40\n\n3.5.9 Plots with whiskers .40\n\n3.5.10 Curves .41\n\nV\n4 Statistical modelling\n\n4.1 Regression model .43\n\n4.2 General linear model .45\n\n4.3 Generalized linear model .47\n\n4.4 Searching for the .83\n\n5.4.7 Diagnosis of the final model .85\n\n5.5 Conclusion .88\n\n6 Systematic part\n\n6.1 Regression 108\n\n8.3 Weighted regression .116\n\n8.4 Multiple regression .120\n\nVI\n8.5 Two-way A NOVA 132\n regression .176\n\n10.5 One-way ANCODEV .183\n\n10.6 Ihree-way ANODEV (Contingency table) 190\n\n11
First edition x, 245 stran : ilustrace ; 24 cm
- Conspectus
- Biologické vědy
- NML Fields
- biologie
- statistika, zdravotnická statistika
- knihovnictví, informační věda a muzeologie
- NML Publication type
- kolektivní monografie
Permutation methods are commonly used to test the significance of regressors of interest in general linear models (GLMs) for functional (image) data sets, in particular for neuroimaging applications as they rely on mild assumptions. Permutation inference for GLMs typically consists of three parts: choosing a relevant test statistic, computing pointwise permutation tests, and applying a multiple testing correction. We propose new multiple testing methods as an alternative to the commonly used maximum value of test statistics across the image. The new methods improve power and robustness against inhomogeneity of the test statistic across its domain. The methods rely on sorting the permuted functional test statistics based on pointwise rank measures; still, they can be implemented even for large data. The performance of the methods is demonstrated through a designed simulation experiment and an example of brain imaging data. We developed the R package GET, which can be used for the computation of the proposed procedures.
- MeSH
- Humans MeSH
- Linear Models MeSH
- Brain * diagnostic imaging MeSH
- Neuroimaging * MeSH
- Computer Simulation MeSH
- Research Design MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
Wiley series in probability and statistics
1st ed. xxi, 325 s.
- Conspectus
- Statistika
- NML Fields
- statistika, zdravotnická statistika
Texts in statistical science
2nd ed. vii, 225 s.
- Conspectus
- Statistika
- NML Fields
- statistika, zdravotnická statistika
Decision support systems represent very complicated systems offering assistance with the decision making process. Learning the classification rule of a decision support system requires to solve complex statistical task, most commonly by means of classification analysis. However, the regression methodology may be useful in this context as well. This paper has the aim to overview various regression methods, discuss their properties and show examples within clinical decision making.
- MeSH
- Data Interpretation, Statistical MeSH
- Clinical Decision-Making methods MeSH
- Linear Models MeSH
- Logistic Models MeSH
- Least-Squares Analysis MeSH
- Neural Networks, Computer MeSH
- Regression Analysis * MeSH
- Models, Statistical * MeSH
- Statistics as Topic MeSH
- Support Vector Machine MeSH
- Decision Support Systems, Clinical MeSH
Commercially, cellulose products are designated with viscosity grade measured at 2% w/v concentration in water at 20 degrees C using an Ubbelohde viscometer. To represent viscosity/concentration curves, linear function of the eighth root of dynamic viscosity and the concentration is generally used. In this work, the influence on viscosity of aqueous solutions of methylcellulose 400 and hypromellose 4000 by temperature and polymer concentration was modelled using an empirically proposed multiple linear regression in which the transformation of viscosity by logarithm, the reciprocal value of the absolute temperature, and the concentration by square root was recommended. Due to this, the viscosity of both cellulose derivatives investigated could be predicted simultaneously with the mean difference between the observed data and the ones estimated equal to 16.2%. Expanding the linear regression with the linear interaction between logarithm of the polymer viscosity grade and square root of the polymer concentration, the precision of the viscosity prediction increased to the acceptable level of 4.1%. Other interactions between the studied variables did not provide significantly better results. The optimized regression equation enabled the prediction of kinematic, dynamic, relative, and specific viscosity of the aqueous solutions of cellulose derivatives. The dimensionless relative viscosity could be recommended because it takes into account the water viscosity at the same experimental temperature. Selecting viscosity grade of the cellulose derivative and temperature of measurement, the partial regression equations were obtained from which the relative viscosity could be determined as the function of the polymer concentration with the precision in range of 1.3-4.7%.
40\n\n3.5.9 Plots with whiskers .40\n\n3.5.10 Curves .41\n\nV\n4 Statistical modelling\n\n4.1 Regression model .43\n\n4.2 General linear model .45\n\n4.3 Generalized linear model .47\n\n4.4 Searching for the .83\n\n5.4.7 Diagnosis of the final model .85\n\n5.5 Conclusion .88\n\n6 Systematic part\n\n6.1 Regression 108\n\n8.3 Weighted regression .116\n\n8.4 Multiple regression .120\n\nVI\n8.5 Two-way A NOVA 132\n regression .176\n\n10.5 One-way ANCODEV .183\n\n10.6 Ihree-way ANODEV (Contingency table) 190\n\n11
1. elektronické vydání 1 online zdroj (256 stran)
Kniha je zaměřena na regresní modely, konkrétně jednorozměrné zobecněné lineární modely (GLM). Je určena především studentům a kolegům z biologických oborů a vyžaduje pouze základní statistické vzdělání, jakým je např. jednosemestrový kurz biostatistiky. Text knihy obsahuje nezbytné minimum statistické teorie, především však řešení 18 reálných příkladů z oblasti biologie. Každý příklad je rozpracován od popisu a stanovení cíle přes vývoj statistického modelu až po závěr. K analýze dat je použit populární a volně dostupný statistický software R. Příklady byly záměrně vybrány tak, aby upozornily na leckteré problémy a chyby, které se mohou v průběhu analýzy dat vyskytnout. Zároveň mají čtenáře motivovat k tomu, jak o statistických modelech přemýšlet a jak je používat. Řešení příkladů si může čtenář vyzkoušet sám na datech, jež jsou dodávána spolu s knihou.
OBJECTIVE: Alveolar concentration (C(A)NO) and bronchial flux (J(aw)NO) of nitric oxide (NO) characterize the contributions of peripheral and proximal airways to exhaled NO. Both parameters can be estimated using a two-compartment model if the fraction of NO in orally exhaled air (FE(NO)) is measured at multiple constant expiratory flow rates (V). The aim of this study was to evaluate how departures from linearity influence the estimates of C(A)NO and J(aw)NO obtained with the help of linear regression analysis of the relationships between FE(NO) and 1/V (method P), and between the NO output (V(NO) = FE(NO) × V) and V (method T). Furthermore, differences between patients with atopic asthma (AA) and allergic rhinitis (AR) and between methods P and T were assessed. DESIGN: Measurements of FE(NO) were performed with a chemiluminiscence analyzer at five levels of V ranging from 50 to 250 ml/sec in school children and adolescents with mild to moderate-severe AA treated by inhaled corticosteroids (N = 42) and AR (N = 20). RESULTS: Violation of the linearity condition at V ≤ 100 ml/sec caused shifts between methods with regard to the partition of exhaled NO into alveolar (C(A)NO: P > T) and bronchial (J(aw)NO: T > P) components. Both methods gave similar results in the linear range of 150-250 ml/sec: The mean ratios P/T and limits of agreement calculated in AA and AR patients were 1.03 (0.49-1.56) and 1.07 (0.55-1.59) for C(A)NO and 1.03 (0.73-1.33) and 0.99 (0.90-1.10) for J(aw)NO, respectively. No significant differences between AA and AR were found in C(A)NO and J(aw)NO calculated in the linear range by the T method {medians (inter-quartile ranges): 1.7 ppb (0.9-3.9) vs. 2.3 ppb (0.8-3.7), P = 0.91; 1,800 pl/sec (950-3,560) vs. 1,180 pl/sec (639-1,950), P = 0.061}. However, the flow-dependency of the estimates was markedly higher in AA than in AR patients: C(A) NO was decreased 2.8-fold vs. 1.5-fold and J(aw) NO was increased 1.5-fold vs. 1.2-fold in the linear range as compared to the range of 50-250 ml/sec. In both groups, the median standard errors (SE) of the J(aw) NO estimates were similar for the metods P and T and small (<15%) regardless of the range for expiratory flows. The precision of C(A) NO estimates was less in all ranges. For both methods, the SE of the estimates obtained in the range of 150-250 ml/sec exceeded 50% in asthmatics and 30% in AR patients, respectively. The results show that FE(NO) has to be measured at several expiratory flows ≥100 ml/sec for the accurate estimation of C(A) NO and J(aw) NO using linear methods P and T in children and adolescents with AA and AR. A stepwise procedure for detecting nonlinearity and evaluating the quality of FE(NO) measurements is suggested.
- MeSH
- Models, Biological * MeSH
- Asthma metabolism physiopathology MeSH
- Bronchi chemistry metabolism physiopathology MeSH
- Rhinitis, Allergic, Perennial metabolism physiopathology MeSH
- Breath Tests methods MeSH
- Child MeSH
- Humans MeSH
- Linear Models MeSH
- Adolescent MeSH
- Nitric Oxide analysis metabolism MeSH
- Pulmonary Alveoli chemistry metabolism physiopathology MeSH
- Respiratory Function Tests MeSH
- Severity of Illness Index MeSH
- Check Tag
- Child MeSH
- Humans MeSH
- Adolescent MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Evaluation Study MeSH
- Research Support, Non-U.S. Gov't MeSH
BACKGROUND: Impairment of cognition and speech are common in multiple sclerosis (MS) patients, but their relationship is not well understood. OBJECTIVE: To describe the relationship between articulation rate characteristics and processing speed and to investigate the potential role of objective speech analysis for the detection of cognitive decline in MS. METHODS: A total of 122 patients with clinically definite MS were included in this cross-sectional pilot study. Patients underwent three speaking tasks (oral diadochokinesis, reading text and monologue) and assessment of processing speed (Symbol Digit Modalities Test [SDMT], Paced Auditory Serial Addition Test-3 s [PASAT-3]). Association between articulation rate and cognition was analyzed using linear regression analysis. We estimated the area under the receiver operating characteristics curves (AUC) to evaluate the predictive accuracy of articulation rate measures for the detection of abnormal processing speed. RESULTS: We observed an association between articulation rate and cognitive measures (rho = 0.45-0.58; p < 0.001). Faster reading speed by one word per second was associated with an 18.7 point (95% confidence interval [CI] 14.9-22.5) increase of the SDMT score and 14.7 (95% CI 8.9-20.4) point increase of PASAT-3 score (both p < 0.001). AUC values of articulation rate characteristics for the identification of processing speed impairment ranged between 0.67 and 0.79. Using a cutoff of 3.10 in reading speed, we were able to identify impairment in both the SDMT and PASAT-3 with 91% sensitivity and 54% specificity. CONCLUSION: Slowed articulation rate is strongly associated with processing speed decline. Objective quantitative speech analysis identified patients with abnormal cognitive performance.
- MeSH
- Adult MeSH
- Dysarthria etiology MeSH
- Cognition Disorders diagnosis etiology MeSH
- Middle Aged MeSH
- Humans MeSH
- Pilot Projects MeSH
- Cross-Sectional Studies MeSH
- Regression Analysis MeSH
- ROC Curve MeSH
- Multiple Sclerosis complications MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH