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 937 records · Page 52Linked to original sources
PubMed1991

Analysis of the use of multiple technologies in neonatal care.

The use of 53 different technologies was studied in 82 patients in a neonatal intensive care unit. Using a coefficient of similarity based on the utilization pattern of these technologies, it was possible to identify five clusters of patients that can be correlated with the primary diagnostic groups and such other variables as birth weight (BW), gestational age, length of stay (LOS), and weight gain. Four interdependent models were identified by multiple regression analysis. The number of different therapeutic technologies applied to these patients can be explained (r = 0.67) by their Apgar scores, gestational age, and an index of severity of illness based on the diagnostic group. The number of different diagnostic technologies used is directly related to the number of therapies delivered (r = 0.63) and, jointly with BW, determines LOS (r = 0.73). Finally, weight gain is explained by LOS and BW (r = 0.65).

Cluster Analysis↗
PubMed2005

Modeling daily energy balance of dairy cows in the first three lactations.

Daily energy balance was calculated for 111 Holstein cows in their first 3 lactations, based on combinations of smoothed preadjusted phenotypic records for milk yield, feed intake, live weight, and body condition score. Two energy balance traits were defined: one based on milk yield and feed intake (EB1) and the other on live weight and body condition score change (EB2). Bessel functions (BF), Legendre polynomials (LP), sinusoidal functions (SF), and cubic splines (CS) were used to model energy balance within and across lactations. Models with BF or LP fitted fixed regressions of order 1 to 6 and random regressions of order 1 to 10. Cubic splines were fitted at 5 to 30 equally spaced knot points. In within-lactation analyses with BF and LP models, likelihood ratio tests revealed that the fit improved significantly up to random regression order of 5 for EB1 and 4 for EB2, independently of the fixed regression order. For EB1 analyses with LP, improvement was marginal albeit significant even for higher random regression order. For CS models, optimal number of knot points was 13 and 12 for EB1 and EB2, respectively. Residual variance and comparisons between actual and predicted energy balance showed that LP of minimum order 8 and 5 modeled, respectively, EB1 and EB2 better than the other 3 functions. In across-lactation analyses with BF and LP models, likelihood ratio tests were significant as the random regression order increased, for any order of the fixed regression. For CS models, optimal number of knot points was 14 and 16 for EB1 and EB2, respectively. Residual variance and comparisons between actual and predicted energy balance showed that models fitting CS and high (>8) random order BF or LP provided the best fit to both traits. However, in an across-lactation analysis, even higher order of LP or BF will be required to provide as good a fit as within-lactation analyses.

Animals↗
PubMed1993

A nonlinear regression analysis of nonlinear, passive-deflation flow-volume plots.

When studying lung mechanics of intubated premature infants, by the passive-deflation technique we noted that in many flow-volume plots the descending limb was curvilinear with a convexity toward the volume axis. By conventional linear analysis lung mechanics of these patients did not change after the administration of terbutaline, but Mead's tangent-chord slope ratio method for quantifying the amount of curvature showed that the shape of the flow-volume plots did change. Because of the limitations of this method, we developed a microcomputer-based, reiterative regression algorithm which optimizes a nonlinear function for the best fit to any given set of data. We then studied six very low birth weight infants with clinical evidence of pulmonary gas trapping (weight at study, 1.22 +/- 0.29 kg; age, 26 +/- 16 days). We measured respiratory system resistance (Rrs), compliance (Crs), and expiratory time constants (TCrs) by the passive deflation technique before and after subcutaneous administration of 0.02 mg/kg of terbutaline. No effect of terbutaline in a dose sufficient to increase heart rate > 25 beats/min was observed. The same data analyzed using the nonlinear regression technique with a function based upon a two compartment model of parallel inhomogeneities revealed one compartment with relatively normal Rrs, Crs, and TCrs values, and a second compartment with a very high Rrs. The latter fell by 50% after terbutaline. These data suggest that abnormalities of airway resistance in ventilated preterm infants are not easily identifiable by classic linear analysis of lung mechanics.(ABSTRACT TRUNCATED AT 250 WORDS)

Airway Resistance↗
PubMed2000

[Determinations and analysis of masticatory performance in unilateral cleft lip and palate].

OBJECTIVE: Masticatory function is one of the most important physical functions in craniomaxilla system. Masticatory performance is evaluated with the degree of broken dawn tested food in a limited period of time. Unilateral cleft lip and palate (UCLP) is a congenital abnormality in craniofacial growth and developing. It seriously damages face esthetics and masticatory function in UCLP patients. METHODS: 28 UCLP patients (male 17, female 11, permanent teeth) were selected, which all had received plastic operation treatments and never received any orthodontic therapy. The masticatory performance was determined by the advanced light absorbtion method and took peanuts as tested food. Meanwhile, malocclusal patterns and castings were identified in clinic. All of the data were treated with t-test and step wise-regression in statistics. RESULTS: 1. Masticatory performance of male was higher than that of female in normal people, but there was no sexual difference in UCLP. 2. Masticatory performance in UCLP was lower about 53.97% than that in normal people. 3. Different masticatory times within limited time had no effects on masticatory performance. 4. Different Patterns of malocclusion had different effects on masticatory performance. CONCLUSION: Orthodontic therapy is necessary to improve masticatory function in UCLP after plastic surgery.

Adolescent↗
PubMed2003

Censored partial regression.

In this work we study the effect of several covariates on a censored response variable with unknown probability distribution. A semiparametric model is proposed to consider situations where the functional form of the effect of one or more covariates is unknown, as is the case in the application presented in this work. We provide its estimation procedure and, in addition, a bootstrap technique to make inference on the parameters. A simulation study has been carried out to show the good performance of the proposed estimation process and to analyse the effect of the censorship. Finally, we present the results when the methodology is applied to AIDS diagnosed patients.

Acquired Immunodeficiency Syndrome↗
PubMed2006

Market structure and technical efficiency in the hospital services industry: a DEA approach.

This article uses data envelopment analysis and multiple regression analysis to examine empirically the impact of various market-structure elements on the technical efficiency of the hospital services industry in various metropolitan areas of the United States. Market-structure elements include the degree of rivalry among hospitals, extent of HMO activity, and health insurer concentration. The DEA results show the typical hospital services industry experienced 11 percent inefficiency in 1999. Moreover, multiple regression analysis indicates the level of technical efficiency varied directly across metropolitan hospital services industries in response to greater HMO activity and private health insurer concentration in the state. The analysis suggests the degree of rivalry among hospitals had no marginal effect on technical efficiency at the industry level. Evidence also implies that the presence of a state Certificate of Need law was not associated with a greater degree of inefficiency in the typical metropolitan hospital services industry.

Catchment Area, Health↗
PubMed1991

Effect of oral contraception on water-suppressed proton NMR spectra of plasma.

Lipid linewidths were measured in the plasma proton spectra of young women. The individuals taking a contraceptive pill associating ethinyloestradiol and levonorgestrel or norethisterone were found with an average linewidth 2.5 Hz narrower than controls. As this drug regimen systematically induces an increase in plasma VLDL and a decrease in HDL/LDL ratio, our observation supports the theory that the Fossel test reflects plasma lipids abnormalities in cancer patients.

Adult↗
PubMed1989

A cautionary note on the use of autoregressive models in analysis of longitudinal data.

Rosner et al. presented a simple, easily implemented modelling method for retaining time order relationships in analyses of longitudinal data when successive measures are correlated. Evaluation of time order is particularly useful in epidemiologic studies concerned with exposure to potentially toxic substances and subsequent outcome, but may also have use in more traditional growth studies that relate intake to subsequent development. The analysis allows for unequally spaced measures and missing data. The estimation method permits varying numbers of observations per subject and, with measures equally spaced, one can fit the model with use of ordinary least squares regression software. We report on a potential false association that can result when both exposure and outcome are related to time. We illustrate this problem with a small scale simulation and example. We also note a more serious problem with Rosner's approach in interpreting parameters. Although the model may be useful for prediction, parameters depend on the autocorrelation and are not readily interpretable. We recommend alternative modelling strategies be used when autocorrelation of errors is suspected.

Age Factors↗
PubMed1991

A routine tool for detection and assessment of epidemics of influenza-like syndromes in France.

A regression model for the nonepidemic level of influenza-like syndrome has been estimated from the 55,200 cases collected between October 1984 and August 1988 using the French Communicable Diseases Computer Network. The start of a major epidemic in 1988-89 was detected early. The size of the epidemic, for the entire country, was estimated at approximately 4.3 million cases. The excess cost of sick-leave, among those of working age, was estimated at $86 million.

Disease Outbreaks↗
PubMed2005

Analysis of non-fatal and fatal injury rates for mine operator and contractor employees and the influence of work location.

INTRODUCTION: Mining injury surveillance data are used as the basis for assessing the severity of injuries among operator and contractor employees in the underground and surface mining of various minerals. METHOD: Injury rates during 1983-2002 derived from Mine Safety and Health Administration (MSHA) database are analyzed using the negative binomial regression model. The logarithmic mean injury rate is expressed as a linear function of seven indicator variables representing Non-Coal Contractor, Metal Operator, Non Metal Operator, Stone Operator, Sand and Gravel Operator, Coal Contractor, and Work Location, and a continuous variable, RelYear, representing the relative year starting with 1983 as the base year. RESULTS: Based on the model, the mean injury rate declined at a 1.69% annual rate, and the mean injury rate for work on the surface is 52.53% lower compared to the rate for work in the underground. With reference to the Coal Operator mean injury rate: the Non-Coal Contractor rate is 30.34% lower, the Metal Operator rate is 27.18% lower, the Non-Metal Operator rate is 37.51% lower, the Stone Operator rate is 23.44% lower, the Sand and Gravel Operator rate is 16.45% lower, and the Coal Contractor rate is 1.41% lower. Fatality rates during the same 20 year period are analyzed similarly using Poisson regression model. Based on this model, the mean fatality rate declined at a 3.17% annual rate, and the rate for work on the surface is 64.3% lower compared to the rate for work in the underground. With reference to the Coal Operator mean fatality rate: the Non-Coal Contractor rate is 234.81% higher, the Metal Operator rate is 5.79% lower, the Non-Metal Operator rate is 47.36% lower, the Stone Operator rate is 8.29% higher, the Sand and Gravel Operator rate is 60.32% higher, and the Coal Contractor rate is 129.54% higher.

Accidents, Occupational↗
PubMed2005

Covariate-adjusted varying coefficient models.

Covariate-adjusted regression was recently proposed for situations where both predictors and response in a regression model are not directly observed, but are observed after being contaminated by unknown functions of a common observable covariate. The method has been appealing because of its flexibility in targeting the regression coefficients under different forms of distortion. We extend this methodology proposed for regression into the framework of varying coefficient models, where the goal is to target the covariate-adjusted relationship between longitudinal variables. The proposed method of covariate-adjusted varying coefficient model (CAVCM) is illustrated with an analysis of a longitudinal data set containing calcium absorbtion and intake measurements on 188 subjects. We estimate the age-dependent relationship between these two variables adjusted for the covariate body surface area. Simulation studies demonstrate the flexibility of CAVCM in handling different forms of distortion in the longitudinal setting.

Adult↗
PubMed2006

Centering or not centering in multilevel models? The role of the group mean and the assessment of group effects.

In multilevel regression, centering the model variables produces effects that are different and sometimes unexpected compared with those in traditional regression analysis. In this article, the main contributions in terms of meaning, assumptions, and effects underlying a multilevel centering solution are reviewed, emphasizing advantages and critiques of this approach. In addition, in the spirit of Manski, contextual and correlated effects in a multilevel framework are defined to detect group effects. It is shown that the decision of centering in a multilevel analysis depends on the way the variables are centered, on whether the model has been specified with or without cross-level terms and group means, and on the purposes of the specific analysis.

Evaluation Studies as Topic↗
PubMedDate not supplied

Does family interaction prevent adolescent pregnancy?

This study uses data from the 1982 National Survey of Family Growth to ascertain whether family interaction can avert adolescent sexual activity, pregnancy, childbearing and parenthood. The results obtained from using logistic regression procedures indicate that the family may be effective in increasing adolescents' use of contraceptives and selection of abortion or adoption as alternatives to parenthood. Family interaction, however, was not associated with forestalling adolescent sexual activity or with providing for the well-being of the adolescent and her child and it is unlikely that a policy based solely on family interaction will be effective. Characteristics associated with effectiveness in preventing adolescent pregnancy included race, religion, residence, mother's education, the adolescent's age and family income.

Abortion, Legal↗
PubMed2001

Institutional Review Board approval for prospective experimental studies on infants and children.

BACKGROUND/PURPOSE: The Declaration of Helsinki requires Institutional Review Board (IRB) approval for experimental studies on human subjects. The authors questioned whether published prospective surgical experimental studies document IRB approval for infants and children. METHODS: Prospective studies were identified in 5 surgical and 2 major pediatric journals from 1997 through 1999. Documentation of IRB approval was recorded. Results were analyzed using Pearson chi(2) tests and a multivariate regression model. Statistical significance was defined as P less than .05. RESULTS: A total of 149 prospective experimental studies on pediatric subjects were evaluated; the majority being interventional or therapeutic studies (105 of 149). More than 75% were from academic medical centers (125 of 149), grant-supported (110 of 149), and appeared in surgical journals (110 of 149). Slightly less than 25% of studies (40 of 149) documented IRB approval. Observational studies, grant support, and publication in nonsurgical journals all correlated positively with IRB approval and were statistically significant variables (P<.001, P<.001, P<.001, respectively). Interventional or therapeutic, institutionally or privately-funded studies found in surgical journals were most likely to avoid IRB documentation (P<.001). CONCLUSIONS: The majority of prospective pediatric studies in the surgical journals omit IRB documentation. Strict requirements for specific IRB approval and documentation in compliance with the Declaration of Helsinki would allow higher ethical standards for the clinical investigation of infants and children.

Chi-Square Distribution↗
PubMed2000

Tissue Doppler imaging of the fetal heart.

OBJECTIVES: The objectives of this study were: (i) to assess the feasibility of a tissue Doppler imaging (TDI) evaluation in the fetus, (ii) to identify color-TDI patterns consistent with the various phases of the cardiac cycle; and (iii) to assess myocardial velocities and the myocardial velocity gradient. METHODS: Eighty-nine normal fetuses between the 17th and the 37th week of gestation were studied. Color-TDI was superimposed on an apical four-chamber view of the fetal heart and three cardiac cycles captured in cine-loop format. By reviewing the cine-loop strip, color patterns consistent with the various phases of the cardiac cycle were identified. The procedure was then repeated with a transverse four-chamber view. On each frame corresponding to mid-systole, early and late diastole, myocardial velocities were calculated at the subepicardial and subendocardial layer and regressed against gestational age. Statistics included correlation and regression analysis, calculation of the 95% confidence intervals and of the Cronbach's alpha reliability coefficient for repeated observations. RESULTS: TDI examination is acceptably reproducible in the fetus. We were able to identify color-TDI patterns depicting the systolic contraction wave, ventricular relaxation and atrial contraction. Statistical evaluation demonstrated that: all variables (systolic right and left subendocardial and subepicardial velocities, early diastolic right and left subendocardial and subepicardial velocities, end diastolic right and left subendocardial velocities, right subepicardial velocities) except end-diastolic right and left subepicardial velocities, showed a positive correlation with advancing gestational age; subendocardial velocities were higher than subepicardial ones throughout the cardiac cycle in both ventricles; systolic myocardial velocities were higher in the left ventricle whereas early diastolic velocities were higher in the right ventricle; and the ratio between early and late diastolic subendocardial velocities (EM/AM) was constantly < 1 and did not change with advancing gestational age. CONCLUSIONS: TDI evaluation of the fetal heart is feasible and reproducible. Color-TDI is able to identify the various phases of the cardiac cycle. Quantitative evaluation of myocardial velocities has shown also in the fetus the existence of the myocardial velocity gradient found in postnatal life.

Blood Flow Velocity↗
PubMed1980

The health of Mexican Americans: evidence from the human population laboratory studies.

Data are presented from sample surveys conducted in 1974 (N = 3,119) and 1975 (N = 657) in Alameda County, California, by the Human Population Laboratory. Mexican Americans are compared to Anglos and Blacks on selected health status indicators; chronic conditions, disability, symptoms and a summary measure, the Physical Health Spectrum. Comparisons of crude percentages indicate that, compared to Anglos, Blacks report having more chronic conditions, more disability and more symptoms, while Chicanos generally report fewer health problems than these two groups. Controlling for the effects of age, sex, education, family income, marital status, and perceived health reduces the Anglo/Black differentials in reported health problems, primarily by reducing the rates for Blacks. However, even after adjustment the prevalence rates for Blacks remain higher. After controlling for the effects of the six covariates, the rates for Chicanos remain essentially unchanged in both samples, e.g., lower than the other groups. Results of binary regression analysis indicate that the two most powerful predictors of health status in both samples are age/sex and perceived health. Ethnicity overall is not a good predictor of health status, accounting for 1 per cent or less of the explained variance. Socioeconomic status, while predicting slightly better than ethnicity, still accounts for less than 2% of the variance in health status.

Adult↗
PubMed2005

Comparison of random regression test-day models for Polish Black and White cattle.

Test-day milk yields of first-lactation Black and White cows were used to select the model for routine genetic evaluation of dairy cattle in Poland. The population of Polish Black and White cows is characterized by small herd size, low level of production, and relatively early peak of lactation. Several random regression models for first-lactation milk yield were initially compared using the "percentage of squared bias" criterion and the correlations between true and predicted breeding values. Models with random herd-test-date effects, fixed age-season and herd-year curves, and random additive genetic and permanent environmental curves (Legendre polynomials of different orders were used for all regressions) were chosen for further studies. Additional comparisons included analyses of the residuals and shapes of variance curves in days in milk. The low production level and early peak of lactation of the breed required the use of Legendre polynomials of order 5 to describe age-season lactation curves. For the other curves, Legendre polynomials of order 3 satisfactorily described daily milk yield variation. Fitting third-order polynomials for the permanent environmental effect made it possible to adequately account for heterogeneous residual variance at different stages of lactation.

Analysis of Variance↗