Convert summary table of a fixed or group sequential design object to a gt object

Usage

as_gt(x, ...)

# S3 method for class 'fixed_design'
as_gt(x, title = NULL, footnote = NULL, ...)

# S3 method for class 'gs_design'
as_gt(
  x,
  title = NULL,
  subtitle = NULL,
  colname_spanner = "Cumulative boundary crossing probability",
  colname_spannersub = c("Alternate hypothesis", "Null hypothesis"),
  footnote = NULL,
  display_bound = c("Efficacy", "Futility"),
  display_columns = NULL,
  display_inf_bound = FALSE,
  ...
)

Arguments

x: A summary object of a fixed or group sequential design.
...: Additional arguments (not used).
title: A string to specify the title of the gt table.
footnote: A list containing content, location, and attr. content is a vector of string to specify the footnote text; location is a vector of string to specify the locations to put the superscript of the footnote index; attr is a vector of string to specify the attributes of the footnotes, for example, c("colname", "title", "subtitle", "analysis", "spanner"); users can use the functions in the gt package to customize the table. To disable footnotes, use footnote = FALSE.
subtitle: A string to specify the subtitle of the gt table.
colname_spanner: A string to specify the spanner of the gt table.
colname_spannersub: A vector of strings to specify the spanner details of the gt table.
display_bound: A vector of strings specifying the label of the bounds. The default is c("Efficacy", "Futility").
display_columns: A vector of strings specifying the variables to be displayed in the summary table.
display_inf_bound: Logical, whether to display the +/-inf bound.

Value

A gt_tbl object.

Examples

# Fixed design examples ----

library(dplyr)
#> 
#> Attaching package: ‘dplyr’
#> The following objects are masked from ‘package:stats’:
#> 
#>     filter, lag
#> The following objects are masked from ‘package:base’:
#> 
#>     intersect, setdiff, setequal, union

# Enrollment rate
enroll_rate <- define_enroll_rate(
  duration = 18,
  rate = 20
)

# Failure rates
fail_rate <- define_fail_rate(
  duration = c(4, 100),
  fail_rate = log(2) / 12,
  dropout_rate = .001,
  hr = c(1, .6)
)

# Study duration in months
study_duration <- 36

# Experimental / Control randomization ratio
ratio <- 1

# 1-sided Type I error
alpha <- 0.025

# Type II error (1 - power)
beta <- 0.1

# Example 1 ----
fixed_design_ahr(
  alpha = alpha, power = 1 - beta,
  enroll_rate = enroll_rate, fail_rate = fail_rate,
  study_duration = study_duration, ratio = ratio
) %>%
  summary() %>%
  as_gt()


  Fixed Design under AHR Method¹
    
Design
      N
      Events
      Time
      Bound
      alpha
      Power
    
Average hazard ratio
463.078
324.7077
36
1.959964
0.025
0.9
¹ Power computed with average hazard ratio method.
    

# Example 2 ----
fixed_design_fh(
  alpha = alpha, power = 1 - beta,
  enroll_rate = enroll_rate, fail_rate = fail_rate,
  study_duration = study_duration, ratio = ratio
) %>%
  summary() %>%
  as_gt()


  Fixed Design under Fleming-Harrington Method¹
    
Design
      N
      Events
      Time
      Bound
      alpha
      Power
    
Fleming-Harrington FH(0, 0) (logrank)
458.3509
321.3931
36
1.959964
0.025
0.9
¹ Power for Fleming-Harrington test  FH(0, 0) (logrank) using method of Yung and Liu.
    
# \donttest{
# Group sequential design examples ---

library(dplyr)
# Example 1 ----
# The default output

gs_design_ahr() %>%
  summary() %>%
  as_gt()


  Bound summary for AHR design
    
AHR approximations of ~HR at bound
    
Bound
      Z
      Nominal p¹
      ~HR at bound²
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 36 N: 476 Events: 291.9 AHR: 0.68 Information fraction: 1
    
Efficacy
1.96
0.025
0.795
0.9
0.025
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Approximate hazard ratio to cross bound.
    

gs_power_ahr(lpar = list(sf = gsDesign::sfLDOF, total_spend = 0.1)) %>%
  summary() %>%
  as_gt()


  Bound summary for AHR design
    
AHR approximations of ~HR at bound
    
Bound
      Z
      Nominal p¹
      ~HR at bound²
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6
    
Futility
-1.17
0.8792
1.5392
0.0349
0.1208
Efficacy
2.67
0.0038
0.3743
0.0231
0.0038
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.74 Information fraction: 0.8
    
Futility
-0.66
0.7462
1.2359
0.0668
0.2655
Efficacy
2.29
0.0110
0.4812
0.0897
0.0122
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1
    
Futility
-0.23
0.5897
1.0670
0.1008
0.4303
Efficacy
2.03
0.0211
0.5595
0.2070
0.0250
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Approximate hazard ratio to cross bound.
    

gs_design_wlr() %>%
  summary() %>%
  as_gt()


  Bound summary for WLR design
    
WLR approximation of ~wHR at bound
    
Bound
      Z
      Nominal p¹
      ~wHR at bound²
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 36 N: 471.1 Events: 289 AHR: 0.68 Information fraction: 1³
    
Efficacy
1.96
0.025
0.7941
0.9
0.025
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Approximate hazard ratio to cross bound.
    
³ wAHR is the weighted AHR.
    

gs_power_wlr(lpar = list(sf = gsDesign::sfLDOF, total_spend = 0.1)) %>%
  summary() %>%
  as_gt()


  Bound summary for WLR design
    
WLR approximation of ~wHR at bound
    
Bound
      Z
      Nominal p¹
      ~wHR at bound²
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6³
    
Futility
-1.17
0.8798
1.5353
0.0341
0.1202
Efficacy
2.68
0.0037
0.3765
0.0217
0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8³
    
Futility
-0.66
0.7452
1.2319
0.0664
0.2664
Efficacy
2.29
0.0110
0.4846
0.0886
0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1³
    
Futility
-0.22
0.5881
1.0650
0.1002
0.4319
Efficacy
2.03
0.0212
0.5631
0.2071
0.0250
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Approximate hazard ratio to cross bound.
    
³ wAHR is the weighted AHR.
    

gs_power_combo() %>%
  summary() %>%
  as_gt()


  Bound summary for MaxCombo design
    
MaxCombo approximation
    
Bound
      Z
      Nominal p¹
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 12 N: 500 Events: 107.4 AHR: 0.84 Event fraction: 0.32²
    
Futility
-1
0.8413
0.0293
0.0000
Efficacy
3
0.0013
0.0175
0.0013
Analysis: 2 Time: 24 N: 500 Events: 246.3 AHR: 0.72 Event fraction: 0.74²
    
Futility
0
0.5000
0.0314
0.0000
Efficacy
2
0.0228
0.7261
0.0233
Analysis: 3 Time: 36 N: 500 Events: 331.3 AHR: 0.68 Event fraction: 1²
    
Futility
1
0.1587
0.0326
0.0000
Efficacy
1
0.1587
0.9674
0.1956
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² EF is event fraction. AHR is under regular weighted log rank test.
    

gs_design_rd() %>%
  summary() %>%
  as_gt()


  Bound summary of Binary Endpoint
    
measured by risk difference
    
Bound
      Z
      Nominal p¹
      ~Risk difference at bound
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 N: 2423.1 Risk difference: 0.05 Information fraction: 1
    
Efficacy
1.96
0.025
0.0302
0.9
0.025
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    

gs_power_rd() %>%
  summary() %>%
  as_gt()


  Bound summary of Binary Endpoint
    
measured by risk difference
    
Bound
      Z
      Nominal p¹
      ~Risk difference at bound
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 N: 40 Risk difference: 0.05 Information fraction: 0.67
    
Futility
-1.28
0.9000
-0.1537
0.0444
0.1000
Efficacy
3.71
0.0001
0.4448
0.0005
0.0001
Analysis: 2 N: 50 Risk difference: 0.05 Information fraction: 0.83
    
Efficacy
2.51
0.0060
0.2693
0.0204
0.0060
Analysis: 3 N: 60 Risk difference: 0.05 Information fraction: 1
    
Efficacy
1.99
0.0231
0.1951
0.0705
² 0.0238
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Cumulative alpha for final analysis (0.0238) is less than the full alpha (0.025) when the futility bound is non-binding. The smaller value subtracts the probability of crossing a futility bound before crossing an efficacy bound at a later analysis (0.025 - 0.0012 = 0.0238) under the null hypothesis.
    

# Example 2 ----
# Usage of title = ..., subtitle = ...
# to edit the title/subtitle
gs_power_wlr(lpar = list(sf = gsDesign::sfLDOF, total_spend = 0.1)) %>%
  summary() %>%
  as_gt(
    title = "Bound Summary",
    subtitle = "from gs_power_wlr"
  )


  Bound Summary
    
from gs_power_wlr
    
Bound
      Z
      Nominal p¹
      ~wHR at bound²
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6³
    
Futility
-1.17
0.8798
1.5353
0.0341
0.1202
Efficacy
2.68
0.0037
0.3765
0.0217
0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8³
    
Futility
-0.66
0.7452
1.2319
0.0664
0.2664
Efficacy
2.29
0.0110
0.4846
0.0886
0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1³
    
Futility
-0.22
0.5881
1.0650
0.1002
0.4319
Efficacy
2.03
0.0212
0.5631
0.2071
0.0250
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Approximate hazard ratio to cross bound.
    
