Muutke küpsiste eelistusi

E-raamat: Analysis of Correlated Data with SAS and R

  • Formaat: 513 pages
  • Ilmumisaeg: 27-Apr-2018
  • Kirjastus: CRC Press
  • Keel: eng
  • ISBN-13: 9781315277714
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 59,79 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Analysis of Correlated Data with SAS and RSuurem pilt
  • Formaat: 513 pages
  • Ilmumisaeg: 27-Apr-2018
  • Kirjastus: CRC Press
  • Keel: eng
  • ISBN-13: 9781315277714
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Analysis of Correlated Data with SAS and R: 4th edition presents an applied treatment of recently developed statistical models and methods for the analysis of hierarchical binary, count and continuous response data. It explains how to use procedures in SAS and packages in R for exploring data, fitting appropriate models, presenting programming codes and results.The book is designed for senior undergraduate and graduate students in the health sciences, epidemiology, statistics, and biostatistics as well as clinical researchers, and consulting statisticians who can apply the methods with their own data analyses. In each chapter a brief description of the foundations of statistical theory needed to understand the methods is given, thereafter the author illustrates the applicability of the techniques by providing sufficient number of examples. The last three chapters of the 4th edition contain introductory material on propensity score analysis, meta-analysis and the treatment of missing data using SAS and R. These topics were not covered in previous editions. The main reason is that there is an increasing demand by clinical researchers to have these topics covered at a reasonably understandable level of complexity. Mohamed Shoukri is principal scientist and professor of biostatistics at The National Biotechnology Center, King Faisal Specialist Hospital and Research Center and Al-Faisal University, Saudi Arabia. Professor Shoukri’s research includes analytic epidemiology, analysis of hierarchical data, and clinical biostatistics. He is an associate editor of the 3Biotech journal, a Fellow of the Royal Statistical Society and an elected member of the International Statistical Institute.
Preface xv
1 Study Designs and Measures of Effect Size 1(18)
1.1 Study Designs
1(10)
1.1.1 Introduction
1(1)
1.1.2 Nonexperimental or Observational Studies
2(1)
1.1.3 Types of Nonexperimental Designs
2(5)
1.1.3.1 Descriptive/Exploratory Survey Studies
2(1)
1.1.3.2 Correlational Studies (Ecological Studies)
2(1)
1.1.3.3 Cross-Sectional Studies
3(1)
1.1.3.4 Longitudinal Studies
3(1)
1.1.3.5 Prospective or Cohort Studies
3(1)
1.1.3.6 Case-Control Studies
4(1)
1.1.3.7 Nested Case-Control Study
5(1)
1.1.3.8 Case-Crossover Study
6(1)
1.1.4 Quasi-Experimental Designs
7(1)
1.1.5 Single-Subject Design (SSD)
7(1)
1.1.6 Quality of Designs
8(1)
1.1.7 Confounding
8(1)
1.1.8 Sampling
9(1)
1.1.9 Types of Sampling Strategies
9(1)
1.1.10 Summary
10(1)
1.2 Effect Size
11(6)
1.2.1 What Is Effect Size?
11(1)
1.2.2 Why Report Effect Sizes?
11(2)
1.2.3 Measures of Effect Size
13(1)
1.2.4 What Is Meant by "Small," "Medium," and "Large "?
13(2)
1.2.5 Summary
15(1)
1.2.6 American Statistical Association (ASA) Statement about the p-value
15(2)
Exercises
17(2)
2 Comparing Group Means When the Standard Assumptions Are Violated 19(24)
2.1 Introduction
19(1)
2.2 Nonnormality
20(3)
2.3 Heterogeneity of Variances
23(4)
2.3.1 Bartlett's Test
24(3)
2.3.2 Levene's Test (1960)
27(1)
2.4 Testing Equality of Group Means
27(5)
2.4.1 Welch's Statistic (1951)
27(1)
2.4.2 Brown and Forsythe Statistic (1974b) for Testing Equality of Group Means
28(1)
2.4.3 Cochran's (1937) Method of Weighing for Testing Equality of Group Means
29(3)
2.5 Nonindependence
32(3)
2.6 Nonparametric Tests
35(8)
2.6.1 Nonparametric Analysis of Milk Data Using SAS
36(7)
3 Analyzing Clustered Data 43(36)
3.1 Introduction
43(1)
3.2 The Basic Feature of Cluster Data
44(4)
3.3 Effect of One Measured Covariate on Estimation of the Intracluster Correlation
48(4)
3.4 Sampling and Design Issues
52(4)
3.4.1 Comparison of Means
52(4)
3.5 Regression Analysis for Clustered Data
56(8)
3.6 Generalized Linear Models
60(1)
3.6.1 Marginal Models (Population Average Models)
61(1)
3.6.2 Random Effects Models
61(1)
3.6.3 Generalized Estimating Equation (GEE)
62(2)
3.7 Fitting Alternative Models for Clustered Data
64(8)
3.7.1 Proc Mixed for Clustered Data
66(1)
3.7.2 Model 1: Unconditional Means Model
66(1)
3.7.3 Model 2: Including a Family Level Covariate
67(2)
3.7.4 Model 3: Including the Sib-Level Covariate
69(1)
3.7.5 Model 4: Including One Family Level Covariate and Two Subject Level Covariates
70(2)
Appendix
72(2)
Exercises
74(5)
4 Statistical Analysis of Cross-Classified Data 79(62)
4.1 Introduction
79(1)
4.2 Measures of Association in 2 x 2 Tables
80(4)
4.2.1 Absolute Risk
80(1)
4.2.2 Risk Difference
81(1)
4.2.3 Attributable Risk
81(1)
4.2.4 Relative Risk
81(1)
4.2.5 Odds Ratio
81(1)
4.2.6 Relationship between Odds Ratio and Relative Risk
82(1)
4.2.7 Incidence Rate and Incidence Rate Ratio As a Measure of Effect Size
82(1)
4.2.8 What Is Person-Time?
82(2)
4.3 Statistical Analysis from the 2 x 2 Classification Data
84(4)
4.3.1 Cross-Sectional Sampling
84(3)
4.3.2 Cohort and Case-Control Studies
87(1)
4.4 Statistical Inference on Odds Ratio
88(6)
4.4.1 Significance Tests
90(4)
4.4.2 Interval Estimation
94(1)
4.5 Analysis of Several 2 x 2 Contingency Tables
94(9)
4.5.1 Test of Homogeneity
97(1)
4.5.2 Significance Test of Common Odds Ratio
98(4)
4.5.3 Confidence Interval on the Common Odds Ratio
102(1)
4.6 Analysis of Matched Pairs (One Case and One Control)
103(5)
4.6.1 Estimating the Odds Ratio
104(2)
4.6.2 Testing the Equality of Marginal Distributions
106(2)
4.7 Statistical Analysis of Clustered Binary Data
108(13)
4.7.1 Approaches to Adjust the Pearson's CM-Square
110(1)
4.7.2 Donner and Donald Adjustment
110(1)
4.7.3 Procedures Based on Ratio Estimate Theory
110(1)
4.7.4 Confidence Interval Construction
111(3)
4.7.5 Adjusted CM-Square for Studies Involving More than Two Groups
114(7)
4.8 Inference on the Common Odds Ratio
121(9)
4.8.1 Donald and Donner's Adjustment
121(2)
4.8.2 Rao and Scott's Adjustment
123(7)
4.9 Calculations of Relative and Attributable Risks from Clustered Binary Data
130(1)
4.10 Sample Size Requirements for Clustered Binary Data
131(2)
4.10.1 Paired-Sample Design
131(1)
4.10.2 Comparative Studies for Cluster Sizes Greater or Equal to Two
132(1)
4.11 Discussion
