Merge pull request #146 from junder873/flexible-below-statistics

Internal adjustments to below statistics to increase flexibility and necessary changes to standardization to match
jmboehm · Feb 15, 2024 · c53fcdb · c53fcdb · junder873 · Feb 15, 2024
2 parents 8a1f0ac + d26d7e2
commit c53fcdb
Show file tree

Hide file tree

Showing 10 changed files with 254 additions and 31 deletions.
diff --git a/Project.toml b/Project.toml
@@ -1,7 +1,7 @@
 name = "RegressionTables"
 uuid = "d519eb52-b820-54da-95a6-98e1306fdade"
 authors = ["Johannes Boehm <[email protected]>"]
-version = "0.6.2"
+version = "0.7.0"
 
 [deps]
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"

diff --git a/docs/src/api.md b/docs/src/api.md
@@ -71,7 +71,6 @@ RegressionTables.reorder_nms_list
 RegressionTables.drop_names!
 RegressionTables.add_blank
 RegressionTables.missing_vars
-RegressionTables.other_stats
 RegressionTables.add_element!
 ```
 
@@ -83,4 +82,25 @@ This section describes how different types are displayed. Throughout this packag
 
 ```@docs
 Base.repr
+```
+
+## New RegressionModel Types
+
+This package is designed to be generally compatible with the [RegressionModel abstraction](https://juliastats.org/StatsBase.jl/latest/statmodels/). It has special conditions defined around four commonly used packages ([FixedEffectModels.jl](https://github.com/matthieugomez/FixedEffectModels.jl), [GLM.jl](https://github.com/JuliaStats/GLM.jl), [GLFixedEffectModels.jl](https://github.com/jmboehm/GLFixedEffectModels.jl) and [MixedModels.jl](https://github.com/JuliaStats/MixedModels.jl)). It is possible to add new models to this list, either by creating an extension for this package or by creating the necessary items in an independent package.
+
+For any new `RegressionModel`, there may be a need to define the following functions for the package to work correctly. Many of these will work without any issues if following the StatsModels API, and many of the others are useful for customizing how the regression result is displayed. It is also possible to redefine how [`RegressionTables.AbstractRegressionStatistic`](@ref) are displayed.
+
+```@docs
+RegressionTables._formula
+RegressionTables._responsename
+RegressionTables._coefnames
+RegressionTables._coef
+RegressionTables._stderror
+RegressionTables._dof_residual
+RegressionTables._pvalue
+RegressionTables.other_stats
+RegressionTables.default_regression_statistics(::RegressionModel)
+RegressionTables.can_standardize
+RegressionTables.standardize_coef_values
+RegressionTables.RegressionType
 ```
diff --git a/docs/src/customization.md b/docs/src/customization.md
@@ -66,6 +66,7 @@ RegressionTables.default_regression_statistics
 RegressionTables.default_print_randomeffects
 RegressionTables.default_print_clusters
 RegressionTables.default_use_relabeled_values
+RegressionTables.default_confint_level
 ```
 
 ## Other Defaults

diff --git a/docs/src/examples.md b/docs/src/examples.md
@@ -176,6 +176,8 @@ Within-R2                                0.642      0.598        0.391
 
 ### ConfInt (Confidence Interval)
 
+Confidence level defaults to the 95th percentile:
+
 ```jldoctest
 regtable(rr1,rr2,rr3,rr4; below_statistic = ConfInt)
 
@@ -209,6 +211,41 @@ Within-R2                                             0.642             0.598
 ------------------------------------------------------------------------------------------------
 ```
 
+Set the Confidence Interval level either by setting [`RegressionTables.default_confint_level`](@ref) or by adjusting the `confint_level` keyword argument
+
+```jldoctest
+regtable(rr1,rr2,rr3,rr4; below_statistic = ConfInt, confint_level=0.9, align=:c)
+
+# output
+
+ 
+-------------------------------------------------------------------------------------------------
+                                               SepalLength                          SepalWidth
+                           ---------------------------------------------------   ----------------
+                                 (1)               (2)               (3)                (4)
+-------------------------------------------------------------------------------------------------
+(Intercept)                    6.526***
+                            (5.734, 7.319)
+SepalWidth                      -0.223          0.432***          0.516***
+                           (-0.480, 0.033)   (0.297, 0.567)    (0.345, 0.688)
+PetalLength                                     0.776***          0.723***            -0.188*
+                                             (0.669, 0.882)    (0.510, 0.937)    (-0.326, -0.049)
+PetalWidth                                                         -0.625            0.626***
+                                                              (-1.211, -0.038)    (0.421, 0.830)
+PetalLength & PetalWidth                                            0.066
+                                                               (-0.045, 0.177)
+SepalLength                                                                          0.378***
+                                                                                  (0.269, 0.486)
+-------------------------------------------------------------------------------------------------
+Species Fixed Effects                              Yes               Yes                Yes
+isSmall Fixed Effects                                                Yes
+-------------------------------------------------------------------------------------------------
+N                                150               150               150                150
+R2                              0.014             0.863             0.868              0.635
+Within-R2                                         0.642             0.598              0.391
+-------------------------------------------------------------------------------------------------
+```
+
 ## Standard Errors on same line as coefficient
 
 ```jldoctest
@@ -1240,6 +1277,39 @@ Pseudo R2                0.006       0.811       0.347       0.297
 ------------------------------------------------------------------
 ```
 