³ wAHR is the weighted AHR.
    

# Example 3 ----
# Usage of colname_spanner = ..., colname_spannersub = ...
# to edit the spanner and its sub-spanner
gs_power_wlr(lpar = list(sf = gsDesign::sfLDOF, total_spend = 0.1)) %>%
  summary() %>%
  as_gt(
    colname_spanner = "Cumulative probability to cross boundaries",
    colname_spannersub = c("under H1", "under H0")
  )


  Bound summary for WLR design
    
WLR approximation of ~wHR at bound
    
Bound
      Z
      Nominal p¹
      ~wHR at bound²
      
        Cumulative probability to cross boundaries
      
    
under H1
      under H0
    
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6³
    
Futility
-1.17
0.8798
1.5353
0.0341
0.1202
Efficacy
2.68
0.0037
0.3765
0.0217
0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8³
    
Futility
-0.66
0.7452
1.2319
0.0664
0.2664
Efficacy
2.29
0.0110
0.4846
0.0886
0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1³
    
Futility
-0.22
0.5881
1.0650
0.1002
0.4319
Efficacy
2.03
0.0212
0.5631
0.2071
0.0250
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Approximate hazard ratio to cross bound.
    
³ wAHR is the weighted AHR.
    

# Example 4 ----
# Usage of footnote = ...
# to edit the footnote
gs_power_wlr(lpar = list(sf = gsDesign::sfLDOF, total_spend = 0.1)) %>%
  summary() %>%
  as_gt(
    footnote = list(
      content = c(
        "approximate weighted hazard ratio to cross bound.",
        "wAHR is the weighted AHR.",
        "the crossing probability.",
        "this table is generated by gs_power_wlr."
      ),
      location = c("~wHR at bound", NA, NA, NA),
      attr = c("colname", "analysis", "spanner", "title")
    )
  )


  Bound summary for WLR design¹
    
WLR approximation of ~wHR at bound
    
Bound
      Z
      Nominal p
      ~wHR at bound³
      
        Cumulative boundary crossing probability²
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6⁴
    
Futility
-1.17
0.8798
1.5353
0.0341
0.1202
Efficacy
2.68
0.0037
0.3765
0.0217
0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8⁴
    
Futility
-0.66
0.7452
1.2319
0.0664
0.2664
Efficacy
2.29
0.0110
0.4846
0.0886
0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1⁴
    
Futility
-0.22
0.5881
1.0650
0.1002
0.4319
Efficacy
2.03
0.0212
0.5631
0.2071
0.0250
¹ this table is generated by gs_power_wlr.
    
² the crossing probability.
    
³ approximate weighted hazard ratio to cross bound.
    
⁴ wAHR is the weighted AHR.
    

# Example 5 ----
# Usage of display_bound = ...
# to either show efficacy bound or futility bound, or both(default)
gs_power_wlr(lpar = list(sf = gsDesign::sfLDOF, total_spend = 0.1)) %>%
  summary() %>%
  as_gt(display_bound = "Efficacy")


  Bound summary for WLR design
    
WLR approximation of ~wHR at bound
    
Bound
      Z
      Nominal p¹
      ~wHR at bound²
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6³
    
Efficacy
2.68
0.0037
0.3765
0.0217
0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8³
    
Efficacy
2.29
0.0110
0.4846
0.0886
0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1³
    
Efficacy
2.03
0.0212
0.5631
0.2071
0.0250
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² Approximate hazard ratio to cross bound.
    
³ wAHR is the weighted AHR.
    

# Example 6 ----
# Usage of display_columns = ...
# to select the columns to display in the summary table
gs_power_wlr(lpar = list(sf = gsDesign::sfLDOF, total_spend = 0.1)) %>%
  summary() %>%
  as_gt(display_columns = c("Analysis", "Bound", "Nominal p", "Z", "Probability"))


  Bound summary for WLR design
    
WLR approximation of ~wHR at bound
    
Bound
      Nominal p¹
      Z
      
        Cumulative boundary crossing probability
      
    
Alternate hypothesis
      Null hypothesis
    
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6²
    
Futility
0.8798
-1.17
0.0341
0.1202
Efficacy
0.0037
2.68
0.0217
0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8²
    
Futility
0.7452
-0.66
0.0664
0.2664
Efficacy
0.0110
2.29
0.0886
0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1²
    
Futility
0.5881
-0.22
0.1002
0.4319
Efficacy
0.0212
2.03
0.2071
0.0250
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
    
² wAHR is the weighted AHR.
    
# }

Design	N	Events	Time	Bound	alpha	Power
Fixed Design under AHR Method¹
Average hazard ratio	463.078	324.7077	36	1.959964	0.025	0.9
¹ Power computed with average hazard ratio method.

