Muutke küpsiste eelistusi

E-raamat: Handbook for Applied Modeling: Non-Gaussian and Correlated Data

5.00/5 (2 hinnangut Goodreads-ist)
(Northwestern University, Illinois), (University of Northern Colorado)
  • Formaat: EPUB+DRM
  • Ilmumisaeg: 14-Jul-2017
  • Kirjastus: Cambridge University Press
  • Keel: eng
  • ISBN-13: 9781108206914
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 45,68 €*
  • * 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.
Handbook for Applied Modeling: Non-Gaussian and Correlated DataSuurem pilt
  • Formaat: EPUB+DRM
  • Ilmumisaeg: 14-Jul-2017
  • Kirjastus: Cambridge University Press
  • Keel: eng
  • ISBN-13: 9781108206914
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. 

Designed for the applied practitioner, this book is a compact, entry-level guide to modeling and analyzing non-Gaussian and correlated data. Many practitioners work with data that fail the assumptions of the common linear regression models, necessitating more advanced modeling techniques. This Handbook presents clearly explained modeling options for such situations, along with extensive example data analyses. The book explains core models such as logistic regression, count regression, longitudinal regression, survival analysis, and structural equation modelling without relying on mathematical derivations. All data analyses are performed on real and publicly available data sets, which are revisited multiple times to show differing results using various modeling options. Common pitfalls, data issues, and interpretation of model results are also addressed. Programs in both R and SAS are made available for all results presented in the text so that readers can emulate and adapt analyses for their own data analysis needs. Data, R, and SAS scripts can be found online at http://www.spesi.org.

Arvustused

'This book is a guide to modeling and analyzing non-Gaussian and correlated data. There is clearly a need for such a book to help less experienced data scientists The data sets and models are well explained, and the limitations of each type of model on the various data sets is illustrated by frequent plots.' Peter Rabinovitch, MAA Reviews

Muu info

This compact, entry-level Handbook equips applied practitioners to choose and use core models for real-world data - with R and SAS.
Preface xiii
1 The Data Sets
1(24)
1.1 Introduction
1(2)
1.1.1 The School Survey on Crime and Safety
2(1)
1.1.2 The Framingham Heart Study
2(1)
1.1.3 Fire-Climate Interactions in the American West
2(1)
1.1.4 English Wikipedia Clickstream Data
3(1)
1.2 Exploratory Data Analysis
3(1)
1.3 Gauss-Markov Assumptions
4(1)
1.4 Data Summaries and Tables
4(1)
1.5 Graphical Representations
4(3)
1.5.1 Histograms
5(1)
1.5.2 Q-Q Plots
5(1)
1.5.3 Box-Whisker Plots
5(1)
1.5.4 Scatter Plots
6(1)
1.6 Pairwise Correlation
7(1)
1.7 Machine Learning Pattern Recognition
7(1)
1.8 Exploring the Data Sets
8(15)
1.8.1 School Survey on Crime and Safety Data
8(5)
1.8.2 Framingham Heart Study Data
13(4)
1.8.3 Fire-Climate Interactions in the American West Data
17(3)
1.8.4 English Wikipedia Clickstream Data
20(3)
1.9 Summary
23(1)
1.10 Further Reading
24(1)
2 The Model-Building Process
25(25)
2.1 Introduction
25(1)
2.2 The Model-Building Process
26(4)
2.2.1 Exploratory Data Analysis
26(1)
2.2.2 Model Construction
27(1)
2.2.3 Model Fit Diagnostics
28(1)
2.2.4 Model Effects Analysis
28(1)
2.2.5 Model Interpretation and Prediction
29(1)
2.2.6 Effects and Predictive Model Differences
29(1)
2.3 Constant Variance Response Models
30(1)
2.4 Nonconstant Variance Response Models
31(1)
2.5 Discrete, Categorical Response Models
32(2)
2.6 Count Response Models
34(3)
2.7 Time-to-Event Response Models
37(2)
2.8 Longitudinal Response Models
39(2)
2.9 Structural Equation Modeling
41(2)
2.10 Effect Size
43(1)
2.11 Model Fit Measures
43(5)
2.11.1 Measures of Fit
43(2)
2.11.2 Residual Analyses
45(3)
2.12 Summary
48(1)
2.13 Further Reading
49(1)
3 Constant Variance Response Models
50(7)
3.1 Introduction
50(1)
3.2 School Survey on Crime and Safety
50(2)
3.3 Framingham Heart Study
52(1)
3.4 Fire-Climate Interactions in the American West
53(2)
3.5 English Wikipedia Clickstream Data
55(1)
3.6 Summary
56(1)
3.7 Further Reading
56(1)
4 Nonconstant Variance Response Models
57(19)
4.1 Heterogeneity in Response Variance
57(1)
4.2 Detecting Heteroscedasticity
58(1)
4.2.1 Descriptive Statistics
58(1)
4.2.2 Tests for Grouped Data
58(1)
4.2.3 Tests for Continuous Predictors
59(1)
4.3 Variance-Stabilizing Transformations
59(1)
4.3.1 Selecting the Transformation
59(1)
4.3.2 Model Diagnostics
59(1)
4.4 Weighted Least Squares
60(1)
4.4.1 WLS Estimation
60(1)
4.4.2 Selecting the Weights
60(1)
4.5 SSOCS Analysis: Annual Suspensions
61(9)
4.5.1 Exploratory Data Analysis
61(2)
4.5.2 Normal Linear Model
63(1)
4.5.3 Outcome Transformations
63(2)
4.5.4 Weighted Least Squares
65(3)
4.5.5 Parameter Interpretations
68(1)
4.5.6 Model Prediction
69(1)
4.6 Fire-Climate Analysis: Decade Averages
70(5)
4.6.1 Exploratory Data Analysis
70(1)
4.6.2 Normal Linear Model
71(1)
4.6.3 Weighted Least Squares
72(2)
4.6.4 Parameter Interpretations
74(1)
4.6.5 Model Prediction
74(1)
4.7 Summary
75(1)
4.8 Further Reading
75(1)
5 Discrete, Categorical Response Models
76(32)
5.1 Categorical Responses
76(1)
5.2 Binary Logistic Regression
76(5)
5.2.1 Descriptive Statistics for Binary Outcomes
77(1)
5.2.2 The Logistic Regression Model
78(1)
5.2.3 Interpreting Model Coefficients
78(1)
5.2.4 Model Fit
79(2)
5.3 Nominal Multinomial Models
81(1)
5.4 Ordinal Multinomial Models
82(3)
5.4.1 Cumulative Logit Model
83(1)
5.4.2 Adjacent Categories Model
83(1)
5.4.3 Continuation Ratio Model
84(1)
5.5 FHS Analysis: Probability of Hypertension
85(8)
5.5.1 Exploratory Data Analyses
85(1)
5.5.2 Logistic Regression Model
86(1)
5.5.3 Logistic Regression Model Fit
87(2)
5.5.4 Model Parameter Interpretations
89(1)
5.5.5 Model Prediction
90(3)
5.6 SSOCS Analysis: Probability of Bullying
93(8)
5.6.1 Exploratory Data Analysis
93(1)
5.6.2 Ordinal Multinomial Model
94(2)
5.6.3 Ordinal Multinomial Model Fit
96(1)
5.6.4 Model Parameters Interpretations
97(2)
5.6.5 Model Prediction
99(2)
5.7 Clickstream Analysis: Probability of Redlink
101(5)
5.7.1 Exploratory Data Analysis
102(1)
5.7.2 Logistic Regression Model
102(1)
5.7.3 Logistic Regression Model Fit
103(1)
5.7.4 Model Parameter Interpretations
104(1)
5.7.5 Model Prediction
105(1)
5.8 Summary
106(1)
5.9 Further Reading
107(1)
6 Count Response Models
108(24)
6.1 Introduction
108(1)
6.2 Modeling Count Data
109(6)
6.2.1 Poisson Models
109(1)
6.2.2 Overdispersion
110(1)
6.2.3 Coefficient Interpretations
111(2)