133(1)
Exercises
134(7)
5 Modeling Binary Outcome Data 141(56)
5.1 Introduction
141(2)
5.2 The Logistic Regression Model
143(3)
5.3 Coding Categorical Explanatory Variables and Interpretation of Coefficients
146(4)
5.4 Interaction and Confounding in Logistic Regression
150(5)
5.5 The Goodness of Fit and Model Comparisons
155(8)
5.5.1 The Pearson's Chi2 Statistic
155(1)
5.5.2 The Likelihood Ratio Criterion (Deviance)
155(8)
5.6 Modeling Correlated Binary Outcome Data
163(14)
5.6.1 Introduction
163(1)
5.6.2 Population Average Models: The Generalized Estimating Equation (GEE) Approach
164(2)
5.6.3 Cluster-Specific Models (Random-Effects Models)
166(2)
5.6.4 Interpretation of Regression Parameters
168(6)
5.6.5 Multiple Levels of Clustering
174(3)
5.7 Logistic Regression for Case-Control Studies
177(11)
5.7.1 Cohort versus Case-Control Models
177(3)
5.7.2 Matched Analysis
180(1)
5.7.3 Fitting Matched Case-Control Study Data in SAS and R
181(7)
5.7.4 Some Cautionary Remarks on the Matched Case-Control Designs
188(1)
5.8 Sample Size Calculations for Logistic Regression
188(2)
5.9 Sample Size for Matched Case Control Studies
190(1)
Exercises
191(6)
6 Analysis of Clustered Count Data 197(32)
6.1 Introduction
197(1)
6.2 Poisson Regression
197(18)
6.2.1 Model Inference and Goodness of Fit
202(1)
6.2.2 Overdispersion in Count Data
203(1)
6.2.3 Count Data Random Effects Models
204(3)
6.2.4 Introducing the Generalized Linear Mixed Model (GLMM)
207(1)
6.2.5 Fitting GLMM Using SAS GLIMMIX
208(7)
6.3 Other Models: Poisson Inverse Gaussian and Zero Inflated Poisson with Random Effects
215(12)
Exercises
227(2)
7 Repeated Measures and Longitudinal Data Analysis 229(50)
7.1 Introduction
229(1)
7.2 Examples
230(2)
7.2.1 Experimental Studies
230(1)
7.2.1.1 Liver Enzyme Activity
230(1)
7.2.1.2 Effect of Mycobacterium Inoculation on Weight
230(1)
7.2.2 Observational Studies
230(5)
7.2.2.1 Variations in Teenage Pregnancy Rates in Canada
230(2)
7.2.2.2 Number of Tuberculosis Cases in Saudi Arabia
232(1)
7.3 Methods for the Analysis of Repeated Measures Data
232(1)
7.4 Basic Models
233(2)
7.5 The Issue of Missing Observations
235(1)
7.6 Mixed Linear Regression Models
235(4)
7.6.1 Formulation of the Models
235(1)
7.6.2 Covariance Patterns
236(2)
7.6.3 Statistical Inference and Model Comparison
238(1)
7.6.4 Estimation of Model Parameters
238(1)
7.7 Examples Using the SAS Mixed and GLIMMIX Procedures
239(26)
7.7.1 Linear Mixed Model for Normally Distributed Repeated Measures Data
239(12)
7.7.2 Analysis of Longitudinal Binary and Count Data
251(14)
7.8 Two More Examples for Longitudinal Count Data: Fixed Effect Modeling Strategy
265(5)
7.9 The Problem of Multiple Comparisons in Repeated Measures Experiments
270(3)
7.10 Sample Size Requirements in the Analysis of Repeated Measures
273(2)
Exercises
275(4)
8 Introduction to Time Series Analysis 279(56)
8.1 Introduction
279(2)
8.2 Simple Descriptive Methods
281(19)
8.2.1 Multiplicative Seasonal Variation Model
283(6)
8.2.2 Additive Seasonal Variation Model
289(3)
8.2.3 Detection of Seasonality: Nonparametric Test
292(4)
8.2.4 Autoregressive Errors: Detection and Estimation
296(2)
8.2.5 Modeling Seasonality and Trend Using Polynomial and Trigonometric Functions
298(2)
8.3 Fundamental Concepts in the Analysis of Time Series
300(4)
8.3.1 Stochastic Processes
300(1)
8.3.2 Stationary Series
301(1)
8.3.3 Autocovariance and Autocorrelation Functions
302(2)
8.4 Models for Stationary Time Series
304(12)
8.4.1 Autoregressive Processes
304(1)
8.4.2 The AR(1) Model
304(1)
8.4.3 AR(2) Model (Yule's Process)
305(3)
8.4.4 Moving Average Processes
308(1)
8.4.5 First-Order Moving Average Process MA(1)
308(1)
8.4.6 Second-Order Moving Average Process MA(2)
309(1)
8.4.7 Mixed Autoregressive Moving Average Processes
310(2)
8.4.8 ARIMA Models
312(4)
8.5 Forecasting
316(5)
8.5.1 AR(1) Model
316(2)
8.5.2 AR(2) Model
318(1)
8.5.3 MA(1) Model
319(2)
8.6 Forecasting with Exponential Smoothing Models
321(4)
8.7 Modeling Seasonality with ARIMA: Condemnation Rates Series Revisited
325(4)
8.8 Interrupted Time Series (Quasi-Experiments)
329(3)
8.9 Stationary versus Nonstationary Series
332(1)
Exercises
333(2)
9 Analysis of Survival Data 335(48)
9.1 Introduction
335(1)
9.2 Fundamental Concept in Survival Analysis
336(3)
9.3 Examples
339(2)
9.3.1 Cystic Ovary Data
339(1)
9.3.2 Breast Cancer Data
339(1)
9.3.3 Ventilating Tube Data
339(1)
9.3.4 Age at Culling of Dairy Cows
340(1)
9.3.5 Model for End-Stage Liver Disease and Its Effect on Survival of Liver Transplanted Patients
340(1)
9.4 Estimating Survival Probabilities
341(1)
9.5 Nonparametric Methods
341(4)
9.5.1 Methods for Noncensored Data
341(1)
9.5.2 Methods for Censored Data
342(3)
9.6 Nonparametric Techniques for Group Comparisons
345(6)
9.6.1 The Log-Rank Test
345(4)
9.6.2 Log-Rank Test for More Than Two Groups
349(2)
9.7 Parametric Methods
351(2)
9.7.1 Exponential Model
351(1)
9.7.2 Weibull Model
351(2)
9.8 Semiparametric Models
353(4)
9.8.1 Cox Proportional Hazards Model
353(2)
9.8.2 Estimation of Regression Parameters
355(1)
9.8.3 Treatment of Ties in the Proportional Hazards Model
356(1)
9.9 Survival Analysis of Competing Risk
357(8)
9.9.1 Cause-Specific Hazard
360(1)
9.9.2 Subdistribution Hazard
361(4)
9.10 Time-Dependent Variables
365(3)
9.10.1 Types of Time-Dependent Variables
365(1)
9.10.2 Model with Time-Dependent Variables
366(2)
9.11 Joint Modeling of Longitudinal and Time to Event Data
368(1)
9.12 Submodel Specification
369(3)
9.12.1 The Survival Submodel
369(2)
9.12.2 Estimation: JM Package
371(1)
9.13 Modeling Clustered Survival Data
372(6)
9.13.1 Marginal Models (GJE Approach)
373(1)
9.13.2 Random Effects Models (Frailty Models)
373(5)
9.13.2.1 Weibull Model with Gamma Frailty
375(3)
9.14 Sample Size Requirements for Survival Data
378(3)
9.14.1 Sample Size Based on Log-Rank Test
379(1)
9.14.2 Exponential Survival and Accrual
379(1)
9.14.3 Sample Size Requirements for Clustered Survival
380(1)
Exercises
381(2)
10 Introduction to Propensity Score Analysis 383(26)
10.1 Introduction
383(1)
10.2 Confounding
383(4)
10.2.1 Definition of Confounding
383(1)
10.2.2 Identification of Confounding
384(1)
10.2.3 Control of Confounding in Study Design
385(2)
10.2.3.1 Restriction
385(1)
10.2.3.2 Matching
386(1)
10.3 Propensity Score Methods
387(1)
10.3.1 Propensity Scores
387(1)
10.3.2 Propensity Score Estimation and Covariate Balance
387(1)
10.4 Methods for Propensity Score Estimation
388(2)
10.5 Propensity Score Estimation When Units of Analysis Are Clusters
390(1)
10.6 The Controversy Surrounding Propensity Score
391(1)
10.7 Examples
392(8)
10.8 Propensity Score Matching in R
400(5)
10.9 Propensity Score Stratification in R
405(2)
Exercises
407(2)
11 Introductory Meta-Analysis 409(30)
11.1 Introduction
409(1)
11.2 Definition and Goals of Meta-Analysis
410(1)
