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 37 records · Page 2Linked to original sources
PubMed1990

Parallelism test on microcomputers for statistically comparing regression lines of bivariate data sets.

Biomedical research is frequently confronted with regression lines that directionally describe the trend of phenomena, each one represented by a set of correlated x and y data. There could be a need to verify whether the regressions lines of two (or more) phenomena are statistically comparable in their slopes and intercepts, in order to draw conclusions about the similarity or dissimilarity of the conditions under scrutiny. The parallelism test the principles and methodology of which are presented here addresses this problem. A program for microcomputers is supplied as a non-profit software that can be freely shared on the understanding that the copyright belongs to the authors of this article.

Analysis of Variance↗
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↗
PubMed2003

Optimization of structural variables of a flextensional transducer by the statistical multiple regression analysis method.

The performance of an acoustic transducer is determined by the effects of many structural variables, and in most cases the influences of these variables are not linearly independent of each other. To achieve optimal performance of an acoustic transducer, we must consider the cross-coupled effects of its structural variables. In this study, with the finite-element method, the variation of the operation frequency and sound pressure of a flextensional transducer in relation to its structural variables is analyzed. Through statistical multiple regression analysis of the results, functional forms of the operation frequency and sound pressure of the transducer in terms of the structural variables were derived, with which the optimal structure of the transducer was determined by means of a constrained optimization technique, the sequential quadratic programming method of Phenichny and Danilin. The proposed method can reflect all the cross-coupled effects of multiple structural variables, and can be extended to the design of general acoustic transducers.

Journal Article↗
PubMedDate not supplied

[Speed of calcaneal ultrasound attenuation in the identification of vertebral fractures in patients with senile osteoporosis].

Vertebral collapse is a frequent complication of osteoporosis with usually severe sequels. We examined a group of female patient with known senile osteoporosis to try to define a subgroup with atraumatic vertebral collapse on the basis of broadband ultrasound attenuation (BUA) values in the heel. 186 patients were submitted to calcaneal ultrasound densitometry and to radiography of the dorsolumbar spine; we also investigated the body mass index and postmenopausal and menopausal ages to identify the variable with the highest correlation with fracture, with the multiple regression statistical analysis. The regression model analysis showed a statistically significant correlation of BUA values (inverse relation) and weight (direct relation) with the risk of collapse (0.967 and 1.075 odds ratio, respectively). We subdivided the patients according to their body mass index and made the receiver operating characteristics (ROC) curves, thus increasing test accuracy, with 45 MHz BUA threshold, 66.67% sensitivity and 71.43% specificity. Calcaneal BUA is a good indicator of atraumatic vertebral collapse in senile osteoporosis patients; when the weight variable is associated, sensitivity, specificity and positive and negative predictive values (66.67%, 71.43% and 66.6% and 71%, respectively) increase, thus helping define this subgroup of patients.

Aged↗
PubMed2004

Advanced statistics: linear regression, part II: multiple linear regression.

The applications of simple linear regression in medical research are limited, because in most situations, there are multiple relevant predictor variables. Univariate statistical techniques such as simple linear regression use a single predictor variable, and they often may be mathematically correct but clinically misleading. Multiple linear regression is a mathematical technique used to model the relationship between multiple independent predictor variables and a single dependent outcome variable. It is used in medical research to model observational data, as well as in diagnostic and therapeutic studies in which the outcome is dependent on more than one factor. Although the technique generally is limited to data that can be expressed with a linear function, it benefits from a well-developed mathematical framework that yields unique solutions and exact confidence intervals for regression coefficients. Building on Part I of this series, this article acquaints the reader with some of the important concepts in multiple regression analysis. These include multicollinearity, interaction effects, and an expansion of the discussion of inference testing, leverage, and variable transformations to multivariate models. Examples from the first article in this series are expanded on using a primarily graphic, rather than mathematical, approach. The importance of the relationships among the predictor variables and the dependence of the multivariate model coefficients on the choice of these variables are stressed. Finally, concepts in regression model building are discussed.

Bias↗
PubMed2000

Normative growth standard for upper arm measurements for exclusively breastfed infants.

OBJECTIVE: To develop a normogram for upper arm measurements for the evaluation of exclusively breastfed infants and to evaluate the clinical usefulness of the normogram. DESIGN: A prospective study involving the evaluation of infants discharged from the Newborn Unit and follow-up for the first six months of life while being exclusively breastfed. SETTING: Neonatal follow up Clinic, University Teaching Hospital, Benin City, Nigeria from 1st June, 1995 to 31st May, 1997. SUBJECTS: A total of 219 exclusively breastfed infants were recruited and analysed for the development of the normogram. A second group of 100 normal exclusively breastfed infants were evaluated to determine the clinical usefulness of the normogram. INTERVENTIONS: Determination of the upper arm measurement of the infants and development of the normogram using the statistics of the regression analysis of these measurements on postnatal age. MAIN OUTCOME MEASURES: Upper arm measurements, mean measurements at each completed month, regression statistics (MAC on postnatal age). RESULTS: Mean MAC measurements increased progressively from the first to the sixth completed months. There was a significant difference between the mean measurements at the 4th and 6th completed months. Upper arm measurements showed a highly significant correlation with postnatal age and the regression line and the 95% confidence limits were used to develop the normogram. Of the 100 infants in the second group, 92% had normal infant growth using the normogram. CONCLUSION: The developed normogram of upper arm measurements was evaluated to be clinically useful in exclusively breastfed infants.

Anthropometry↗
PubMed1990

Risk factors of alcoholism in Taiwan Chinese: an epidemiological approach.

This study investigated the risk factors of alcohol abuse and alcohol dependence, as defined by DSM-III criteria, in 11,004 Chinese subjects in the Taiwan community. Risk factors were analyzed using chi-square and multivariate logistic regression statistics. The logistic regression shows that the risk factors of alcohol dependence include male, having had childhood or adulthood behavior problems; of alcohol abuse include male, having had childhood or adulthood behavior problems, non-metropolitan community, age cohort, job-holder. The etiological models proposed are biological for Chinese alcohol dependence and interactional for Chinese alcohol abuse.

Adult↗
PubMed1991

Risk factors of alcoholism among Taiwan aborigines: implications for etiological models and the nosology of alcoholism.

The objective of this study was to explore possible risk factors of alcohol abuse (AA) and dependence (AD), as defined by DSM-III criteria, in Taiwan aborigines. The risk factors in a sample of 1555 Taiwan aborigines were analyzed by using the chi-square test and multivariate logistic regression statistics. The logistic regression showed that the risk factors of AD are being male, having relatively little education, being involved in a problem marriage, being a laborer, being part of a couple with a drinking problem, and having a positive family history of alcoholism. AA has the risk factors of ethnic subgroups dwelling in the main Taiwan Island, male, poor education, working people, and a drinking problem for the couple. Etiological models are proposed as social origins for AA, with interactional model for AD, in this aboriginal sample. Data on Chinese alcoholism is discussed, and a generalized hypothesis constructed that, for the same phenotypical subtype of alcoholism in different ethnic groups, the etiological models are different.

Adult↗
PubMed2004

Experimentally induced androgen depletion accentuates ethnicity-related contrasts in luteinizing hormone secretion in asian and caucasian men.

The basis for ethnicity-related distinctions in gonadotropin secretion are unknown but may have important populational and physiological implications. In male contraceptive trials, exogenous testosterone and progestins suppress spermatogenesis to a greater degree in Asian than Caucasian men. In addition, iv infusion of testosterone inhibits LH release more in Asian than Caucasian volunteers. We test the converse postulate that experimental reduction of androgen-dependent negative feedback by way of the steroidogenic inhibitor combination ketoconazole/dexamethasone will unveil ethnicity-related mechanisms of regulated LH secretion in young men. LH release was monitored by sampling blood every 10 min for 24 h followed by immunoradiometric assay, model-free pulse detection, an entropy (regulatory) statistic, and cosine regression. Statistical comparisons revealed that healthy young Asian and Caucasian men maintain comparable baseline concentrations of LH, testosterone, estradiol, SHBG, and molar testosterone to SHBG ratios. In contrast, the two ethnic groups differ prominently in each of basal, pulsatile, entropic, and 24-h rhythmic LH adaptations to short-term androgen withdrawal. Therefore, we postulate that physiological nonuniformity of sex steroid-dependent negative feedback in particular may contribute to populational diversity in LH regulation.

Adaptation, Physiological↗
PubMed2003

Quantile regression: a statistical tool for out-of-hospital research.

The performance of out-of-hospital systems is frequently evaluated based on the times taken to respond to emergency requests and to transport patients to hospital. The 90th percentile is a common statistic used to measure these indicators, since they reflect performance for most patients. Traditional regression models, which assess how the mean of a distribution varies with changes in patient or system characteristics, are thus of limited use to researchers in out-of-hospital care. In contrast, quantile regression models estimate how specified quantiles (or percentiles) of the distribution of the outcome variable vary with patient or system characteristics. The authors examined the performance of traditional linear regression vs. that of quantile regression to assess the association between hospital transport interval and patient and system characteristics. They demonstrate that richer inferences can be drawn from the data using quantile regression, utilizing data drawn from a study of ambulance diversion and out-of-hospital delay. The results demonstrate that the effect of ambulance diversion upon out-of-hospital transport intervals is not uniform, but is worse on the right tail of the distribution of transport intervals. In other words, ambulance diversion disproportionately affects those patients who already have longer transport intervals. Second, the distribution of transport intervals, conditional on a given set of variables, is positively skewed, and not uniformly or symmetrically distributed. The flexibility of quantile regression models makes them particularly well suited to out-of-hospital research, and they may allow for more relevant evaluation of out-of-hospital system performance.

Ambulances↗
PubMed2004

Advanced statistics: linear regression, part I: simple linear regression.

Simple linear regression is a mathematical technique used to model the relationship between a single independent predictor variable and a single dependent outcome variable. In this, the first of a two-part series exploring concepts in linear regression analysis, the four fundamental assumptions and the mechanics of simple linear regression are reviewed. The most common technique used to derive the regression line, the method of least squares, is described. The reader will be acquainted with other important concepts in simple linear regression, including: variable transformations, dummy variables, relationship to inference testing, and leverage. Simplified clinical examples with small datasets and graphic models are used to illustrate the points. This will provide a foundation for the second article in this series: a discussion of multiple linear regression, in which there are multiple predictor variables.

Biometry↗
PubMed2004

[Assessment of exposure to traffic pollution in epidemiological studies: a review].

BACKGROUND: Automobile exhaust is a major source of air pollution in urban areas. To study health effects of traffic exhaust fumes epidemiologists need specific tools in order to achieve a precise assessment of human exposure to traffic air pollution (TAP) and avoid misclassification. The aim of this review is to study the different ways of assessing human exposure to TAP in epidemiological studies dealing with short-term or long-term health effects of TAP. METHODS: After presenting the different designs and goals of the studies mentioned above, this review focuses on methods of assessing exposure to TAP and their different associated health endpoints. RESULTS: To assess exposure to TAP, most published studies have used more or less complex exposure indices. Several teams have used residence location and its proximity to traffic, traffic counts, or a combination of both. More recently, some authors have developed mathematical dispersion models and statistical regression models. DISCUSSION: Our analysis shows that reliable and validated tools would be needed to assess accurately human exposure to TAP. This can only be achieved with statistical regression models and mathematical dispersion models. Although such methods may be difficult to implement, their use can be facilitated by adding a geographic information system.

Adolescent↗
PubMed2006

The impact of ambient temperature on mortality among the urban population in Skopje, Macedonia during the period 1996-2000.

BACKGROUND: This study assesses the relationship between daily numbers of deaths and variations in ambient temperature within the city of Skopje, R. Macedonia. METHODS: The daily number of deaths from all causes, during the period 1996-2000, as well as those deaths from cardiovascular diseases, occurring within the city of Skopje were related to the average daily temperature on the same day using Multiple Regression statistical analyses. Temperature was measured within the regression model as two complementary variables: 'Warm' and 'Cold'. Excess winter mortality was calculated as winter deaths (deaths occurring in December to March) minus the average of non-winter deaths (April to July of the current year and August to November of the previous year). RESULTS: In this study the average daily total of deaths was 7% and 13% greater in the cold when compared to the whole period and warm period respectively. The same relationship was noticed for deaths caused by cardiovascular diseases. The Regression Beta Coefficient (b = -0.19) for the total mortality as a function of the temperature in Skopje during the period 1996-2000 was statistically significant with negative connotation as was the circulatory mortality due to average temperature (statistically significant regression Beta coefficient (b = -0.24)). A measure of this increase is provided, on an annual basis, in the form of the excess winter mortality figure. CONCLUSION: Mortality with in the city of Skopje displayed a marked seasonality, with peaks in the winter and relative troughs in the summer.

Adolescent↗
PubMed1998

Cytologic features of mycobacterial pleuritis: logistic regression and statistical analysis of a blinded, case-controlled study.

Tuberculous pleural effusions are characterized by lymphocytosis; the significance of mesothelial cells is uncertain, as are the cytologic features in concurrent human immunodeficiency virus (HIV) infection. This blinded study compared 38 culture-positive pleural fluids (6 HIV+) with 38 controls from benign exudative processes. Logistic regression analysis selected mature lymphocytes as most predictive of positive culture, and mesothelial cells and eosinophils as negative predictors. Mesothelial cells were scant (< 10% of nucleated cells) in 36/38 cases with mycobacteria (sensitivity 95%); if these cell were > 10%, tuberculosis was virtually ruled out in HIV- patients. Specificity was maximized (82%) when mesothelial cells < 10% were combined with lymphocytes > 50%; positive predictive value with this combination was 76%, but was raised to 96% if moderate/marked cellularity was also identified. Among tuberculosis cases, reactive mesothelial cells differentiated HIV+ from HIV- patients; there was no other significant difference.

Acquired Immunodeficiency Syndrome↗
PubMed2004

Automatic quality assessment of peptide tandem mass spectra.

MOTIVATION: A powerful proteomics methodology couples high-performance liquid chromatography (HPLC) with tandem mass spectrometry and database-search software, such as SEQUEST. Such a set-up, however, produces a large number of spectra, many of which are of too poor quality to be useful. Hence a filter that eliminates poor spectra before the database search can significantly improve throughput and robustness. Moreover, spectra judged to be of high quality, but that cannot be identified by database search, are prime candidates for still more computationally intensive methods, such as de novo sequencing or wider database searches including post-translational modifications. RESULTS: We report on two different approaches to assessing spectral quality prior to identification: binary classification, which predicts whether or not SEQUEST will be able to make an identification, and statistical regression, which predicts a more universal quality metric involving the number of b- and y-ion peaks. The best of our binary classifiers can eliminate over 75% of the unidentifiable spectra while losing only 10% of the identifiable spectra. Statistical regression can pick out spectra of modified peptides that can be identified by a de novo program but not by SEQUEST. In a section of independent interest, we discuss intensity normalization of mass spectra.

Algorithms↗
PubMed2006

Properties of R(2) statistics for logistic regression.

Various R(2) statistics have been proposed for logistic regression to quantify the extent to which the binary response can be predicted by a given logistic regression model and covariates. We study the asymptotic properties of three popular variance-based R(2) statistics. We find that two variance-based R(2) statistics, the sum of squares and the squared Pearson correlation, have identical asymptotic distribution whereas the third one, Gini's concentration measure, has a different asymptotic behaviour and may overstate the predictivity of the model and covariates when the model is mis-specified. Our result not only provides a theoretical basis for the findings in previous empirical and numerical work, but also leads to asymptotic confidence intervals. Statistical variability can then be taken into account when assessing the predictive value of a logistic regression model.

Biometry↗