The DOI matches its Crossref record; 63 of the 64 references it cites were found in a registry or an index.
A significance test for the lasso
Open accessAbstract
In the sparse linear regression setting, we consider testing the significance of the predictor variable that enters the current lasso model, in the sequence of models visited along the lasso solution path. We propose a simple test statistic based on lasso fitted values, called the covariance test statistic, and show that when the true model is linear, this statistic has an $\operatorname{Exp}(1)$ asymptotic distribution under the null hypothesis (the null being that all truly active variables are contained in the current lasso model). Our proof of this result for the special case of the first predictor to enter the model (i.e., testing for a single significant predictor variable against the global null) requires only weak assumptions on the predictor matrix $X$. On the other hand, our proof for a general step in the lasso path places further technical assumptions on $X$ and the generative model, but still allows for the important high-dimensional case $p>n$, and does not necessarily require that the current lasso model achieves perfect recovery of the truly active variables. Of course, for testing the significance of an additional variable between two nested linear models, one typically uses the chi-squared test, comparing the drop in residual sum of squares (RSS) to a $\chi^{2}_{1}$ distribution. But when this additional variable is not fixed, and has been chosen adaptively or greedily, this test is no longer appropriate: adaptivity makes the drop in RSS stochastically much larger than $\chi^{2}_{1}$ under the null hypothesis. Our analysis explicitly accounts for adaptivity, as it must, since the lasso builds an adaptive sequence of linear models as the tuning parameter $\lambda$ decreases. In this analysis, shrinkage plays a key role: though additional variables are chosen adaptively, the coefficients of lasso active variables are shrunken due to the $\ell_{1}$ penalty. Therefore, the test statistic (which is based on lasso fitted values) is in a sense balanced by these two opposing properties—adaptivity and shrinkage—and its null distribution is tractable and asymptotically $\operatorname{Exp}(1)$.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Unlike stepwise variable selection procedures, LARS does not over-inflate effect size estimates during variable selection,14 nor bias hypothesis tests of those effect sizes.19”
From A structured approach to hypotheses involving continuous exposures over the life course (2016) · cites this paper as [19]
In the citing paper
“However, stepwise regression would introduce biases that LARS is known to overcome,19 and we have previously discussed how the grouped lasso and elastic net methods would result in the identification of needlessly complicated hypotheses.13”
From A structured approach to hypotheses involving continuous exposures over the life course (2016) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482
Self-citationThe Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Self-citationThe Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Self-citationDonoho, D. L. (2006) · IEEE Transactions on Information Theory · doi:10.1109/tit.2006.871582 · Cited by 23,994
Regularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957
Regularization Paths for Generalized Linear Models via Coordinate Descent
Friedman, J., Hastie, T., & Tibshirani, R. (2010) · Journal of Statistical Software · doi:10.18637/jss.v033.i01 · Cited by 19,927
Self-citationDonoho, D. L. (2004) · Cited by 16,703
Boyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,917
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
Lu, Z. Q. J. (2010) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1111/j.1467-985x.2010.00646_6.x · Cited by 12,916
A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
Beck, A., & Teboulle, M. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080716542 · Cited by 11,952
Efron, B., Hastie, T., Johnstone, I., & Tibshirani, R. (2004) · The Annals of Statistics · doi:10.1214/009053604000000067 · Cited by 9,357
Self-citationNear-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
Candès, E. J., & Tao, T. (2006) · IEEE Transactions on Information Theory · doi:10.1109/tit.2006.885507 · Cited by 6,809
Atomic Decomposition by Basis Pursuit
Chen, S. S., Donoho, D. L., & Saunders, M. A. (1998) · SIAM Journal on Scientific Computing · doi:10.1137/s1064827596304010 · Cited by 6,734
Estimation of the Mean of a Multivariate Normal Distribution
Stein, C. M. (1981) · The Annals of Statistics · doi:10.1214/aos/1176345632 · Cited by 2,795
Meinshausen, N., & Bühlmann, P. (2010) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2010.00740.x · Cited by 2,463
On Model Selection Consistency of Lasso
Zhao, P., & Yu, B. (2006) · doi:10.5555/1248547.1248637 · Cited by 2,314
Pathwise coordinate optimization
Friedman, J. H., Hastie, T. J., Höfling, H., & Tibshirani, R. J. (2007) · The Annals of Applied Statistics · doi:10.1214/07-aoas131 · Cited by 1,906
Self-citationExtreme value theory : an introduction
de Haan, L., & Ferreira, A. M. (2006) · EUR Research Repository (Erasmus University Rotterdam) · Cited by 1,310
Wainwright, M. J. (2009) · IEEE Transactions on Information Theory · doi:10.1109/tit.2009.2016018 · Cited by 1,202
NESTA: A Fast and Accurate First-Order Method for Sparse Recovery
Becker, S., Bobin, J., & Candès, E. J. (2011) · SIAM Journal on Imaging Sciences · doi:10.1137/090756855 · Cited by 1,106
On asymptotically optimal confidence regions and tests for high-dimensional models
van de Geer, S., Bühlmann, P., Ritov, Y., & Dezeure, R. (2014) · The Annals of Statistics · doi:10.1214/14-aos1221 · Cited by 1,016
Confidence Intervals for Low Dimensional Parameters in High Dimensional Linear Models
Zhang, C., & Zhang, S. S. (2013) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/rssb.12026 · Cited by 1,011
On the “degrees of freedom” of the lasso
Zou, H., Hastie, T. J., & Tibshirani, R. J. (2007) · The Annals of Statistics · doi:10.1214/009053607000000127 · Cited by 962
Self-citationHuman Immunodeficiency Virus Reverse Transcriptase and Protease Sequence Database
Shafer, R. W., Stevenson, D., & Chan, B. K. (1999) · Nucleic Acids Research · doi:10.1093/nar/27.1.348 · Cited by 907
NESTA: A Fast and Accurate First-Order Method for Sparse Recovery
Becker, S., Bobin, J., & Candès, E. J. (2009) · Cited by 897
A new approach to variable selection in least squares problems
Osborne, M. R. (2000) · IMA Journal of Numerical Analysis · doi:10.1093/imanum/20.3.389 · Cited by 861
L 1-Regularization Path Algorithm for Generalized Linear Models
Park, M. Y., & Hastie, T. J. (2007) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2007.00607.x · Cited by 859
Human immunodeficiency virus reverse transcriptase and protease sequence database
Rhee, S. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkg100 · Cited by 818
Osborne, M. R., Presnell, B., & Turlach, B. A. (2000) · Journal of Computational and Graphical Statistics · doi:10.2307/1390657 · Cited by 705
Confidence Intervals and Hypothesis Testing for High-Dimensional RegressionPreprint
Javanmard, A., & Andrea Montanari, A. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.3171 · Cited by 654
Templates for convex cone problems with applications to sparse signal recovery
Becker, S., Candès, E. J., & Grant, M. C. (2011) · Mathematical Programming Computation · doi:10.1007/s12532-011-0029-5 · Cited by 588
How Biased is the Apparent Error Rate of a Prediction Rule?
Efron, B. (1986) · Journal of the American Statistical Association · doi:10.2307/2289236 · Cited by 587
Extreme Value Theory: An Introduction
Michailidis, G. C., & Stoev, S. (2007) · Technometrics · doi:10.1198/tech.2007.s684 · Cited by 517
The lasso problem and uniqueness
Tibshirani, R. J. (2013) · Electronic Journal of Statistics · doi:10.1214/13-ejs815 · Cited by 514
Self-citationHigh-dimensional variable selectionPreprint
Wasserman, L., & Roeder, K. (2009) · Cited by 504
Near-ideal model selection by ℓ1 minimization
Candès, E. J., & Plan, Y. (2008) · Cited by 469
Estimation of Parameters and Large Quantiles Based on the k Largest Observations
Weissman, I. (1978) · Journal of the American Statistical Association · doi:10.1080/01621459.1978.10480104 · Cited by 468
Scaled sparse linear regression
Sun, T., & Zhang, C.-H. (2012) · Biometrika · doi:10.1093/biomet/ass043 · Cited by 463
p -Values for High-Dimensional Regression
Meinshausen, N., Meier, L., & Bühlmann, P. (2009) · Journal of the American Statistical Association · doi:10.1198/jasa.2009.tm08647 · Cited by 447
High-dimensional variable selection
Wasserman, L., & Roeder, K. (2009) · The Annals of Statistics · doi:10.1214/08-aos646 · Cited by 409
Persistence in high-dimensional linear predictor selection and the virtue of overparametrization
Greenshtein, E., & Ritov, Y. (2004) · Bernoulli · doi:10.3150/bj/1106314846 · Cited by 362
Degrees of freedom in lasso problems
Tibshirani, R. J., & Taylor, J. (2012) · doi:10.1184/r1/6586544.v1 · Cited by 333
Self-citationRecovery of Exact Sparse Representations in the Presence of Bounded Noise
Fuchs, J.-J. (2005) · IEEE Transactions on Information Theory · doi:10.1109/tit.2005.855614 · Cited by 321
Near-ideal model selection by ℓ1 minimization
Candès, E. J., & Plan, Y. (2009) · The Annals of Statistics · doi:10.1214/08-aos653 · Cited by 303
Variance Estimation Using Refitted Cross-Validation in Ultrahigh Dimensional Regression
Fan, J., Guo, S., & Hao, N. (2011) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2011.01005.x · Cited by 264
Degrees of freedom in lasso problems
Tibshirani, R. J., & Taylor, J. (2012) · The Annals of Statistics · doi:10.1214/12-aos1003 · Cited by 239
Self-citationStatistical significance in high-dimensional linear models
Bühlmann, P. (2013) · Bernoulli · doi:10.3150/12-bejsp11 · Cited by 196
Javanmard, A., & Andrea Montanari, A. (2014) · IEEE Transactions on Information Theory · doi:10.1109/tit.2014.2343629 · Cited by 137
Estimation of parameters and large quantiles based on the K largest observations
Weissman, I. (1978) · Advances in Applied Probability · doi:10.1017/s0001867800030561 · Cited by 134
Validity of the expected Euler characteristic heuristic
Taylor, J., Takemura, A., & Adler, R. J. (2005) · The Annals of Probability · doi:10.1214/009117905000000099 · Cited by 104
Self-citationA Perturbation Method for Inference on Regularized Regression Estimates
Minnier, J., Tian, L., & Cai, T. (2011) · Journal of the American Statistical Association · doi:10.1198/jasa.2011.tm10382 · Cited by 102
Statistical Inference After Model Selection
Berk, R. A., Brown, L., & Zhao, L. H. (2009) · Journal of Quantitative Criminology · doi:10.1007/s10940-009-9077-7 · Cited by 90
Adaptive Confidence Intervals for the Test Error in Classification
Laber, E. B., & Murphy, S. A. (2011) · Journal of the American Statistical Association · doi:10.1198/jasa.2010.tm10053 · Cited by 61
L1 Regularization Path Algorithm for Generalized Linear Models
Jing, Y. (2008) · Journal of Jiamusi University · Cited by 60
P-values for high-dimensional regressionPreprint
Meinshausen, N., Meier, L., & Bühlmann, P. (2008) · arXiv (Cornell University) · doi:10.48550/arxiv.0811.2177 · Cited by 37
Nearly optimal sample size in hypothesis testing for high-dimensional regression
Javanmard, A., & Andrea Montanari, A. (2013) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2013.6736695 · Cited by 32
Confidence Intervals for Low-Dimensional Parameters With High-Dimensional DataPreprint
Zhang, C., & Zhang, S. S. (2011) · arXiv (Cornell University) · Cited by 29
Sequential Selection Procedures and False Discovery Rate ControlPreprint
G’Sell, M., Wager, S., Chouldechova, A., & Tibshirani, R. J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1309.5352 · Cited by 16
Self-citationAdaptive testing for the graphical lassoPreprint
G’Sell, M., Taylor, J., & Tibshirani, R. J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1307.4765 · Cited by 15
Self-citationTests in adaptive regression via the Kac-Rice formulaPreprint
Taylor, J., Loftus, J. R., & Tibshirani, R. J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1308.3020 · Cited by 15
Self-citationEstimation of parameters and large quantiles based on the K largest observations
Weissman, I. (1978) · Advances in Applied Probability · doi:10.2307/1426930 · Cited by 9
van de Geer, S. (2013) · Journal of Statistical Planning and Inference · doi:10.1016/j.jspi.2013.03.006 · Cited by 6
False Discovery Rate Control for Sequential Selection Procedures, with Application to the LassoPreprint
G’Sell, M., Wager, S., Chouldechova, A., & Tibshirani, R. J. (2013) · arXiv (Cornell University) · Cited by 6
Self-citation
Cited by
Sorted by citations
Statistical predictions with glmnet
Engebretsen, S., & Bohlin, J. (2019) · Clinical Epigenetics · doi:10.1186/s13148-019-0730-1 · Cited by 1,212
Tau and Aβ imaging, CSF measures, and cognition in Alzheimer’s disease
Brier, M. R., Gordon, B., Friedrichsen, K., McCarthy, J., Stern, A., Christensen, J., Owen, C., Aldea, P., Su, Y., Hassenstab, J., et al. (2016) · Science Translational Medicine · doi:10.1126/scitranslmed.aaf2362 · Cited by 734
Exact post-selection inference, with application to the lasso
Lee, J. D., Sun, D. L., Sun, Y., & Taylor, J. (2016) · The Annals of Statistics · doi:10.1214/15-aos1371 · Cited by 733
Self-citationControlling the false discovery rate via knockoffs
Barber, R. F., & Candès, E. J. (2015) · The Annals of Statistics · doi:10.1214/15-aos1337 · Cited by 756
Detecting and quantifying causal associations in large nonlinear time series datasets
Runge, J., Nowack, P., Kretschmer, M., Flaxman, S., & Sejdinović, D. (2019) · Publication Database PIK (Potsdam Institute for Climate Impact Research (PIK)) · Cited by 713
Metadata
- Authors
- Lockhart, R., Taylor, J., Tibshirani, R. J., & Tibshirani, R.
- Affiliations
- Simon Fraser University (CA)
- Carnegie Mellon University (US)
- Venue
- The Annals of Statistics
- Publisher
- Institute of Mathematical Statistics
- Published
- 2014-04-01
- Volume
- 42
- Issue
- 2
- Pages
- 413-468
- ISSN
- 0090-5364 (ISSN-L)
- 2168-8966
- PMC
- PMC4285373
- OpenAlex
- W2172185584
- Cited by
- 541
- References
- 64
- Citations by year
- 2026: 6 · 2025: 20 · 2024: 21 · 2023: 22 · 2022: 43 · 2021: 40 · 2020: 59 · 2019: 68 · 2018: 67 · 2017: 51 · 2016: 60 · 2015: 50 · 2014: 23
- FWCI
- 64.76
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- The Annals of Statistics (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- KiltHub Repository (submittedVersion)
- Project Euclid (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation
- National Institutes of Health
- Natural Sciences and Engineering Research Council of Canada
- National Institute of Biomedical Imaging and Bioengineering (R01EB001988)
- Air Force Office of Scientific Research
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Statistical Methods and Models
- Physical Sciences › Computer Science › Signal Processing › Sparse and Compressive Sensing Techniques
- Keywords
- LASSO, significance testing, sparse linear regression, shrinkage, high-dimensional regression, nested models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