11.3 How Is a Meta-Analysis Done?
410(3)
11.3.1 Decide on a Research Topic and the Hypothesis to be Tested
411(1)
11.3.2 Inclusion Criteria
411(1)
11.3.3 Searching Strategy and Data Extraction
411(1)
11.3.4 Study Evaluation
412(1)
11.3.5 Establish Database
413(1)
11.3.6 Performing the Analysis
413(1)
11.4 Issues in Meta-Analysis
413(3)
11.4.1 Design Issues
413(1)
11.4.2 Positive Studies Are More Likely to be Published (Publication Bias)
413(1)
11.4.3 Funnel Plot
414(1)
11.4.4 Studies May Be Heterogeneous
415(1)
11.4.5 Confounding
415(1)
11.4.6 Modeling
416(1)
11.4.7 Evaluating the Results
416(1)
11.5 Assessing Heterogeneity in Meta-Analysis
416(3)
11.5.1 Sources of Heterogeneity
416(1)
11.5.2 Measuring Heterogeneity
417(1)
11.5.3 Measures of Heterogeneity
417(2)
11.6 Statistical Methods
419(2)
11.6.1 Fixed Effect Approach
419(1)
11.6.2 Binary Data
420(1)
11.7 Random Effect Model
421(1)
11.8 Examples
422(6)
11.9 Meta-Analysis of Diagnostic Accuracy
428(10)
Exercises
438(1)
12 Missing Data 439(42)
12.1 Introduction
439(1)
12.2 Patterns of Missing Data
440(1)
12.3 Mechanisms of Missing Data
440(4)
12.3.1 Data Missing Completely at Random (MCAR)
440(2)
12.3.1.1 Remarks on MCAR
441(1)
12.3.2 Missing at Random (MAR)
442(1)
12.3.3 Nonignorable, or Missing Not at Random (MNAR)
443(1)
12.4 Methods of Handling Missing Data
444(4)
12.4.1 Listwise or Casewise Data Deletion
445(1)
12.4.2 Pairwise Data Deletion
445(1)
12.4.3 Mean Substitution
445(1)
12.4.4 Regression Methods
445(1)
12.4.5 Maximum Likelihood Methods
445(1)
12.4.6 Multiple Imputation (MI)
445(1)
12.4.7 Expectation Maximization (EM)
446(2)
12.5 Pattern-Mixture Models for Nonignorable Missing Data
448(1)
12.6 Strategies to Cope with Incomplete Data
449(1)
12.7 Missing Data in SAS
449(1)
12.8 Missing Data in R: MICE
450(1)
12.9 Examples
450(15)
References
465(16)
Index 481
Mohamed Shoukri is principal scientist and professor of biostatistics at The National Biotechnology Center, King Faisal Specialist Hospital and Research Center and Al-Faisal University, Saudi Arabia. Professor Shoukris research includes analytic epidemiology, analysis of hierarchical data, and clinical biostatistics. He is an associate editor of the 3Biotech journal, a Fellow of the Royal Statistical Society and an elected member of the International Statistical Institute.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97813152777146e.html
Märksõnad: