Michael Law
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Michael Law has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Charlotte Brown
Department of Statistics University of Michigan Ann Arbor
44 shared publications - Justin A. Colacino
University of Michigan School of Public Health
44 shared publications - Ya'Acov Ritov
Department of Statistics, University of Michigan, Ann Arbor, USA
44 shared publications - Jin Niu
Department of Economics, Brown University, Providence, Rhode Island
43 shared publications - Alexander Henzi
Seminar for Statistics ETH Zurich Zurich Switzerland
1 shared publication - Jin Niu
Department of Economics Brown University
1 shared publication
Latest Publications
- 14 May 2024
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 111 (4) , 1169-1186
A rank-based sequential test of independence
Summary: We consider the problem of independence testing for two univariate random variables in a sequential setting. By leveraging recent developments on safe, anytime-valid inference, we propose a test with time-uniform Type-I error control and derive explicit bounds on the finite-sample performance of the test. We demonstrate the empirical performance of the procedure in comparison to existing sequential and nonsequential independence tests. Furthermore, since the proposed test is distribution-free under the null hypothesis, we empirically simulate the gap due to Ville’s inequality, the supermartingale analogue of Markov’s inequality, that is commonly applied to control Type-I error in anytime-valid inference, and apply this to construct a truncated sequential test.
- 14 May 2024
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 111 (4) , 1169-1186
A rank-based sequential test of independence
Summary: We consider the problem of independence testing for two univariate random variables in a sequential setting. By leveraging recent developments on safe, anytime-valid inference, we propose a test with time-uniform Type-I error control and derive explicit bounds on the finite-sample performance of the test. We demonstrate the empirical performance of the procedure in comparison to existing sequential and nonsequential independence tests. Furthermore, since the proposed test is distribution-free under the null hypothesis, we empirically simulate the gap due to Ville’s inequality, the supermartingale analogue of Markov’s inequality, that is commonly applied to control Type-I error in anytime-valid inference, and apply this to construct a truncated sequential test.
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
FIGURE 2 from Longitudinal Position and Cancer Risk in the United States Revisited
Output of linear approximation for total cancers. Figure shows linear approximation results of total cancer incidence rate by relative position with 95% bootstrap confidence band with 607 counties (A) and with 2,853 counties (B).
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessFIGURE 2 from Longitudinal Position and Cancer Risk in the United States Revisited
Output of linear approximation for total cancers. Figure shows linear approximation results of total cancer incidence rate by relative position with 95% bootstrap confidence band with 607 counties (A) and with 2,853 counties (B).
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Figure 3 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 3 shows maps of cancer incidence rate by county for most prevalent cancer.
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure 3 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 3 shows maps of cancer incidence rate by county for most prevalent cancer.
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
FIGURE 4 from Longitudinal Position and Cancer Risk in the United States Revisited
Output of natural splines for most prevalent cancers. Figure shows the output of natural splines conducted on incidence by longitude and time zone for four of the most prevalent cancers, with 95% bootstrap confidence band. A, Liver and bile duct cancer (without MST, n = 1,063). B, Lung and bronchus cancer (n = 2,441). C, Colon and rectum cancer (n = 1,955). D, Pancreas cancer (n = 1,191).
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessFIGURE 4 from Longitudinal Position and Cancer Risk in the United States Revisited
Output of natural splines for most prevalent cancers. Figure shows the output of natural splines conducted on incidence by longitude and time zone for four of the most prevalent cancers, with 95% bootstrap confidence band. A, Liver and bile duct cancer (without MST, n = 1,063). B, Lung and bronchus cancer (n = 2,441). C, Colon and rectum cancer (n = 1,955). D, Pancreas cancer (n = 1,191).
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table 7 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Table 7 shows Reported Coefficients of Relative Position for Other Selected Cancers (with 95% Confidence Interval)
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 7 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Table 7 shows Reported Coefficients of Relative Position for Other Selected Cancers (with 95% Confidence Interval)
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table 1 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Table 1 shows Types of Cancer Included in Composite Cancer Incidence Rate (19 total)
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 1 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Table 1 shows Types of Cancer Included in Composite Cancer Incidence Rate (19 total)
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Figure 1 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 1 shows a map of U.S. counties contained in our analysis of composite cancer incidence according to their respective time zones (n = 2853).
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure 1 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 1 shows a map of U.S. counties contained in our analysis of composite cancer incidence according to their respective time zones (n = 2853).
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table 4 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Table 4 shows sources for data.
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 4 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Table 4 shows sources for data.
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Figure 7 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 7 shows the linear approximation result of incidence by relative position for four of the most prevalent cancers, with 95% bootstrap confidence band.
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure 7 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 7 shows the linear approximation result of incidence by relative position for four of the most prevalent cancers, with 95% bootstrap confidence band.
- Open Access
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Figure 3 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 3 shows maps of cancer incidence rate by county for most prevalent cancer.
- 7 February 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure 3 from Longitudinal Position and Cancer Risk in the United States Revisited
Supplementary Figure 3 shows maps of cancer incidence rate by county for most prevalent cancer.