1 / 51

Raymond J. Carroll Texas A&M University http://stat.tamu.edu/~carroll carroll@stat.tamu.edu Postdoctoral Training Pr

Non/Semiparametric Regression and Clustered/Longitudinal Data. Raymond J. Carroll Texas A&M University http://stat.tamu.edu/~carroll carroll@stat.tamu.edu Postdoctoral Training Program: http://stat.tamu.edu/B3NC. Where am I From?. Wichita Falls, my hometown. College Station, home of

nelson
Download Presentation

Raymond J. Carroll Texas A&M University http://stat.tamu.edu/~carroll carroll@stat.tamu.edu Postdoctoral Training Pr

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Non/Semiparametric Regression and Clustered/Longitudinal Data Raymond J. Carroll Texas A&M University http://stat.tamu.edu/~carroll carroll@stat.tamu.edu Postdoctoral Training Program: http://stat.tamu.edu/B3NC

  2. Where am I From? Wichita Falls, my hometown College Station, home of Texas A&M Big Bend National Park I-45 I-35

  3. Acknowledgments Raymond Carroll Oliver Linton Alan Welsh Series of papers are on my web site Lin, Wang and Welsh: Longitudinal data (Mammen & Linton for pseudo-observation methods) Linton and Mammen: time series data Xihong Lin Naisyin Wang Enno Mammen

  4. Outline • Longitudinal models: • panel data • Background: • splines = kernels for independent data • Correlated data: • do splines = kernels? • Semiparametric case: • partially linear model: • does it matter what nonparametric method is used?

  5. Panel Data (for simplicity) • i = 1,…,n clusters/individuals • j = 1,…,m observations per cluster

  6. Panel Data (for simplicity) • i = 1,…,n clusters/individuals • j = 1,…,m observations per cluster • Important points: • The cluster size m is meant to be fixed • This is not a multiple time series problem where the cluster size increases to infinity • Some comments on the single time series problem are given near the end of the talk

  7. The Marginal Nonparametric Model • Y = Response • X = time-varying covariate • Question: can we improve efficiency by accounting for correlation?

  8. The Marginal Nonparametric Model • Important assumption • Covariates at other waves are not conditionally predictive, i.e., they are surrogates • This assumption is required for any GLS fit, including parametric GLS

  9. Independent Data • Splines (smoothing, P-splines, etc.) with penalty parameter = l • Ridge regression fit • Some bias, smaller variance • is over-parameterized least squares • is a polynomial regression

  10. Independent Data • Kernels (local averages, local linear, etc.), with kernel density function K and bandwidth h • As the bandwidth h 0, only observations with X near t get any weight in the fit

  11. Independent Data • Major methods • Splines • Kernels • Smoothing parameters required for both • Fits: similar in many (most?) datasets • Expectation: some combination of bandwidths and kernel functions look like splines 12

  12. Independent Data • Splines and kernels are linear in the responses • Silverman showed that there is a kernel function and a bandwidth so that the weight functions are asymptotically equivalent • In this sense, splines = kernels • This talk is about the same result for correlated data

  13. The weight functions Gn(t=.25,x) in a specific case for independent data Kernel Smoothing Spline Note the similarity of shape and the locality: only X’s near t=0.25 get any weight

  14. Working Independence • Working independence: Ignore all correlations • Fix up standard errors at the end • Advantage: the assumption is not required • Disadvantage: possible severe loss of efficiency if carried too far

  15. Working Independence • Working independence: • Ignore all correlations • Should posit some reasonable marginal variances • Weighting important for efficiency • Weighted versions: Splines and kernels have obvious analogues • Standard method: Zeger & Diggle, Hoover, Rice, Wu & Yang, Lin & Ying, etc.

  16. Working Independence • Working independence: • Weighted splines and weighted kernels are linear in the responses • The Silverman result still holds • In this sense, splines = kernels

  17. Accounting for Correlation • Splines have an obvious analogue for non-independent data • Let be a working covariance matrix • Penalized Generalized least squares (GLS) • GLS ridge regression • Because splines are based on likelihood ideas, they generalize quickly to new problems

  18. Accounting for Correlation • Splines have an obvious analogue for non-independent data • Kernels are not so obvious • Local likelihood kernel ideas are standard in independent data problems • Most attempts at kernels for correlated data have tried to use local likelihood kernel methods

  19. Kernels and Correlation • Problem: how to define locality for kernels? • Goal: estimate the function at t • Let be a diagonal matrix of standard kernel weights • Standard Kernel method: GLS pretending inverse covariance matrix is • The estimate is inherently local

  20. Kernels and Correlation Specific case: m=3, n=35 Exchangeable correlation structure Red: r = 0.0 Green: r = 0.4 Blue: r= 0.8 Note the locality of the kernel method The weight functions Gn(t=.25,x) in a specific case 18

  21. Splines and Correlation Specific case: m=3, n=35 Exchangeable correlation structure Red: r = 0.0 Green: r = 0.4 Blue: r= 0.8 Note the lack of locality of the spline method The weight functions Gn(t=.25,x) in a specific case

  22. Splines and Correlation Specific case: m=3, n=35 Complex correlation structure Red: Nearly singular Green: r = 0.0 Blue: r= AR(0.8) Note the lack of locality of the spline method The weight functions Gn(t=.25,x) in a specific case

  23. Splines and Standard Kernels • Accounting for correlation: • Standard kernels remain local • Splines are not local • Numerical results can be confirmed theoretically • Don’t we want our nonparametric regression estimates to be local?

  24. Results on Kernels and Correlation • GLS with weights • Optimal working covariance matrix is working independence! • Using the correct covariance matrix • Increases variance • Increases MSE • Splines Kernels (or at least these kernels) 24

  25. Pseudo-Observation Kernel Methods • Better kernel methods are possible • Pseudo-observation: original method • Construction: specific linear transformation of Y • Mean = Q(X) • Covariance = diagonal matrix • This adjusts the original responses without affecting the mean

  26. Pseudo-Observation Kernel Methods • Construction: specific linear transformation of Y • Mean = Q(X) • Covariance = diagonal • Iterative: • Efficiency: More efficient than working independence • Proof of Principle: kernel methods can be constructed to take advantage of correlation

  27. Efficiency of Splines and Pseudo-Observation Kernels Exchng: Exchangeable with correlation 0.6 AR: autoregressive with correlation 0.6 Near Sing: A nearly singular matrix

  28. Better Kernel Methods: SUR • Simulations of the original pseudo-observation method: it is not as efficient as splines • Suggests room for a better estimate • Naisyin Wang: her talk will describe an even better kernel method • Basis: seemingly unrelated regression ideas • Generalizable: based on likelihood ideas

  29. SUR Kernel Methods • It is well known that the GLS spline has an exact, analytic expression • We have shown that the Wang SUR kernel method has an exact, analytic expression • Both methods are linear in the responses

  30. SUR Kernel Methods • The two methods differ only in one matrix term • This turns out to be exactly the same matrix term considered by Silverman in his work • Relatively nontrivial calculations show that Silverman’s result still holds • Splines = SUR Kernels 29

  31. Nonlocality • The lack of locality of GLS splines and SUR kernels is surprising • Suppose we want to estimate the function at t • If any observation has an X near t, then all observations in the cluster contribute to the fit, not just those with covariates near t • Splines, pseudo-kernels and SUR kernels all borrow strength

  32. Nonlocality • Wang’s SUR kernels = BLUP-like pseudo kernels with a clever linear transformation. Let • SUR kernels are working independence kernels

  33. Locality of Kernels • Original pseudo-observation method: pseudo observations uncorrelated • SUR kernels: pseudo-observations are correlated • SUR kernels are not local • SUR kernels are local in (the same!) pseudo-observations

  34. Locality of Splines • Splines = SUR kernels (Silverman-type result) • GLS spline: • Iterative • standard independent spline smoothing • SUR pseudo-observations at each iteration • GLS splines are not local • GLS splines are local in (the same!) pseudo-observations

  35. Time Series Problems • Time series problems: many of the same issues arise • Original pseudo-observation method • Two stages • Linear transformation • Mean Q(X) • Independent errors • Single standard kernel applied • Potential for great gains in efficiency (even infinite for AR problems with large correlation)

  36. Time Series: AR(1) Illustration, First Pseudo Observation Method • AR(1), correlation r: • Regress Yt0 on Xt

  37. Time Series Problems • More efficient methods can be constructed • Series of regression problems: for all j, • Pseudo observations • Mean • White noise errors • Regress for each j: fits are asymptotically independent • Then weighted average • Time series version of SUR-kernels for longitudinal data?

  38. Time Series: AR(1) Illustration, New Pseudo Observation Method • AR(1), correlation r: • Regress Yt0 on Xt and Yt1 on Xt-1 • Weights: 1 and r2

  39. Time Series Problems • AR(1) errors with correlation r • Efficiency of original pseudo-observation method to working independence: • Efficiency of new (SUR?) pseudo-observation method to original method: 36

  40. The Semiparametric Model • Y = Response • X,Z = time-varying covariates • Question: can we improve efficiency for bby accounting for correlation?

  41. Profile Methods • Given b, solve for Q, say • Basic idea: Regress • Working independence • Standard kernels • Pseudo –observations kernels • SUR kernels

  42. Profile Methods • Given b, solve for Q, say • Then fit GLS or W.I. to the model with mean • Question: does it matter what kernel method is used? • Question: How bad is using W.I. everywhere? • Question: are there efficient choices?

  43. The Semiparametric Model: Special Case • If X does not vary with time, simple semiparametric efficient method available • The basic point is that has common mean and covariance matrix • If were a polynomial, GLS likelihood methods would be natural

  44. The Semiparametric Model: Special Case • Method: Replace polynomial GLS likelihood with GLS local likelihood with weights • Then do GLS on the derived variable • Semiparametric efficient

  45. Profile Method: General Case • Given b, solve for Q, say • Then fit GLS or W.I. to the model with mean • In this general case, how you estimate Q matters • Working independence • Standard kernel • Pseudo-observation kernel • SUR kernel

  46. Profile Methods • In this general case, how you estimate Q matters • Working independence • Standard kernel • Pseudo-observation kernel • SUR kernel • We have published the asymptotically efficient score, but not how to implement it

  47. Profile Methods • Naisyin Wang’s talk will describe • These phenomena • Search for an efficient estimator • Loss of efficiency for using working independence to estimate Q • Examples where ignoring the correlation can change conclusions

  48. Conclusions (1/3): Nonparametric Regression • In nonparametric regression • Kernels = splines for working independence (W.I.) • Weighting is important for W.I. • Working independence is inefficient • Standard kernels splines for correlated data

  49. Conclusions (2/3): Nonparametric Regression • In nonparametric regression • Pseudo-observation methods improve upon working independence • SUR kernels = splines for correlated data • Splines and SUR kernels are not local • Splines and SUR kernels are local in pseudo-observations

  50. Conclusions (3/3): Semiparametric Regression • In semiparametric regression • Profile methods are a general class • Fully efficient parameter estimates are easily constructed if X is not time-varying • When X is time-varying, method of estimating affects properties of parameter estimates • Ignoring correlations can change conclusions (see N. Wang talk)

More Related