112: add numerical tolerance options

[danielinteractive]

closes #112

[github-actions]

Code Coverage Summary

Filename                     Stmts    Miss  Cover    Missing
-------------------------  -------  ------  -------  ------------
R/bias.R                        34       0  100.00%
R/find_data.R                    3       0  100.00%
R/predict_couterfactual.R       77       0  100.00%
R/prediction_cf.R               22       0  100.00%
R/robin_glm.R                   49       1  97.96%   40
R/robin_lm.R                    28       0  100.00%
R/surv_effect.R                 67       0  100.00%
R/survival_cov_adj.R           146       0  100.00%
R/survival_score.R             294       0  100.00%
R/survival.R                   345       1  99.71%   603
R/treatment_effect.R           101       1  99.01%   51
R/utils.R                      204       3  98.53%   83, 115, 119
R/variance_anhecova.R           44       0  100.00%
R/variance_hc.R                 10       0  100.00%
TOTAL                         1424       6  99.58%

Diff against main

Filename        Stmts    Miss  Cover
------------  -------  ------  -------
R/survival.R      +28       0  +0.03%
TOTAL             +28       0  +0.01%

Results for commit: acbf242

Minimum allowed coverage is 80%

♻️ This comment has been updated with latest results

[github-actions]

Unit Tests Summary

  1 files   13 suites   9s ⏱️
142 tests  96 ✅ 46 💤 0 ❌
348 runs  284 ✅ 64 💤 0 ❌

Results for commit acbf242.

♻️ This comment has been updated with latest results.

[github-actions]

Unit Test Performance Difference

Test Suite	$Status$	Time on main	$±Time$	$±Tests$	$±Skipped$	$±Failures$	$±Errors$
survival	💚	$7.94$	$-1.99$	$+7$	$0$	$0$	$0$

Additional test case details

Test Suite	$Status$	Time on main	$±Time$	Test Case
survival	👶		$+0.02$	h_log_hr_est_via_score_passes_control_to_uniroot
survival	👶		$+0.21$	robin_surv_gives_the_same_estimate_as_coxph
survival	👶		$+0.02$	surv_control_works_as_expected

Results for commit bb55a97

♻️ This comment has been updated with latest results.

[clarkliming]

@danielinteractive may I ask why changing the control will lead to such difference?

[danielinteractive]

Before the control epsilon for the uniroot was too large, therefore we did not find the actual root of the score function, i.e. the HR estimate was not really correct.