Epidemiologic Analysis: A Case-Oriented Approach 2003

定價 $ 950

售價 $ 600

數量:

Epidemiologic Analysis: A Case-Oriented Approach 2003-需求單

內容簡介

Using real data from published sources, this engaging and lucid casebook shows how statistical tools can be used to analyze important epidemiologic issues. Its 18 cases address a variety of interesting research problems from Mendel's classic sweet pea experiments to recent studies of AIDS and exposure to electro-magnetic field radiation. Each includes a data set. The cases are described succinctly and the methods used to analyze them are then discussed in detail. A wide range of statistical and graphical tools are included, from simple mean values to nonparametric bivariate regression smoothing techniques. The level of discussion is sophisticated but mathematically simple, affording access to a broad audience interested in using collected data to study human health and disease. The author's focus on describing, interpreting and presenting results will set this book apart from other texts.

作者簡介

Steve Selvin, Professor of Biostatistics and Epidemiology, University of California, Berkeley.

1. Measurement of Trend (a 2 by c Table)

　Topic: Trends in Multiple Birth Defects

　Methods: Chi-Square and Regression Techniques (Linear and Logistic)

　Data Type: Surveillance

2. Odds Ratio and Relative Risk

　Part I: Odds Ratio

　Topic: Smoking and the Risk of Low Birth Weight

　Methods: 2 by 2 by k Tables, Odds Ratios, Summary Odds Ratios and Logistic Regression

　Part II: Relative Risk

　Topic: Behavior Type and the Risk of Coronary Disease

　Methods: 2 by 2 by k: Tables, Relative Risk, Summary Relative Risk and Poisson Regression

3. Randomized Trial

　Topic: Alzheimer's Disease Clinical Trial

　Methods: t-Tests, Wilcoxon Tests, Bootstrap Estimation and Permutation Tests

　Data Type: Randomized Trial

4. Bias

　Part I: Regression to the Mean

　Topic: Bias in Repeated Blood Pressure Measurements

　Methods: t-Test, Simple Linear Regression and Correlation

　Part II: Misclassification

　Topic: Bias from Misclassified Treatment/Control Status

　Methods: Odds Ratios, Bootstrap Estimation and Confidence Intervals

5. Goodness-of-Fit

　Topic: Mendel's Ornamental Flower Data

　Methods: Pearson's Chi-Square Goodness-of-Fit Tests

　Data Type: Experimental

6. Analysis of a Two-Way Table

　Topic: Marital Status and the Risk of Rectal Cancer

　Methods: r by c Table, Median Polish and Poisson Regression Models

　Data Type: Survey/Incidence (Surveillance Data)

7. Cluster Analysis

　Topic: Classification by Race/Ethnicity Based on Gene Frequencies

　Methods: Graphic Cluster Analysis, Principal Components Analysis with Contour Plots

　Data Type: Aggregate or Ecologic

8. Matched Analysis (One Case and Two Controls)

　Topic: Electro-Magnetic Field Radiation and the Risk of a Birth Defect

　Methods: t-Tests, Analysis of Variance, Matched Analysis, and Conditional Logistic Models

　Data Type: Matched Sets (Population-Based Vial Records)

9. Multivariable Linear Regression

　Topic: Weight Gained During Pregnancy and Birth Weight

　Methods: Multivariable Linear Regression Models

　Data Type: Cross-Sectional (Hospital Database)

10. Linear Logistic Regression

　Topic: Noise Exposure and the Risk of Hypertension

　Methods: Linear and Polynomial Logistic Regression and General Additive Models

　Data Type: Cross-Sectional (Industrial Hygiene Measurements)

11. Poisson Regression

　Part I: Standardized Mortality Ratio

　Topic: Gender and the Risk of Stomach Cancer

　Methods: Age Adjustment (Model Free), SMR and Poisson Regression Models

　Part II: Adjusted Rates

　Topic: Race, Birth Weight and Perinatal Mortality

　Methods: Polynomial Regression Models

12. Log-Linear Model (Poisson Model Applied to Tabular Data)

　Topic: Vitamin Use and the Risk of Neural Tube Defects

　Methods: Log-Linear Models (Poisson Regression Models)

　Data Type: Case/Control (Medical Records)

13. Survival Analysis (Cox's Proportional Hazards Model)

　Topic: Prognostic Factors in the Development of AIDS

　Methods: Kaplan-Meier Plots, Parametric Survival Curves and Proportional Hazards Models

　Data Type: Prospective (Follow-Up Survival Data)

14. Multivariate Comparison of Two Groups

　Topic: Maternal Weight Change Over Two Pregnancies

　Methods: Canonical Correlation Analysis, Multivariate t-Tests and Analysis of Variance

　Data Type: Longitudinal (Hospital Database)

15. Smoothing Sequential Data

　Topic: Trends in Hodgkins Disease Among African-Americans

　Methods: Smoothing of Incidence and Mortality Data

　Data Type: Time-Series (Registry Records)

16. Nonparametric Regression Analysis

　Topic: Maternal Weight, Height and Birth Weight

　Methods: Nonparametric Estimation and Regression Techniques

　Data Type: Cross-sectional (Hospital Records)

References

Appendix

　a.1 Introduction

　a.2 Variances of Sums

　a.3 Binomial Probability Distribution

　a.4 Hypergeometric Probability Distribution

　a.5 Chi-Square Distribution: A Pattern

　a.6 Mantel-Haenszel Summary Odds Ratio

　a.7 Mantel-Haenszel-Cochran Test for Independence

　a.8 Taylor Series Expansion—Power Series

　a.9 Two Variances

　a.10 Rate Ratio

　a.11 Odds Ratio

　a.12 Weighted Average

　a.13 Additive Model for a Two-Way Classification

　a.14 Two by c table

　a.15 Kaplan-Meier Estimated Survival Probabilities

　a.16 Mean and Median Survival Time

　a.17 Two Properties of the Multivariable Logistic Model

Index

ISBN-13碼 : 9780195144895

ISBN-10碼 : 0195144899

出版日期 : 2001

書系代碼 : 18043

作者 : Steve Selvin

開數 : 菊16開

頁數 : 344

裝訂 : 平裝

印刷 : 黑白

定價 : NT$950.00