Foundations of Linear and Generalized Linear Models by Alan Agresti

By Alan Agresti

A useful evaluation of crucial principles and ends up in statistical modeling

Written by means of a highly-experienced writer, Foundations of Linear and Generalized Linear Models is a transparent and entire consultant to the major ideas and result of linear statistical types. The booklet provides a extensive, in-depth evaluate of the main popular statistical types by means of discussing the speculation underlying the types, R software program functions, and examples with crafted types to explain key principles and advertise sensible version building.

The publication starts off via illustrating the basics of linear types, corresponding to how the model-fitting tasks the information onto a version vector subspace and the way orthogonal decompositions of the information yield information regarding the consequences of explanatory variables. as a result, the publication covers the preferred generalized linear versions, which come with binomial and multi-nomial logistic regression for express facts, and Poisson and unfavorable binomial log linear versions for count number facts.

Focusing at the theoretical underpinnings of those types, Foundations of Linear and Generalized Linear Models additionally good points:
• An advent to quasi-likelihood equipment that require weaker distributional assumptions, comparable to generalized estimating equation methods
• an summary of linear combined types and generalized linear combined versions with random results for clustered correlated facts, Bayesian modeling, and extensions to deal with tricky circumstances equivalent to excessive dimensional difficulties
• quite a few examples that use R software program for all textual content info analyses
• greater than four hundred workouts for readers to perform and expand the speculation, tools, and knowledge research
• A supplementary site with datasets for the examples and workouts a useful textbook for upper-undergraduate and graduate-level scholars in facts and biostatistics classes, Foundations of Linear and Generalized Linear Models can be an exceptional reference for training statisticians and biostatisticians, in addition to somebody who's attracted to studying in regards to the most vital statistical versions for interpreting information.

Show description

Read Online or Download Foundations of Linear and Generalized Linear Models PDF

Similar probability books

Empirical likelihood

Empirical chance presents inferences whose validity doesn't rely on specifying a parametric version for the knowledge. since it makes use of a probability, the tactic has convinced inherent benefits over resampling equipment: it makes use of the information to figure out the form of the boldness areas, and it makes it effortless to mixed info from a number of resources.

Shape Optimization under Uncertainty from a Stochastic Programming Point of View

Optimization difficulties are suitable in lots of components of technical, commercial, and fiscal functions. whilst, they pose difficult mathematical study difficulties in numerical research optimization. Harald Held considers an elastic physique subjected to doubtful inner and exterior forces. considering the fact that easily averaging the potential loadings will lead to a constitution that will now not be strong for the person loadings, he makes use of ideas from point set-based form optimization and two-stage stochastic programming.

OECD Glossary of Statistical Terms (OECD Glossaries)

###############################################################################################################################################################################################################################################################

Statistics and Probability Theory: In Pursuit of Engineering Decision Support

Of functional relevance - but theoretically sturdy and consistant
Emphasis on relevance for engineering selection help and assessments
Written for engineers through an engineer

This ebook presents the reader with the fundamental abilities and instruments
of records and chance within the context of engineering modeling and research. The emphasis is at the program and the reasoning at the back of the applying of those abilities and instruments for the aim of bettering determination making in engineering.

The objective of the publication is to make sure that the reader will gather the necessary theoretical foundation and technical talents similar to to believe ok with the idea of uncomplicated records and chance. additionally, during this e-book, rather than many commonplace books at the similar topic, the viewpoint is to target using the idea for the aim of engineering version construction and determination making. This paintings is appropriate for readers with very little past wisdom with regards to statistics and probability.

Content point » Professional/practitioner

Keywords » Bayesian likelihood idea - Engineering version development - Engineering determination help - likelihood - Statistics

Related matters » actual & info technological know-how - chance concept and Stochastic tactics - creation & technique Engineering

Additional info for Foundations of Linear and Generalized Linear Models

Example text

3) Since ???? 2 L(????)∕???????? 2 = 2XT X is positive definite, the minimum rather than maximum ̂ of L(????) occurs at ????. 2 Hat Matrix and Moments of Estimators The fitted values ????̂ are a linear transformation of y, ????̂ = X????̂ = X(XT X)−1 XT y. ̂ with each column Here “normal” refers not to the normal distribution but to orthogonality of (y − ????) of X. 2 29 LEAST SQUARES MODEL FITTING The n × n matrix H = X(XT X)−1 XT is called3 the hat matrix because it linearly transforms y to ????̂ = Hy. The hat matrix H is a projection matrix, projecting y to ????̂ in the model space C(X).

8 A model M has model matrix X. A simpler model M0 results from removing the final term in M, and hence has model matrix X0 that deletes the final column from X. From the definition of a column space, explain why C(X0 ) is contained in C(X). 9 For the normal linear model, explain why the expression yi = ∑p with ????i ∼ N(0, ???? 2 ) is equivalent to yi ∼ N( j=1 ????j xij , ???? 2 ). 10 GLMs normally use a hierarchical structure by which the presence of a higher-order term implies also including the lower-order terms.

For a particular model fit, the sample version estimates the difference between the overall means if all subjects sampled were in group 1 and if all subjects sampled were in group 0. For observational data, this mimics a counterfactual measure to estimate if we could instead conduct an experiment and observe subjects under each treatment group, rather than have half the observations missing. See Gelman and Hill (2006, Chapters 9 and 10), Rubin (1974), and Rosenbaum and Rubin (1983). 1 Suppose that yi has a N(????i , ???? 2 ) distribution, i = 1, … , n.

Download PDF sample

Rated 4.83 of 5 – based on 31 votes