Subset selection in regression - Info and Reading Options

"Subset selection in regression" Table Of Contents:

• 1- Machine generated contents note: 1 Objectives
• 2- 1.1 Prediction, explanation, elimination or what?
• 3- 1.2 How many variables in the prediction formula?
• 4- 1.3 Alternatives to using subsets
• 5- 1.4 'Black box' use of best-subsets techniques
• 6- 2 Least-squares computations
• 7- 2.1 Using sums of squares and products matrices
• 8- 2.2 Orthogonal reduction methods
• 9- 2.3 Gauss-Jordan v. orthogonal reduction methods
• 10- 2.4 Interpretation of projections
• 11- Appendix A. Operation counts for all-subsets regression
• 12- A.1 Garside's Gauss-Jordan algorithm
• 13- A.2 Planar rotations and a Hamiltonian cycle
• 14- A.3 Planar rotations and a binary sequence
• 15- A.4 Fast planar rotations
• 16- 3 Finding subsets which fit well
• 17- 3.1 Objectives and limitations of this chapter
• 18- 3.2 Forward selection
• 19- 3.3 Efroymson's algorithm
• 20- 3.4 Backward elimination
• 21- 3.5 Sequential replacement algorithms
• 22- 3.6 Replacing two variables at a time
• 23- 3.7 Genierating all subsets
• 24- 3.8 Using branch-and-bound techniques
• 25- 3.9 Grouping variables
• 26- 3.10 Ridge regression and other alternatives
• 27- 3.11 The nonnegative garrote and the lasso
• 28- 3.12 Some examples
• 29- 3.13 Conclusions and recommendations
• 30- Appendix A. An algorithm for the lasso
• 31- 4 Hypothesis testing
• 32- 4.1 Is there any information in the remaining variables?
• 33- 4.2 Is one subset better than another?
• 34- 4.2.1 Applications of Spj-tvoll's method
• 35- 4.2.2 Using other confidence ellipsoids
• 36- Appendix A.Spjotvoll's method - detailed description
• 37- 5 When to stop?
• 38- 5.1 What criterion should we use?
• 39- 5.2 Prediction criteria
• 40- 5.2.1 Mean squared errors of prediction (MSEP)
• 41- 5.2.2 MSEP for the fixed model
• 42- 5.2.3 MSEP for the random model
• 43- 5.2.4 A simulation with random predictors
• 44- 5.3 Cross-validation and the P SS statistic
• 45- 5.4 Bootstrapping
• 46- 5.5 Likelihood and information-based stopping rules
• 47- 5.5.1 Minimum description length (MDL)
• 48- Appendix A. Approximate equivaence of stppingules
• 49- A.1 F-to-enter
• 50- A.2 Adjusted R2 or Fisher's A-statistic
• 51- A.3 Akaikesinformatibn criterion (AIC)
• 52- 6 Estatmaion of regression eficients
• 53- 6.1 Selection bias
• 54- 6.2 Choice between two varies
• 55- 6.3 Selection rduction
• 56- 6.3.1 Monte C o et tionfias i f d lection
• 57- 6.3.2 Shrinkage methods
• 58- 6.3.3 Using the jack-knife
• 59- 6.3.4 Independent; data sets ;
• 60- 6.4 Conditional likiood estimations
• 61- 6.5 Estimationofpopulation means
• 62- 6.6 Estimating least-squares projections ;
• 63- Appendix A. Changing projections to equate sums of squares
• 64- 7 Bayesian mnethods
• 65- 7.1 Bayesian introduction
• 66- 7.2 'Spike and slab'prior
• 67- 7.3 Normal prior for regression coefficients
• 68- 7.4 Model averaging
• 69- 7.5 Picking the best model
• 70- 8 Conclusions and some recommendations
• 71- References
• 72- Index.

Read “Subset selection in regression”:

Read “Subset selection in regression” by choosing from the options below.