Design	N	Events	Time	Bound	alpha	Power
Fixed Design under Fleming-Harrington Method¹
Fleming-Harrington FH(0, 0) (logrank)	458.3509	321.3931	36	1.959964	0.025	0.9
¹ Power for Fleming-Harrington test FH(0, 0) (logrank) using method of Yung and Liu.

Bound	Z	Nominal p¹	~HR at bound²	Cumulative boundary crossing probability
Bound summary for AHR design
AHR approximations of ~HR at bound
Bound	Z	Nominal p¹	~HR at bound²	Alternate hypothesis	Null hypothesis
Analysis: 1 Time: 36 N: 476 Events: 291.9 AHR: 0.68 Information fraction: 1
Efficacy	1.96	0.025	0.795	0.9	0.025
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
² Approximate hazard ratio to cross bound.

Bound	Z	Nominal p¹	~wHR at bound²	Cumulative boundary crossing probability
Bound summary for WLR design
WLR approximation of ~wHR at bound
Bound	Z	Nominal p¹	~wHR at bound²	Alternate hypothesis	Null hypothesis
Analysis: 1 Time: 36 N: 471.1 Events: 289 AHR: 0.68 Information fraction: 1³
Efficacy	1.96	0.025	0.7941	0.9	0.025
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
² Approximate hazard ratio to cross bound.
³ wAHR is the weighted AHR.

Bound	Z	Nominal p¹	Cumulative boundary crossing probability
Bound summary for MaxCombo design
MaxCombo approximation
Bound	Z	Nominal p¹	Alternate hypothesis	Null hypothesis
Analysis: 1 Time: 12 N: 500 Events: 107.4 AHR: 0.84 Event fraction: 0.32²
Futility	-1	0.8413	0.0293	0.0000
Efficacy	3	0.0013	0.0175	0.0013
Analysis: 2 Time: 24 N: 500 Events: 246.3 AHR: 0.72 Event fraction: 0.74²
Futility	0	0.5000	0.0314	0.0000
Efficacy	2	0.0228	0.7261	0.0233
Analysis: 3 Time: 36 N: 500 Events: 331.3 AHR: 0.68 Event fraction: 1²
Futility	1	0.1587	0.0326	0.0000
Efficacy	1	0.1587	0.9674	0.1956
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
² EF is event fraction. AHR is under regular weighted log rank test.

Bound	Z	Nominal p¹	~Risk difference at bound	Cumulative boundary crossing probability
Bound summary of Binary Endpoint
measured by risk difference
Bound	Z	Nominal p¹	~Risk difference at bound	Alternate hypothesis	Null hypothesis
Analysis: 1 N: 2423.1 Risk difference: 0.05 Information fraction: 1
Efficacy	1.96	0.025	0.0302	0.9	0.025
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.

Bound	Z	Nominal p¹	~wHR at bound²	Cumulative boundary crossing probability
Bound Summary
from gs_power_wlr
Bound	Z	Nominal p¹	~wHR at bound²	Alternate hypothesis	Null hypothesis
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6³
Futility	-1.17	0.8798	1.5353	0.0341	0.1202
Efficacy	2.68	0.0037	0.3765	0.0217	0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8³
Futility	-0.66	0.7452	1.2319	0.0664	0.2664
Efficacy	2.29	0.0110	0.4846	0.0886	0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1³
Futility	-0.22	0.5881	1.0650	0.1002	0.4319
Efficacy	2.03	0.0212	0.5631	0.2071	0.0250
¹ One-sided p-value for experimental vs control treatment. Value < 0.5 favors experimental, > 0.5 favors control.
² Approximate hazard ratio to cross bound.
³ wAHR is the weighted AHR.

Bound	Z	Nominal p	~wHR at bound³	Cumulative boundary crossing probability²
Bound summary for WLR design¹
WLR approximation of ~wHR at bound
Bound	Z	Nominal p	~wHR at bound³	Alternate hypothesis	Null hypothesis
Analysis: 1 Time: 14.9 N: 108 Events: 30 AHR: 0.79 Information fraction: 0.6⁴
Futility	-1.17	0.8798	1.5353	0.0341	0.1202
Efficacy	2.68	0.0037	0.3765	0.0217	0.0037
Analysis: 2 Time: 19.2 N: 108 Events: 40 AHR: 0.75 Information fraction: 0.8⁴
Futility	-0.66	0.7452	1.2319	0.0664	0.2664
Efficacy	2.29	0.0110	0.4846	0.0886	0.0121
Analysis: 3 Time: 24.5 N: 108 Events: 50 AHR: 0.71 Information fraction: 1⁴
Futility	-0.22	0.5881	1.0650	0.1002	0.4319
Efficacy	2.03	0.0212	0.5631	0.2071	0.0250
¹ this table is generated by gs_power_wlr.
² the crossing probability.
³ approximate weighted hazard ratio to cross bound.
⁴ wAHR is the weighted AHR.