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 217 records · Page 12Linked to original sources

PubMed1982

Regression analysis in health services research: the use of dummy variables.

Dummy variables frequently are used in regression analysis but often in an incorrect fashion. A brief review of examples in the medical care literature showed that the interpretation of dummy variable regression coefficients and their significance was often incorrect or unclear. This article shows how dummy variables can be used and assessed properly. The importance of testing for the joint effect of a group of dummy variables is stressed. It also gives a standard and useful extension of the dummy variable technique to testing for the effect of collections of variables.

Blue Cross Blue Shield Insurance Plans↗

PubMedDate not supplied

[Statistical and regression analysis in interpreting computerized morphometric results].

UNLABELLED: The aim of the study is to construct the statistical framework requested by the interpretation of the results obtained through computerized morphometry procedures. The study also includes the regression analysis of the investigated quantitative features. MATERIAL AND METHODS: The automatic measurements performed under Zeiss KS400 environment were achieved on a microscopic specimen of dental pulp. The areas and the perimeters were determined for 139 fibroblasts, so as to define two statistical series able to characterize the size of the cells. RESULTS AND DISCUSSIONS: The results are formulated in both analytic and numerical terms, the latter relying on the graphical support and computational resources of Zeiss KS400 environment. Also, the mathematical support is implemented. The research focuses on three key aspects: (i) the role of the class organization (clustering) in the correct evaluation of the measured cellular areas, (ii) the global characterization of these areas by the standard statistical indices, (iii) the linear and quadratic regression perimeter versus area. CONCLUSIONS: The study is based on a concrete morphometric investigation of a dental pulp microscopic specimen, but the statistical and regression analysis can be applied to any other kind of specimen that undergoes a morphometric examination. The implementation under Zeiss KS400 is easy adaptable to other software environments providing similar facilities. For an exhaustive approach, in accordance with the sampling and selection laws, this type of study should be successively practiced on several fields of the microscopic specimens.

Algorithms↗

PubMed1987

Multiple regression analysis of sixteen risk factors including serum apolipoproteins in angiographically documented coronary artery disease.

Multiple regression analysis of 16 risk factors, including serum apolipoproteins in angiographically measured coronary stenosis, was carried out in 239 consecutive patients (159 males and 80 females, ranging in age from 30-80 years and mean 56.4 years) who underwent coronary angiography for suspected coronary artery disease during the past five years (1981-1985). The risk factors (independent variables) were age, total cholesterol (TC), triglyceride (TG), high density lipoprotein-cholesterol (HDL-C), low density lipoprotein-cholesterol (LDL-C), HDL-C/TC, apolipoprotein (Apo) A-I, A-II, B, C-II, C-III, E, YRSMOK (average number of packs per day X years of smoking), weight index (WI), glucose tolerance (GT), and blood pressure (BP). Severity of coronary atherosclerosis was scored as the extent of disease seen at arteriography (coronary score: CS). The order of importance of risk factors to CS in the five groups of subjects studied were as follows. (1) All patients: YRSMOK greater than Apo A-I greater than TC greater than GT, (2) Male group: Apo A-I greater than TC greater than Age greater than GT, (3) Female group: TC, (4) Young group (age below 54 years): BP greater than YRSMOK, and (5) Old group (age over 55 years): YRSMOK greater than TG greater than TC greater than GT. The results clearly indicated the importance of Apo A-I but not other apolipoproteins including Apo B in males, and that of blood pressure in the young group of the patients studied.

Adult↗

PubMed2000

Comparison of the role of dopamine, serotonin, and noradrenaline genes in ADHD, ODD and conduct disorder: multivariate regression analysis of 20 genes.

The present study is based on the proposal that complex disorders resulting from the effects of multiple genes are best investigated by simultaneously examining multiple candidate genes in the same group of subjects. We have examined the effect of 20 genes for dopamine, serotonin, and noradrenergic metabolism on a quantitative score for attention deficit hyperactivity disorder (ADHD) in 336 unrelated Caucasian subjects. The genotypes of each gene were assigned a score from 0 to 2, based on results from the literature or studies in an independent set of subjects (literature-based scoring), or results based on analysis of variance for the sample (optimized gene scoring). Multivariate linear regression analysis with backward elimination was used to determine which genes contributed most to the phenotype for both coding methods. For optimized gene scoring, three dopamine genes contributed to 2.3% of the variance, p = 0.052; three serotonin genes contributed to 3%, p = 0.015; and six adrenergic genes contributed to 6.9%, p = 0.0006. For all genes combined, 12 genes contributed to 11.6% of the variance, p = 0.0001. These results indicate that the adrenergic genes play a greater role in ADHD than either the dopaminergic or serotonergic genes combined. The results using literature-based gene scoring were similar. An examination of two additional comorbid phenotypes, conduct disorder and oppositional defiant disorder (ODD), indicated they shared genes with ADHD. For ODD different genotypes of the same genes were often used. These results support the value of the simultaneous examination of multiple candidate genes.

Adolescent↗

PubMed1992

Estimation of unbound concentrations of morphine from microdialysate concentrations by use of nonlinear regression analysis in vivo and in vitro during steady state conditions.

The unbound concentration of morphine in striatum of rats was estimated during a constant rate infusion of morphine 14 mumol/h*kg, by use of the microdialysis technique and nonlinear regression analysis. The concentrations in plasma of morphine and its metabolite, morphine-3-glucuronide, were 4.2 +/- 1.4 microM and 7.7 +/- 4.0 microM, respectively, during the constant rate infusion. The corresponding estimated unbound concentrations of morphine in striatum varied between 0.06 and 0.11 microM. No morphine-3-glucuronide was detected in the brain dialysates. The unbound concentration in striatum was lower than expected based on unbound plasma concentrations and could be an indication of active transport from the brain. Five different equations were tested to find the best empirical description of the relationship between microdialysate concentration and perfusion rate by nonlinear regression analysis. The equations were validated by a serum in vitro study, where three unbound concentrations of morphine estimated from microdialyis were compared to estimates obtained from equilibrium dialysis. The precision of the parameter estimates obtained from the five equations was tested by Monte Carlo simulations. One of the equations (Eq. 4) was selected in preference to the others, because of the good agreement with the estimated unbound concentration obtained by equilibrium dialysis in vitro, and good precision of the parameter estimates. The method described in this paper is valuable when estimating the unbound concentration of drug from microdialysate concentrations during steady state conditions. Furthermore, the method is easily accessible when working in the pharmacokinetic and pharmacodynamic field.

Animals↗

PubMedDate not supplied

Using logistic regression analysis in preliminary differential diagnosis of adnexal masses.

The aim of our study was to generate predictive model, which would allow to estimate the influence of analyzed parameters on predictive accuracy of differential diagnosis of adnexal masses and to evaluate prospectively diagnostic efficacy of the statistic model in the new set of patients. A total of 686 women diagnosed and surgically treated in the Gynecological and Obstetrical Teaching Hospital of University of Medical Sciences in Poznan, Poland, were recruited into the study. Preoperative diagnostics included gynecological examination, ultrasonographic evaluation, tumor Doppler blood flow analysis, and serum levels of CA125 and TPS. In order to find the best combination of features and to calculate the individual probability of the malignancy, stepwise logistic regression analysis with quasi-Newton estimation was applied. The essential part of the best prognostic model, described by foregoing variables, is as follows: [z = -6.005 + 0.058 x age + 1.174 x septa + 1.317 x tumor localization + 1.185 x ascites + 2.28 x solid element + 2.429 x vessels localization -2.386 x PI + 0.084 x MEDV]. The highest sensitivity and specificity for the obtained model were 87.84% and 93.74%, respectively. Prognostic model, constructed with the use of logistic regression analysis, is characterized by higher sensitivity and specificity than individually applied diagnostic tests. Prospective evaluation of this model application in a larger group of patients with adnexal masses will enable precise assessment of its objective clinical usefulness.

Adnexal Diseases↗

PubMed2006

The time course of visual word recognition as revealed by linear regression analysis of ERP data.

EEG correlates of a range of psycholinguistic word properties were used to investigate the time course of access to psycholinguistic information during visual word recognition. Neurophysiological responses recorded in a visual lexical decision task were submitted to linear regression analysis. First, 10 psycholinguistic features of each of 300 stimulus words were submitted to a principal component analysis, which yielded four orthogonal variables likely to reflect separable processes in visual word recognition: Word length, Letter n-gram frequency, Lexical frequency and Semantic coherence of a word's morphological family. Since the lexical decision task required subjects to distinguish between words and pseudowords, the binary variable Lexicality was also investigated using a factorial design. Word-pseudoword differences in the event-related potential first appeared at 160 ms after word onset. However, regression analysis of EEG data documented a much earlier effect of both Word length and Letter n-gram frequency around 90 ms. Lexical frequency showed its earliest effect slightly later, at 110 ms, and Semantic coherence significantly correlated with neurophysiological measures around 160 ms, simultaneously with the lexicality effect. Source estimates indicated parieto-temporo-occipital generators for the factors Length, Letter n-gram frequency and Word frequency, but widespread activation with foci in left anterior temporal lobe and inferior frontal cortex related to Semantic coherence. At later stages (>200 ms), all variables exhibited simultaneous EEG correlates. These results indicate that information about surface form and meaning of a lexical item is first accessed at different times in different brain systems and then processed simultaneously, thus supporting cascaded interactive processing models.

Adult↗

PubMed1980

A program for non-linear regression analysis to be used on desk-top computers.

A simple program for non-linear regression analysis, based upon the strategy of evolution, is described. It should run on any minicomputer (even on "personal computers') if a BASIC interpreter is available. It can easily be modified for the both the type of function and the "best fitting' condition.

Anti-Bacterial Agents↗

PubMed2005

Comparison of methods for calculating serum osmolality: multivariate linear regression analysis.

BACKGROUND: There are several methods for calculating serum osmolality, and their accordance with measured osmolality is the subject of controversy. METHODS: The concentrations of sodium, potassium, glucose, blood urea nitrogen (BUN) and osmolalities of 210 serum samples were measured. Two empirical equations were deduced for the calculation of serum osmolality by regression analysis of the data. To choose the best equation, chemical concentrations were also used to calculate osmolalities according to our formulas and 16 different equations were taken from the literature and compared with the measured osmolalities. Correlation and linear regression analyses were performed using Excel and SPSS software. RESULTS: Multiple linear regression analysis showed that serum concentrations of sodium (beta = 0.778, p< or = 0.000), BUN (beta = 0.315, p < or = 0.000), glucose (beta = 0.0.089, p < or = 0.007) and potassium (beta = 0.109, p < or = 0.008) are strong predictors of serum osmolality. The data were also analyzed by manual linear regression to yield the equations: osmolality = 1.897[Na + ]+glucose+BUN+13.5, and osmolality = 1.90[Na+ + K+]+glucose+BUN+5.0. The osmotic coefficient for sodium and potassium solutes was deduced to be 0.949 from the slope of the curves of measured osmolality vs. [Na+] and [Na+ + K+], respectively. The inclusion of a BUN value in the equation for osmolality increased the correlation coefficient by approximately 450% and decreased the SD of difference by approximately 35% (p < or = 0.002). Inclusion of the osmotic coefficient for sodium solutes caused an underestimation of measured osmolality and positive osmolal gap unless an appropriate coefficient, constant value and/or the potassium value were included in the equation. The agreement was not improved when molal chemical concentrations were used instead of molar values. The formula presented by Dorwart and Chalmers gave inferior results to those obtained with our formulas. CONCLUSIONS: Our data suggest use of the Worthley et al. formula Osm = 2[Na +]+glucose+BUN for rapid mental calculation and the formulas of Bhagat et al. or ours for calculation of serum osmolality by equipment linked to a computer.

Blood Glucose↗

PubMed1975

Regression analysis of the relationship between physical properties and the in vitro inhibition of monoamine oxidase by propynylamines.

Regression analysis of the potency of inhibition of monoamine oxidase by 47 propynylamines revealed that there are three determinants of inhibitory potency: (1) the smallest substituent on the nitrogen must be methyl or hydrogen in order for any activity to be observed; (2) potency is parabolically related to pKa-the optimum pKa is 6.2; and (3) ortho-substituted benzylamine analogs are ten times more potent than predicted on the basis of pKa values. The optimum pKa cannot be explained by differences in fraction ionized but rather in terms of the multistep sequence whereby these compounds inhibit MAO. A very slight positive effect of hydrophobicity on potency was found. The potency of several analogs not included in the original analysis was predicted.

Alkynes↗

PubMed2005

Pleiotropic effects of statins: benefit beyond cholesterol reduction? A meta-regression analysis.

OBJECTIVES: This study sought to determine whether statins reduce coronary heart disease (CHD) risk more than other interventions that also primarily lower low-density lipoprotein cholesterol (LDL-C). BACKGROUND: Statins have anti-inflammatory, immunomodulatory, antithrombotic, vascular, and other non-LDL-C-lowering effects. It is unclear whether these pleiotropic effects contribute to cardiovascular risk reduction beyond that expected from LDL-C reduction alone. METHODS: Trials published in English language journals were retrieved by searching Medline (1966 to October 2004), bibliographies, and the author's reference files. Randomized, placebo-controlled trials of interventions to primarily lower LDL-C of three or more years' duration in which clinical disease or death were primary outcomes were used. Information on sample size, treatment type and duration, participant characteristics at baseline, reduction in lipids, and outcome was independently abstracted by two authors (J.R. and N.M.) using a standardized protocol. Data from 5 diet, 3 bile acid sequestrant, 1 surgery, and 10 statin trials, with 81,859 participants, were included in the CHD meta-regression analysis. RESULTS: The regression lines for non-statin and statin trials were similar and consistent with a one-to-one relationship between LDL-C lowering and CHD and stroke reduction over five years of treatment. CONCLUSIONS: The pleiotropic effects of statins do not seem to contribute an additional cardiovascular risk reduction benefit beyond that expected from the degree of LDL-C lowering observed in other trials that primarily lowered LDL-C.

Cholesterol, LDL↗

PubMedDate not supplied

Multiple-dose non-linear regression analysis program. Aminoglycoside dose prediction.

The ability of a new multiple-dose non-linear regression analysis program to predict steady-state aminoglycoside peak and trough serum concentrations was evaluated. 30 patients receiving either amikacin (7), gentamicin (10) or tobramycin (13) were studied. A standard method of prediction which requires the collection of 3 or 4 serum samples during a dosing interval and a predictive method which relies upon population-based estimates of pharmacokinetic parameters were compared with the new approach which requires the collection of 2 serum samples. There were no significant differences between the methods which utilised serum concentration data with regard to predictive precision (mean prediction error of about 10%). These methods were more precise than the population-based method (p less than 0.01, mean prediction error 29.1%). None of the methods produced biased estimates. These results indicate that when the regression program is employed, valid estimates of pharmacokinetic parameters and prediction of steady-state serum concentrations can be obtained with fewer serum samples than have been recommended.

Adult↗

PubMed2001

A step-by-step guide to non-linear regression analysis of experimental data using a Microsoft Excel spreadsheet.

The objective of this present study was to introduce a simple, easily understood method for carrying out non-linear regression analysis based on user input functions. While it is relatively straightforward to fit data with simple functions such as linear or logarithmic functions, fitting data with more complicated non-linear functions is more difficult. Commercial specialist programmes are available that will carry out this analysis, but these programmes are expensive and are not intuitive to learn. An alternative method described here is to use the SOLVER function of the ubiquitous spreadsheet programme Microsoft Excel, which employs an iterative least squares fitting routine to produce the optimal goodness of fit between data and function. The intent of this paper is to lead the reader through an easily understood step-by-step guide to implementing this method, which can be applied to any function in the form y=f(x), and is well suited to fast, reliable analysis of data in all fields of biology.

Computational Biology↗

PubMed1986

Regression analysis in the presence of heterogeneous intraclass correlations.

In the statistical analysis of twinship and familial data, one often encounters the need for regression methods that control for the possibly different aggregation of the twins and the members of the families according to their type (e.g., monozygotic, dizygotic for twinship data). We present the maximum likelihood solution for the regression analysis of data in the presence of heterogeneous intraclass correlations. This work extends previous results for the case of a homogeneous intraclass correlation. An application of the methods for the analysis of twinship data is included.

Adult↗

PubMed1984

Regression analysis in medical research.

Even the most respected medical journals continue to publish articles containing unwarranted conclusions, which thus appear validated. This often results from the unfamiliarity of medical investigators with statistics leading to improper study design, data collection, analysis, and presentation. The increased use of multivariate analysis adds to the perplexity of medical readers not adequately prepared to judge the statistical method. This article attempts to acquaint readers with the terminology of regression analysis and how to use regression formulas.

Methods↗

PubMed2004

The impact of pharmacogenomic factors on steroid dependency in pediatric heart transplant patients using logistic regression analysis.

Many pharmacogenomic predictors of drug response are now available, and include both drug metabolism-disposition factors and drug targets. Information on statistical approaches to analyzing large clinical data sets in relation to genetic polymorphisms is limited. The objective of this study was to evaluate whether logistic regression could identify pharmacogenomic predictors of outcome in a large data set in a complex transplant patient population. Seventy pediatric heart transplant patients were studied. Patients were followed for at least 1 yr post-transplantation as outpatients, and weaned from corticosteroids if clinically appropriate. Logistic regression analysis was used to identify the predictors of steroid dependency. The dependent variable was the presence or absence of steroid therapy at 1 yr post-transplantation. The independent variables were the patients' transplant age, gender, MDR1 C3435T and G2677T, CYP3A53B and cytokine polymorphisms. By chi-square test for the MDR1 C3435T polymorphism, 12 of 18 (67%) patients in the CC group were still on prednisone, whereas only 18 of 47 (38%) of the CT/TT group were still receiving prednisone (p = 0.04). For the IL-10 groups, two of 15 patients with the high producer genotype (13.3%) remained on prednisone, in comparison with 16 of 28 patients with the intermediate producer genotype (57.1%) and 15 of 26 patients with the low producer genotype (57.7%, p = 0.01). Logistic regression analysis confirmed MDR1 C3435T (p = 0.021), and IL-10 polymorphisms (intermediate producer genotype p = 0.015; low producer genotype p = 0.013) as independent risk factors for steroid dependency at 1 yr after transplantation. This approach identifies pharmacogenomic factors, which can be studied more extensively in larger data sets, and used in prospective studies to individualize immunosuppressive therapy following solid organ transplantation.

Adolescent↗

PubMed1998

Regression analysis of multiple protein structures.

A general framework is presented for analyzing multiple protein structures using statistical regression methods. The regression approach can superimpose protein structures rigidly or with shear. Also, this approach can superimpose multiple structures explicitly, without resorting to pairwise superpositions. The algorithm alternates between matching corresponding landmarks among the protein structures and superimposing these landmarks. Matching is performed using a robust dynamic programming technique that uses gap penalties that adapt to the given data. Superposition is performed using either orthogonal transformations, which impose the rigid-body assumption, or affine transformations, which allow shear. The resulting regression model of a protein family measures the amount of structural variability at each landmark. A variation of our algorithm permits a separate weight for each landmark, thereby allowing one to emphasize particular segments of a protein structure or to compensate for variances that differ at various positions in a structure. In addition, a method is introduced for finding an initial correspondence, by measuring the discrete curvature along each protein backbone. Discrete curvature also characterizes the secondary structure of a protein backbone, distinguishing among helical, strand, and loop regions. An example is presented involving a set of seven globin structures. Regression analysis, using both affine and orthogonal transformations, reveals that globins are most strongly conserved structurally in helical regions, particularly in the mid-regions of the E, F, and G helices.

Algorithms↗

PubMed1989

[An epidemiological survey follow-up study on infant breast-feeding. III. Multiple stepwise regression analysis to factors affecting human milk amount].

This paper reports the result of multiple regression analysis to factors affecting human milk amount. By using survey follow-up study method, the data were obtained from 461 mothers who breast-fed their infants within six months after delivery. According to the results of stepwise regression, factors including the number of breast-feeding per day after one month post-partum, the number of breast-feeding per day within one month post-partum, breast-feeding infant regularly, menstruation recovery late are related to the amount of breast milk positively (increasing human milk amount), and factors including maternal poor appetite in lactation period, family deficient breast milk history, infant poor development, maternal disease in pregnancy and lactation period, contraceptive agents used, sunk or sore nipples are related to the amount of breast milk negatively (decreasing human milk amount). Because there are a lot of factors can affect human milk amount, it coincides with practical situation that multiple analysis is used to analysis these factors. It is also an attempt to use this method in mother and infant health care field.

Breast Feeding↗