SEARCH · PubMed Health

Results for “Regression Analysis”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 397 records · Page 22Linked to original sources

PubMed1993

Determination of specific activity of labeled ligands by nonlinear regression analysis.

The specific radioactivity (SA) of 125I-lysine vasopressin (LVP) was determined by analyzing the binding B (cpm/tube) of variable amounts of tracer T (cpm/tube) to a constant amount of an LVP antibody, in the presence of known quantities L (mol/tube) of LVP standards. The parameters of the equations B = f(F) and B/F = g(T), describing B as a function of free F (cpm/tube) tracer or the ratios B/F as a function of T, were first calculated by nonlinear regression analysis of the results obtained with tracer alone. Then the dependent variables B or B/F were measured in the presence of LVP and analyzed with the same equations by substituting the independent variables F or T with (F + alpha FL) and (T + alpha L), respectively, where alpha (cpm/mol) represents a measure of the SA and FL (FL = L.F/T), free LVP, respectively. The SA was thus treated as an unknown parameter to be calculated by nonlinear regression. This method was compared with the traditional interpolation of the SA from the self-displacement and standard curves. Tracer and ligand were found to have the same affinity for the binding sites, since the set of equations B = f(F + alpha FL) and B/F = g(T + alpha L), describing the binding of the tracer in the presence of LVP and equations B = f(F) and B/F = g(T) to which these equations reduce in the absence of LVP (L = 0), had identical binding parameters. To be valid, any method based on self-displacement requires that the tracer and standards have the same affinity for the binding sites.(ABSTRACT TRUNCATED AT 250 WORDS)

Animals↗

PubMed1980

Predicting the success of a sympathectomy: a prospective study using discriminant function and multiple regression analysis.

A prospective study of 72 limbs treated with phenol sympatholysis for inoperable peripheral arterial occlusive disease was carried out in order to determine which factor or combination of factors could most accurately be used to predict the success or the failure of the sympathetic interruption. Seven variables were recorded prior to phenol sympatholysis and the patients were followed up to 3 years in order to determine the degree of success or failure of the sympathectomy. The results of discriminant function analysis of these data showed that the most important variables in predicting the outcome were (1) the level of ankle systolic pressure, (2) the presence or absence of a neuropathy, and (3) the extent of the ischemic damage. The correct outcome was predicted in 87% of the cases. Using these three variables, multiple regression analysis was performed to construct a table showing the percentage chance of a successful outcome from a sympathectomy. The results show that a phenol sympathectomy is likely to be successful in the management of a patient with peripheral arterial occlusive disease if there is no evidence of a somatic (and hence autonomic) neuropathy, if the ankle systolic pressure is above 30 mm Hg, and if the tissue damage is not too extensive (i.e., only rest pain, night pain, or digital gangrene is present).

Arterial Occlusive Diseases↗

PubMed2004

New method using multi-regression analysis on evoked electromyography during movement to adjust stimulation conditions.

A new method of stimulation of the lower extremities was devised that automatically adjusts the stimulation conditions at any angle of the knee joint. An M-wave is considered to indicate the stimulation conditions, because it is the waveform that results from direct stimulation to the axon of the alpha motor neuron. The present device adjusted the stimulation intensity, using multi-regression analysis to evoke an M-wave of preset amplitude. Participants included five people without any neuromuscular impairment. The subjects sat on a chair during the test. The hip joint was fixed at a flexion angle of 90 degrees, and the ankle joint was fixed at the midposition. During passive knee joint movement ranging from 0 degrees to 135 degrees, M-waves were measured. Electrodes were attached at the popliteal fossa and the patella to stimulate the tibial nerve. Ag-AgCl electrodes were put on the belly of the right soleus muscle for the M-wave measurement. The device was set to give M-waves close to the preset value, 10% Mmax. According to previous research, the allowable limit of M-wave amplitude deviations was reported to be about 5% Mmax. The M-wave amplitudes evoked by the device were in the allowable range (9.2 +/- 2.5% Mmax). The device enabled control of the M-wave amplitude over the entire range of motion of the joint. Using this device, it was possible to examine the excitability of the alpha motor neuron pool more precisely.

Adult↗

PubMed1996

Parametrization by nonlinear regression analysis of the active acid metabolite of ebastine using different weighting methods.

The study of the analytical error function has been applied to evaluate the pharmacokinetics of ebastine active acid metabolite after a single oral dose of 10 mg of metabolite in 6 healthy volunteers. Plasma concentrations were measured using an automated solid phase extraction method. The analytical method was fully validated and the function of the analytical error subsequently determined. The parametric approach was performed by nonlinear regression analysis comparing the results obtained after the application of different weighted least square methods including the homoscedastic method (W = 1) and heteroscedastic methods using weights of 1/C, 1/C2 and the inverse of the concentration variance calculated through the function of the analytical error. The results obtained in the study showed no influence of the different weighting methods used on the estimation of the pharmacokinetic parameters of ebastine acid metabolite.

Administration, Oral↗

PubMed1977

Morale of the urban aged: a regression analysis by race.

This research examined the degree to which previous factors shown to be related to morale were isomorphic for aged whites and aged blacks. The data consisted of a random sample of low income aged blacks and whites in Philadelphia and were collected by the late Donald P. Kent as part of the Aged Services Porject and consisted of 722 black elderly and 214 white elderly, all of whom were 65 years of age or older. The results of a regression analysis indicated that for blacks the only two significant predictors of morale were health and participation in solitary activities. For whites, in addition to health and solitary activities, interaction with family and sex were also found to be significant. It was concluded that for these data the predictors are not isomorphic between races.

Black or African American↗

PubMed1978

Discrimination between descriptive models of L-glutamate uptake by the retina using non-linear regression analysis.

1. The uptake of labelled L-glutamate by the isolated rat retina was measured over a large range of external concentrations (1 micron to 1 mM). 2. The results obtained from measurements of the initial velocity of L-glutamate uptake at different concentrations did not follow simple hyperbolic kinetics. 3. The error structure of replicate velocity measurements was examined and found to be normally distributed and heteroscedastic. 4. Descriptive models were fitted directly to data, weighted by the invariance, using non-linear regression analysis. 5. The most suitable suitable descriptive model consisted of a saturable hyperbola (Vm = 285 n-mole.(g wet wt.)-1.min-1, Km = 252 micron) and a linear term (b = 0.45 min-1).

Animals↗

PubMed1992

Testing models of the redundant-signals effect: a warning concerning the combination-rule regression analysis.

The redundant-signals effect is the observed RT advantage for trials presenting two or more targets, as compared with trials with only one target. Two general classes of parallel-processing model have been proposed to explain this effect: race models (e.g., Raab, 1962) and coactivation models (e.g., Miller, 1982). Various distributional analyses have been used in work aimed at discriminating between these two model classes. The present study reexamined one of these tests--the combination-rule regression analysis based on variable-criterion theory (Grice, Canham, & Boroughs, 1984)--by applying it to the data from two sets of simulated experiments. One set of simulations assumed coactivation; the other set assumed an independent race on redundant-target trials. Nearly identical combination-rule values were observed in the two sets of simulations. This finding shows that the combination rule of variable-criterion theory does not discriminate between models capable of explaining the redundant-signals effect. The implications of this finding are briefly discussed.

Attention↗

PubMed2004

More powerful tests of predictor subsets in regression analysis under nonnormality.

It is well-known that for normally distributed errors parametric tests are optimal statistically, but perhaps less well-known is that when normality does not hold, nonparametric tests frequently possess greater statistical power than parametric tests, while controlling Type I error rate. However, the use of nonparametric procedures has been limited by the absence of easily performed tests for complex experimental designs and analyses and by limited information about their statistical behavior for realistic conditions. A Monte Carlo study of tests of predictor subsets in multiple regression analysis indicates that various nonparametric tests show greater power than the F test for skewed and heavy-tailed data. These nonparametric tests can be computed with available software.

Humans↗

PubMed2005

Biological stability in drinking water: a regression analysis of influencing factors.

Some parameters, such as assimilable organic carbon (AOC), chloramine residual, water temperature, and water residence time, were measured in drinking water from distribution systems in a northern city of China. The measurement results illustrate that when chloramine residual is more than 0.3 mg/L or AOC content is below 50 microg/L, the biological stability of drinking water can be controlled. Both chloramine residual and AOC have a good relationship with Heterotrophic Plate Counts (HPC)(log value), the correlation coefficient was--0.64 and 0.33, respectively. By regression analysis of the survey data, a statistical equation is presented and it is concluded that disinfectant residual exerts the strongest influence on bacterial growth and AOC is a suitable index to assess the biological stability in the drinking water.

Bacteria↗

PubMed1984

Linear regression analysis of binary response data with mixed covariates - a simulation study.

In a clinical trial with binary outcome, analyses are required for treatment or study group comparisons adjusted for covariate effects. A special problem arises with "mixed binary and Gaussian covariates", i.e., when some covariates are binary and some are continuous and may be assumed to be Gaussian. The correct model for such a data structure is of the logistic form. In the past, analyses of such data have been carried out by linear regression as well as by logistic regression methods. In this article, computer simulation was used to study the type I error level of linear regression analysis tests for treatment comparisons, when applied to a binary outcome variate obeying a logistic model with mixed binary and Gaussian covariates. It was found that the true type I error level depends on the distribution of covariates among treatment groups and on the magnitudes of the actual covariate effects, and can differ importantly from that assumed under Gaussian theory. Some recommendations are made for developing computer package programs for this problem.

Clinical Trials as Topic↗

PubMed2001

Regression analysis of cancer incidence rates and water fluoride in the U.S.A. based on IACR/IARC (WHO) data (1978-1992). International Agency for Research on Cancer.

Age-specific and age-standardized rates (ASR) of registered cancers for nine communities in the U.S.A. (21.8 million inhabitants, mainly white) were obtained from IARC data (1978-82, 1983-87, 1988-92). The percentage of people supplied with "optimally" fluoridated drinking water (FD) obtained from the Fluoridation Census 1985, U.S.A. were used for regression analysis of incidence rates of cancers at thirty six sites (ICD-WHO, 1957). About two-thirds of sites of the body (ICD) were associated positively with FD, but negative associations were noted for lip cancer, melanoma of the skin, and cancers of the prostate and thyroid gland. In digestive organs the stomach showed only limited and small intestine no significant link. However, cancers of the oral cavity and pharynx, colon and rectum, hepato-biliary and urinary organs were positively associated with FD. This was also the case for bone cancers in male, in line with results of rat experiments. Brain tumors and T-cell system Hodgkin's disease, Non-Hodgkin lymphoma, multiple myeloma, melanoma of the skin and monocytic leukaemia were also correlated with FD. Of the 36 sites, 23 were positively significant (63.9%), 9 not significant (25.0%) and 4 negatively significant (11.1%). This may indicate a complexity of mechanisms of action of fluoride in the body, especially in view of the coexising positive and negative correlations with the fluoridation index. The likelihood of fluoride acting as a genetic cause of cancer requires consideration.

Air Pollutants↗

PubMed2003

Detection and prediction of hydrolytic rancidity in milk by multiple regression analysis of short-chain free Fatty acids determined by solid phase microextraction gas chromatography and quantitative flavor intensity assessment.

The objective was to establish a method for detecting and predicting hydrolytic rancidity in milk by correlating quantitative sensory data with individual short-chain free fatty acids (FFA) (C(4)-C(12)) in milk determined by solid phase microextraction and gas chromatography (SPME-GC). A FFA-based equation for determining rancid flavor intensities in milk was derived by stepwise regression analysis. A highly significant (p < 0.001) correlation coefficient (R (2)) of 0.84 indicated that rancidity scores were dependent on FFA obtained by SPME-GC and that a good proportion of the variation in the rancidity scores was explained by the model. When rancidity scores were predicted for 19 commercial milks, one sample was found to be distinctly rancid by the statistical model and by the trained sensory panel. The rest of the samples were found to be nonrancid by either method. Thus, the predicting power of the model was shown because there was 100% correct flavor classification for the samples tested.

Animals↗

PubMed1985

Relative risk regression analysis of epidemiologic data.

Relative risk regression methods are described. These methods provide a unified approach to a range of data analysis problems in environmental risk assessment and in the study of disease risk factors more generally. Relative risk regression methods are most readily viewed as an outgrowth of Cox's regression and life model. They can also be viewed as a regression generalization of more classical epidemiologic procedures, such as that due to Mantel and Haenszel. In the context of an epidemiologic cohort study, relative risk regression methods extend conventional survival data methods and binary response (e.g., logistic) regression models by taking explicit account of the time to disease occurrence while allowing arbitrary baseline disease rates, general censorship, and time-varying risk factors. This latter feature is particularly relevant to many environmental risk assessment problems wherein one wishes to relate disease rates at a particular point in time to aspects of a preceding risk factor history. Relative risk regression methods also adapt readily to time-matched case-control studies and to certain less standard designs. The uses of relative risk regression methods are illustrated and the state of development of these procedures is discussed. It is argued that asymptotic partial likelihood estimation techniques are now well developed in the important special case in which the disease rates of interest have interpretations as counting process intensity functions. Estimation of relative risks processes corresponding to disease rates falling outside this class has, however, received limited attention. The general area of relative risk regression model criticism has, as yet, not been thoroughly studied, though a number of statistical groups are studying such features as tests of fit, residuals, diagnostics and graphical procedures. Most such studies have been restricted to exponential form relative risks as have simulation studies of relative risk estimation procedures with moderate numbers of disease events.

Age Factors↗

PubMed1991

Transmission of hepatitis B and hepatitis delta viruses in the households of chronic hepatitis B surface antigen carriers: a regression analysis of indicators of risk.

To evaluate whether clinical and laboratory features of a hepatitis B surface antigen (HBsAg) carrier can predict risks of infection, its chronicity, and the development of liver disease among close contacts, the authors studied a cohort of 994 first degree relatives or cohabitants (household contacts) of 226 non-drug-addicted chronic HBsAg carriers (index cases), of whom 77% had liver disease and 26% were superinfected by hepatitis D virus (HDV). A logistic form of regression analysis was used to assess the role of each feature in the index case as predictor of hepatitis B virus (HBV)- and HDV-related outcomes among household contacts. Six models of risk, expressed as odds ratios, were assessed by multivariate step-down analysis, with the following results. 1) Infection with HBV in the household contact was independently predicted by the index case being son, sibling, spouse, female, or HBV-DNA positive. 2) Chronic HBsAg carriage in the adult household contact was associated with female sex of the index case and with being a sibling; among young subjects, household contacts were more likely to be chronic HBsAg carriers when the index case was the mother, a sibling, or an HBV-DNA-positive subject. 3) HBV-DNA positivity in the young contact was more likely when the index case was HBV-DNA positive and when she was the mother. 4) HBV-DNA positivity in the absence of hepatitis B e antigen (HBeAg) in serum in the index case was not related to a similar pattern of infection in HBsAg-positive contacts. 5) Super-infection with HDV of an HBsAg-positive household contact was significantly predicted by female sex of the index case and by anti-HDV positivity. 6) Chronic liver disease in a contact was predicted only by HDV superinfection of the index case. We conclude that horizontal, nonparenteral transmission of HBV among siblings plays a major role in the household of HBsAg carriers from an intermediate endemicity area.

Adolescent↗

PubMed1990

Estimation of left ventricular ejection fraction with healed myocardial infarction by multiple regression analysis of electrocardiographic Minnesota Q-QS codes. POSCH Group.

The cardiac damage caused by a myocardial infarction may be evidenced by abnormal electrocardiographic Q-QS complexes (i.e., Minnesota Q-QS codes) and by impairment of left ventricular function. It has been shown that the level of significance of the Q-QS codes is highly correlated with the extent of left ventricular impairment. This study was directed to quantitating this relationship in subjects with a healed myocardial infarction and expressing it mathematically. Using multiple linear regression analysis, a coefficient value was obtained corresponding to the level of significance of each Q-QS code located in each electrocardiographic cardiac area. The left ventricular ejection fraction was estimated by subtracting the coefficient of the most significant code present in each cardiac area from the constant, which was calculated to be the ejection fraction in the absence of any Q-QS code. The results were reproducible, and there was a good correlation between the estimated and measured ejection fraction.

Adult↗

PubMed2005

Using half-normal probability plot and regression analysis to differentiate complex traits: differentiating disease response of multigenic resistance and susceptibility in tomatoes to multiple pathogen isolates.

The need for a new analytical approach was encountered in the course of characterizing newly developed tomato lines resistant to late blight. Late blight resistant tomato lines were created in independent breeding programs using the accession Solanum pimpinellifolium L. (formerly Lycopersicon pimpinellifolium (L.) Miller) L3708 as the source of the resistance. However, initial field observation suggested that the late blight resistance in the lines produced by two independent breeding programs differed. Possible causes included a partial transfer of the late blight resistance derived from S. pimpinellifolium L3708 or the possibility of race specificity of this resistance. A crucial issue was determining the most appropriate and robust analytical method to use with data from laboratory analyses of the responses of nine tomato lines against five P. infestans isolates. Prior analysis by standard ANOVA revealed significant differences across tomato lines but could not determine whether the disease responses in the CLN-R lines were different from those of the heterozygous F(1) hybrids, created by crossing susceptible tomatoes with the fixed CU-R lines. A different analytical method was needed. Therefore, sporangia numbers/leaflet and diseased area data were analyzed using a half-normal probability plot and regression analysis. The results of this analysis show its utility for genetic or pathology studies. Considering only populations of the uniform tomato lines, this method confirms the results obtained by using a standard ANOVA, but provides a clearer demonstration of the distributions of the individuals within the populations and how this distribution impacts variance and the difference among the populations. This method also allows a joint analysis of the uniform lines with an additional population that is less uniform, because it is segregating. Such an analysis would be invalid using a standard ANOVA. The results of this joint analysis determined that the additional population was divergent from the fixed CU-R lines, and, against some isolates, against the CLN-R lines as well. Half-normal probability plot analysis method would be applicable more broadly beyond analysis of disease resistance data. It could be useful for data from populations that are not normally distributed, for traits which are affected by epistatic gene action, and could be useful for selection of extremes.

Genotype↗

PubMed1989

Assessment of air pollution sources in an industrial atmosphere using principal component and multilinear regression analysis.

Aerosol samples collected in the industrial area of Estarreja, Portugal, were used to assess the source classes responsible for the particulate levels observed in the local atmosphere. Principal Component Analysis was applied separately to the concentrations of aerosol constituents and meteorological variables to obtain the number of Principal Components and to verify the influence of weather conditions on ambient air quality. The technique led to the conclusion that soil and transport emissions represent important aerosol sources even in this industrial environment. The quantitative contribution of each source class was calculated using Multilinear Regression Analysis; 37% of the aerosol mass had a soil origin, 8% was from sea spray, 18% resulted from transport emissions and 24% contained ammonium salts. Twelve percent of total suspended particle (TSP) mass could not be explained by any of the six Principal Components retained. Ammonium salts and two other minor Principal Components seem to result mainly from industrial emissions. More specific information about the contribution of each particular source was not possible with this technique.

Air Pollutants, Occupational↗

PubMed1984

Clinical macrovascular disease in Caucasoid diabetic subjects: logistic regression analysis of risk variables.

A cross-sectional study of 1084 Caucasoid diabetic subjects in rural Western Australia revealed a high rate of clinical macrovascular disease (46%), including coronary heart disease (13%), stroke (8%), and peripheral vascular disease (38%). Age was the major time-related variable for total macrovascular disease and for peripheral vascular disease, with identical prevalence rates in Type 1 (insulin-dependent) and Type 2 (non-insulin-dependent) diabetes when age was taken into account. In 179 Type 1 diabetic subjects, logistic regression analysis showed no associated risk factors other than age. In 905 Type 2 diabetic subjects the independent risk factors for total macrovascular disease, identified by a forward step-wise selection procedure, were age as the major contributor, with plasma creatinine levels and plasma glucose levels (all p less than 0.001), high-density lipoprotein cholesterol levels, serum total cholesterol levels, and the (supine-erect) systolic blood pressure difference (all p less than 0.05). There were no direct associations with percentage desirable weight, cigarette smoking or male sex. Type 2 diabetic subjects demonstrated a very strong negative association between high-density lipoprotein cholesterol levels and coronary heart disease, and significant associations were found also between plasma glucose levels and coronary heart disease (p less than 0.01), and glycosylated haemoglobin levels and peripheral vascular disease (p less than 0.001).

Adolescent↗