STAT 548 2020-21
Nancy Heckman's Suggested Papers
MY RESEARCH INTERESTS: I am interested in smoothing methods in regression (spline smoothing, kernel smoothing) and in the closely related area of Functional Data Analysis (FDA). In FDA, each sampling unit provides information about an entire function.
Common FDA techniques include mixed effects models as in longitudinal data analysis, and stochastic processes. I am also interested in hidden Markov models, especially in the context of FDA.
I apply these methods to several areas: evolutionary biology, energy consumption, and animal movement.
to list papers that are related to my research interests, but take me a bit further afield, so that we can both learn some things.
If you are interested in discussing a paper, please e-mail so that we can find a mutually convenient time.
ADDITIONAL PAPERS may be added from time to time, if I come
across some. You are also welcome to suggest a paper - preferrably one that ties
in with my research interests.
GOALS: for some of the papers, I've tried to list some goals. These goals are
just suggestions, and we can discuss what you want to do.
For instance, in some cases, I've written
too many goals. For other papers - we can discuss goals.
Delaigle, A. and Hall, P. (2012).
Methodology and theory for partial least squares applied to functional data.
Annals of Statistics, 40, 322-352.
It's interesting to think about how partial least squares might be used in functional data analysis. This is one approach. Partial least squares is a method that can scale up to large data.
R. Dennis Cook, Bing Li and Francesca Chiaromonte (2007).
Dimension Reduction in Regression without Matrix Inversion.
Biometrika, Vol. 94, No. 3 569-584
Goal: This paper seems to lay the groundwork for partial least squares-type dimension reduction. I think understanding the whole paper is a tall order. Pick a part to understand.
AVAILABLE: Kendall, David G. (1989).
A Survey of the Statistical Theory of Shape.
Statist. Sci. Volume 4, Number 2, 87-99.
Goal: I've been wanting to understand the geometry used
to describe shape, as discussed in this article. Can you
explain it to me? I find this a difficult paper, but if you
are into geometry maybe you will have better luck. You can certainly
restrict your work to one aspect of this paper, perhaps
considering a simple case.
AVAILABLE: Duchesne, Fortin and Rivest (2015).
between step selection functions and biased correlated random
walks for statistical inference on animal movement. PLOS ONE,
R Langrock, T Kneib, A Sohn and S DeRuiter (2015).
Nonparametric Inference in Hidden Markov Models Using P-Splines.
Biometrics 71: 520-528.
DeRuiter, Langrock, Skirbutus, Goldbogen, Calambokidis, Friedlaender and Southall (2017). A multivariate mixed hidden Markov model for blue whale behaviour and responses to sound exposure. The Annals of Applied Statistics.
Langrock, Adam, Leos-Barajas, Mews, Miller and Papastamatiou (2018). Spline-based nonparametric inference in general state-switching models. Statistica Neerlandica.
Return to the STAT548 home page