6.2.4 Negative Binomial Models
113(1)
6.2.5 Zero-Inflated Models
114(1)
6.2.6 Zero-Deflated Models
114(1)
6.2.7 Hurdle Models
115(1)
6.3 Fire-Climate Analysis: Decade Counts
115(8)
6.3.1 Exploratory Data Analysis
115(1)
6.3.2 Poisson Model
116(2)
6.3.3 Negative Binomial Models
118(1)
6.3.4 Zero-Inflated NB Models
119(4)
6.4 SSOCS Analysis: Annual Suspensions
123(3)
6.4.1 Hurdle Negative Binomial Model
123(1)
6.4.2 Model Fit
124(1)
6.4.3 Model Interpretations
124(2)
6.5 Clickstream Analysis: Site Pairings
126(4)
6.5.1 Exploratory Data Analysis
126(1)
6.5.2 Left-truncated Count Model
126(2)
6.5.3 Count Model Fit
128(1)
6.5.4 Coefficient Interpretations
129(1)
6.6 Summary
130(1)
6.7 Further Reading
131(1)
7 Time-to-Event Response Models
132(20)
7.1 Time-to-Event Data
132(1)
7.2 Time-to-Event Models
133(2)
7.3 FHS Analysis: Time to Hypertension
135(15)
7.3.1 Life Tables
135(3)
7.3.2 Kaplan-Meier Method
138(2)
7.3.3 Cox Proportional Hazards Models
140(5)
7.3.4 Time-Dependent Cox Models
145(5)
7.4 Summary
150(1)
7.5 Further Reading
150(2)
8 Longitudinal Response Models
152(31)
8.1 Longitudinal Data
152(1)
8.2 Autocorrelation in Longitudinal Data
153(3)
8.2.1 Descriptive Analysis
153(1)
8.2.2 Scatter plots
153(1)
8.2.3 Autocorrelation Plots
154(1)
8.2.4 Variograms
155(1)
8.2.5 Modeling Longitudinal Data
156(1)
8.3 Marginal Models
156(4)
8.3.1 Generalized Estimating Equations
157(1)
8.3.2 Working Correlation Structure
157(2)
8.3.3 Marginal Model Fit
159(1)
8.4 Conditional Models
160(3)
8.4.1 Random-Intercept Models
160(1)
8.4.2 Random-Slopes Models
161(1)
8.4.3 Conditional Model Fit
162(1)
8.5 FHS Analysis: Probability of Hypertension
163(9)
8.5.1 Exploratory Data Analysis
163(3)
8.5.2 Marginal Longitudinal Model
166(1)
8.5.3 Examining the Autocorrelation
166(2)
8.5.4 Marginal Longitudinal Model Fit
168(1)
8.5.5 Model Parameter Interpretations
168(2)
8.5.6 Model Prediction
170(2)
8.6 Fire-Climate Analysis: Decade Counts
172(9)
8.6.1 Exploratory Data Analysis
172(3)
8.6.2 Autocorrelation in Decade Counts
175(1)
8.6.3 Conditional Models for Decade Counts
175(1)
8.6.4 Conditional Longitudinal Model Fit
176(2)
8.6.5 Model Parameter Interpretations
178(1)
8.6.6 Model Prediction
179(2)
8.7 Summary
181(1)
8.8 Further Reading
181(2)
9 Structural Equation Modeling
183(19)
9.1 Introduction
183(6)
9.1.1 SEM Variable Categories
184(1)
9.1.2 Model Types
185(1)
9.1.3 SEM Paths
185(2)
9.1.4 Confirmatory Factor Analysis
187(1)
9.1.5 Evaluating Model Fit
188(1)
9.2 FHS Analysis: Latent Stress
189(5)
9.3 SSOCS Analysis: School Climate and Academic Success
194(7)
9.4 Summary
201(1)
9.5 Further Reading
201(1)
10 Matching Data to Models
202(9)
10.1 The Decision Process of Modeling
202(5)
10.2 Results of Model Application
207(2)
10.2.1 School Survey on Crime and Safety
207(1)
10.2.2 Framingham Heart Study
208(1)
10.2.3 Fire-Climate Interactions in the American West
208(1)
10.2.4 English Wikipedia Clickstream
209(1)
10.3 Perspectives on Modeling
209(2)
Bibliography 211(2)
Index 213
Jamie D. Riggs is an adjunct lecturer in the Predictive Analytics program at Northwestern University, Illinois. She specializes in the statistical issues of solar system cratering processes, solar physics, and galactic dynamics, and has collaborated with researchers at the Los Alamos National Laboratory, New Mexico and the Southwest Research Institute, Texas. She has held technical and managerial positions at Sun Microsystems, Inc., National Oceanic and Atmospheric Administration, and the Boeing Company, where she applied advanced statistical designs and analyses to manufacturing and business problems. She is the Solar System and Planetary Sciences Section Head of the International Astrostatistics Association. Trent L. Lalonde is Associate Professor of Applied Statistics at the University of Northern Colorado, and Director of the University's Research Consulting Lab. He has spent a number of years designing and teaching graduate courses covering statistical methods for students in diverse areas such as special education, psychological sciences, and public health. In addition, he has helped direct dissertations in these areas, and has consulted with numerous faculty on publications and funding proposals. He has received awards for both instruction and advising, and has Chaired the Applied Public Health Statistics section of the American Public Health Association.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97811082069146e.html
Märksõnad: