PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 12773666

Correlation and simple linear regression.

Kelly H Zou·Kemal Tuncali·Stuart G Silverman
View original source ↗Export metadata ↓

Abstract

In this tutorial article, the concepts of correlation and regression are reviewed and demonstrated. The authors review and compare two correlation coefficients, the Pearson correlation coefficient and the Spearman rho, for measuring linear and nonlinear relationships between two continuous variables. In the case of measuring the linear relationship between a predictor and an outcome variable, simple linear regression analysis is conducted. These statistical concepts are illustrated by using a data set from published literature to assess a computed tomography-guided interventional technique. These statistical methods are important for exploring the relationships between variables and can be applied to many radiologic studies.

Explore related subjects

Factor Analysis, StatisticalFluoroscopyHumansLinear ModelsRadiation DosageRadiology, InterventionalStatistics, NonparametricTomography, X-Ray ComputedJournal ArticleReview

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Kelly H Zou, Kemal Tuncali, Stuart G Silverman. 2003. Correlation and simple linear regression.. https://doi.org/10.1148/radiol.2273011499

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2003

International versions of the Menopause Rating Scale (MRS).

BACKGROUND: Symptom scales for aging women have clinically been used for years and the interest in measuring health-related quality of life (HRQoL) has increased in recent years. The Menopause Rating Scale (MRS) is a formally validated scale according to the requirements for quality of life instruments. The aim of this paper is to review the current state of the instrument particularly concerning versions of the scale in different languages. MRS VERSIONS AVAILABLE: The translations were performed following international methodological recommendations for the linguistic & cultural adaptation of HRQoL instruments. The first translation was done from the German original scale into English (UK & USA). The English version was used as the source language for the translations into French, Spanish, Swedish, Mexican/Argentine, Brazilian, Turkish, and Indonesian languages (attached as additional PDF files). CONCLUSION: The MRS scale is obviously a valuable tool for assessing health related quality of life of women in the menopausal transition and is used worldwide. The currently available 9 language versions have been translated following international standards for the linguistic and cultural translation of quality of life scales. Assistance is offered to help interested parties in the translation process.

Factor Analysis, Statistical↗
PubMed2003

[Lymphoma prognostic correlated factors analysis of 88 cases].

OBJECTIVE: To analyze the characters of incidence, pathological and immunological phenotype of malignant lymphoma(ML), and to study the significance of IgH and TCR T cell receptor gene rearrangement for NHL typing. METHODS: Immunological phenotyping was conducted by SABC, and IgH (FR2A, FR3A) & TCR (beta,gamma) gene rearrangement detected by PCR of some pathological wax and bone marrow samples. RESULTS: (1) In ML, the percentage of non-Hodgkin lymphoma, (NHL) was 88.6% and Hodgkin lymphoma (HL) was 11.4%. The incidence increased with the patient's age. The percentage of patients over 60 years was 38.6%, and the median survival time of those older than 60 years was significantly shorter than that of the younger. (2) The percentage of B-NHL was 68.6%, and that of T-NHL was 28.6%; 3 years' survival time rate of B-NHL was higher than that of T-NHL. (3) The percentage of low grade NHL was 42%, and that of middle and high grade NHL was 58%; and the overall survival time was not significantly different between the two groups. But the overall survival time was longer in patients in stages I-II than in stages III-IV. (4) The results of detection on wax and bone marrow samples showed that B-NHL FR2A were 66.7% and 56.2% positive, FR3A 90.4% and 81.2% positive; in T-NHL patients, TCR-beta and TCR-gamma gene rearrangements were 91.7% and 75.0% positive; T and B classification were the same as the immunological phenotype. CONCLUSION: Age, T and B classifications and staging are the important factors, which affect the prognosis of NHL. Molecular biological methods can help T/B classification when we couldn't get it by phenotyping.

Factor Analysis, Statistical↗
PubMed2003

Investigation of soil multi-element composition in Antalya, Turkey.

The chemical composition of 73 surface soil samples collected at the city of Antalya were analyzed for major, minor and trace elements to assess distribution of soil pollution, due to deposition of pollution-derived particles from the atmosphere. Comparison with data from rural area and distribution maps demonstrated that the composition of soil by metals is not significantly modified by anthropogenic activities in most of the city and its surroundings. In these areas, observed concentrations can be largely accounted for by occurrence of elements in aluminasilicate matrix of soil. However, soil composition is altered substantially close to major industries and at the settlement districts. In such limited areas, concentrations of anthropogenic elements such as Cd, Pb, Zn, Cu and Cr are factors of 20-50 higher than their concentrations in unperturbed soil. Factor analysis revealed three groups of elements that differ in their distributions. One of these components is unperturbed soil component, which is distributed uniformly in the study area; the second one is polluted soil, which is mostly confined to settlement areas and around industries; and the third is a mixed marine and motor vehicle impacted soil component, which occurred at the coastal parts of the city.

Factor Analysis, Statistical↗