|
ผู้แต่ง |
Tu, Yu-Kang | ชื่อเรื่อง |
Statistical thinking in epidemiology / Yu-Kang Tu, MarkS. Gilthorpe | ISBN |
978-142-00-9991-1
| ISBN |
142-009-991-4
| พิมพ์ลักษณ์ |
Boca Raton, FL : CRC Press, c2012 | เลขเรียก |
EP9 Tu883S | ลักษณะทางกายภาพ |
xii, 219 p. : ill. ; 25 cm | หมายเหตุ |
Contents: Vector geometry of linear models for epidemiologists --Path diagrams and directed acyclic graphs -- Mathematicalcoupling and regression to the mean in the relationbetween change and initial value -- Analysis of change inpre-/post-test studies -- Collinearity andmulticollinearity -- Is reverse paradox a paradox? --Testing statistical interaction -- Finding growthtrajectories in lifecourse research -- Partial leastsquares regression for lifecourse research | หมายเหตุ |
Summary: ^"While biomedical researchers may be able to followinstructions in the manuals accompanying the statisticalsoftware packages, they do not always have sufficientknowledge to choose the appropriate statistical methodsand correctly interpret their results. StatisticalThinking in Epidemiology examines common methodologicaland statistical problems in the use of correlation andregression in medical and epidemiological research:mathematical coupling, regression to the mean,collinearity, the reversal paradox, and statisticalinteraction. Statistical Thinking in Epidemiology is aboutthinking statistically when looking at problems inepidemiology. The authors focus on several methods andlook at them in detail: specific examples in epidemiologyillustrate how different model specifications can implydifferent causal relationships amongst variables, andmodel interpretation is undertaken with appropriateconsideration of the context of implicit or explicitcausal relationships. This book is intended for appliedstatisticians and epidemiologists, but can also be veryuseful for clinical and applied health researchers whowant to have a better understanding of statisticalthinking. Throughout the book, statistical softwarepackages R and Stata are used for general statisticalmodeling, and Amos and Mplus are used for structuralequation modeling^"--Provided by publisher | หัวเรื่อง |
Epidemiology--Statistical methods | หัวเรื่อง |
Epidemiology--Mathematics | หัวเรื่อง |
Epidemiologic Methods | หัวเรื่อง |
Statistics as Topic | หัวเรื่อง |
Models, Statistical | ผู้แต่งร่วม |
Gilthorpe, Mark S |
|