiple sources have been cross-checked to ensure the completeness of all crashes including minor crashes that are usually unreported or not coded into crash databases. The ordered probit modeling technique has been adopted in this study to account for the fact that injury levels are naturally ordered variables. The tree-based regression methodology has also been adopted in this study to explore the factors that affect each severity level. The probit model results showed that a combination of crash-specific information and intersection characteristics result in the highest prediction rate of injury level. More specifically, having a divided minor roadway or a higher speed limit on the minor roadway decreased the level of injury while crashes involving a pedestrian/bicyclist and left turn crashes had the highest probability of a more severe crash. Several regression tree models showed a difference in the significant factors that affect the different severity types. Completing the data with minor non injury crashes improved the modeling results and depicted differences when modeling the no injury crashes.

Accidents, Traffic↗
PubMed1994

Hierarchical regression analysis applied to a study of multiple dietary exposures and breast cancer.

Hierarchical regression attempts to improve standard regression estimates by adding a second-stage "prior" regression to an ordinary model. Here, we use hierarchical regression to analyze case-control data on diet and breast cancer. This regression yields semi-Bayes relative risk estimates for dietary items by using a second-stage model to pull estimates toward each other when the corresponding variables have similar levels of nutrients. Unlike classical Bayesian analysis, however, no use is made of previous studies on nutrient effects. Compared with results obtained with one-stage conditional maximum-likelihood logistic regression, our hierarchical regression model gives more stable and plausible estimates. In particular, certain effects with implausible maximum-likelihood estimates have more reasonable semi-Bayes estimates.

Bayes Theorem↗
PubMed1989

Estimation and comparison of changes in the presence of informative right censoring: conditional linear model.

A general linear regression model for the usual least squares estimated rate of change (slope) on censoring time is described as an approximation to account for informative right censoring in estimating and comparing changes of a continuous variable in two groups. Two noniterative estimators for the group slope means, the linear minimum variance unbiased (LMVUB) estimator and the linear minimum mean squared error (LMMSE) estimator, are proposed under this conditional model. In realistic situations, we illustrate that the LMVUB and LMMSE estimators, derived under a simple linear regression model, are quite competitive compared to the pseudo maximum likelihood estimator (PMLE) derived by modeling the censoring probabilities. Generalizations to polynomial response curves and general linear models are also described.

Analysis of Variance↗
PubMed1999

Regression of columnar-lined (Barrett's) oesophagus with omeprazole 40 mg daily: results of 5 years of continuous therapy.

BACKGROUND: We have previously reported the effect of 2 years of omeprazole 40 mg daily on columnar-lined (Barrett's) oesophagus (CLO). AIMS: In the present study, follow-up has been extended to 5 years to assess the macroscopic and microscopic effects of continuing therapy. PATIENTS AND METHODS: The 23 patients have been followed for up to a further 3 years. Endoscopy with multiple biopsies was performed at the end of years 3, 4 and 5. RESULTS: Although there had been a statistically significant regression in the length of CLO after 2 years, there was no overall further measurable change after 5 years. However, one patient showed complete macroscopic and microscopic regression. The number and size of macroscopic squamous islands within the CLO continued to increase, and there was a further increase in microscopic squamous re-epithelialization of surface mucosa, gland ducts and Barrett's gland tissue. Low-grade dysplasia was found consistently in one patient in biopsies taken up to the end of year 3 but it could not be detected thereafter. CONCLUSIONS: Omeprazole 40 mg daily appears to have beneficial effects on CLO, although it rarely induces a complete regression. Whether the benefits will reduce the risk of malignant transformation is unknown.

Aged↗
PubMed1989

A measurement-error model for binary and ordinal regression.

Exposure assessment poses special problems in air pollution epidemiology. This paper proposes a probit regression model for binary and ordinal outcomes that uses exposure validation information to develop estimates for the coefficient of the true exposure when only the inaccurate 'surrogate' measure of exposure is available for the individuals in the health study. This method is closely related to recently developed measurement-error methods, and is based on the assumption that the outcome and the surrogate exposure are conditionally independent given the true exposure. A test statistic is proposed for checking this conditional independence assumption when more than one surrogate is available, and an interpretation of the coefficient estimate is provided in the event that the assumption is violated. The methods are applied to an example involving nitrogen dioxide exposure and wheeze in children.

Air Pollution↗
PubMedDate not supplied

Development and validation of routine analysis methods for the determination of essential, nonessential, and toxic minor and trace elements in cereal and cereal flour samples by inductively coupled plasma-atomic emission spectrometry.

Various digestion procedures were carefully investigated and accurately evaluated with respect to their effect on the analysis of cereals and cereal flours. Multielement methods were selected and well developed for the determination of essential (Cr, Cu, Fe, Mg, Mn, and Zn), nonessential (Ag, Al, Ba, Bi, In, and Ga), and toxic (Cd and Pb) minor and trace elements by inductively coupled plasma-atomic emission spectrometry. Only Ag could be determined, either with aqueous standard or standard addition calibration methods, while the standard addition methods were more accurate for the determination of other elements. The recoveries were mostly within the range of 84.1-113% for the expected values of all analytes with respect to certified reference material NIST SRM 1586a (rice flour). The results proved that, for cereals and cereal flours, the use of H2O2 for wet digestion and HNO3 for dry ashing were not necessary. Linear regression analysis and Student's paired t-test were applied to evaluate the significant differences between different procedures and type of samples.

Calibration↗
PubMed1989

Correlation of contraceptive activity of norethisterone and levonorgestrel esters with VR(w) values and hydrolysis rates.

The relationships between contraceptive activity, hydrophobic character and alkaline hydrolysis rates were studied in three homologous series of norethisterone and levonorgestrel esters. Hydrophobic character was expressed by the high-performance liquid chromatographic retention term, VR(w) or retention volume at 100% aqueous mobile phase. A parabolic and bilinear relationship was shown between log VR(w) and log biological response. No correlation between second-order alkaline hydrolysis rates, k2, measured in 70% (v/v) aqueous dioxan and contraceptive activity was established.

Acetic Anhydrides↗
PubMed1991

Sexual activity and contraceptive use among low-income urban black adolescent females.

A modified form of Nathanson and Becker's (1983) Health Belief Model Questionnaire and other measures designed to assess cognitive processing were administered to low-income black adolescent female clients of an inner-city comprehensive health care clinic. The purpose of the study was to explore determinants of sexual activity and contraceptive use. Subjects were classified as not sexually active (n = 50), sexually active/noncontracepting (n = 20), or sexually active/contracepting (n = 72). Not sexually active subjects tended to be younger, more career motivated, to have a father at home, to be more influenced by family values, and to have more conservative attitudes regarding adolescent sexuality than did sexually active subjects. Sexually active/noncontracepting subjects tended to report fewer benefits and more barriers to the use of contraception. Level of cognitive processing did not differ among the three groups, but was at a lower-than-expected level for age. Finally, inconsistent contraceptive use was common to both sexually active groups.

Adolescent↗
PubMed1992

Effect of child survival on contraceptive use in Bangladesh.

A study in Bangladesh showed that couples who lost a child often stopped practising contraception in order to have another child. Logistic regression analysis revealed that contraceptive continuation was related to maternal age, parity, husband's education and the sex of the last child.

Adolescent↗