+It is also possible to standardize some coefficients and not others
+
+```jldoctest
+lm1 = lm(@formula(SepalLength ~ SepalWidth), df);
+regtable(lm1, lm1, rr7, rr7; standardize_coef=[false, true, false, true])
+
+# output
+
+ 
+---------------------------------------------------------
+                  SepalLength              isSmall
+              -------------------   ---------------------
+                   (1)        (2)         (3)         (4)
+---------------------------------------------------------
+(Intercept)   6.526***   7.881***   10.189***   21.894***
+               (0.479)    (0.578)     (2.607)     (5.601)
+SepalWidth      -0.223     -0.118
+               (0.155)    (0.082)
+SepalLength                         -3.519***   -6.260***
+                                      (0.697)     (1.240)
+PetalLength                          3.580***   13.578***
+                                      (0.708)     (2.686)
+PetalWidth                           -3.637**    -5.957**
+                                      (1.127)     (1.846)
+---------------------------------------------------------
+Estimator          OLS        OLS    Binomial    Binomial
+---------------------------------------------------------
+N                  150        150         150         150
+R2               0.014      0.014
+Pseudo R2        0.006      0.006       0.297       0.297
+---------------------------------------------------------
+```
+
 ## Show Clustered Standard Errors
 
 Displays whether or not the standard errors are clustered and in what ways.

diff --git a/docs/src/regression_statistics.md b/docs/src/regression_statistics.md
@@ -28,7 +28,6 @@ Filter = t -> typeof(t) === DataType && t <: RegressionTables.AbstractUnderStati
 
 ```@docs
 RegressionTables.CoefValue
-RegressionTables.RegressionType
 RegressionTables.HasControls
 RegressionTables.RegressionNumbers
 RegressionTables.FixedEffectValue

diff --git a/ext/RegressionTablesGLMExt.jl b/ext/RegressionTablesGLMExt.jl
@@ -7,8 +7,12 @@ RegressionTables.default_regression_statistics(rr::StatsModels.TableRegressionMo
 
 RegressionTables.RegressionType(x::StatsModels.TableRegressionModel{T}) where {T<:GLM.AbstractGLM} = RegressionType(x.model)
 RegressionTables.RegressionType(x::StatsModels.TableRegressionModel{T}) where {T<:LinearModel} = RegressionType(x.model)
-RegressionTables.standardize_coef_values(x::StatsModels.TableRegressionModel, coefvalues, coefstderrors) =
-    RegressionTables.standardize_coef_values(std(modelmatrix(x), dims=1)[1, :], std(response(x)), coefvalues, coefstderrors)
+
+# k is which coefficient or standard error to standardize
+RegressionTables.standardize_coef_values(x::StatsModels.TableRegressionModel, val, k) =
+    RegressionTables.standardize_coef_values(std(modelmatrix(x)[:, k]), std(response(x)), val)
+
+RegressionTables.can_standardize(x::StatsModels.TableRegressionModel) = true
 
 RegressionTables.RegressionType(x::LinearModel) = RegressionType(Normal())
 RegressionTables.RegressionType(x::GLM.LmResp) = RegressionType(Normal())

diff --git a/ext/RegressionTablesMixedModelsExt.jl b/ext/RegressionTablesMixedModelsExt.jl
@@ -26,8 +26,11 @@ function RegressionTables._coefnames(x::MixedModel)
     out
 end
 
-RegressionTables.standardize_coef_values(x::MixedModel, coefvalues, coefstderrors) =
-    RegressionTables.standardize_coef_values(std(modelmatrix(x), dims=1)[1, :], std(response(x)), coefvalues, coefstderrors)
+# k is which coefficient or standard error to standardize
+RegressionTables.standardize_coef_values(x::MixedModel, val, k) =
+    RegressionTables.standardize_coef_values(std(modelmatrix(x)[:, k]), std(response(x)), val)
+
+RegressionTables.can_standardize(x::MixedModel) = true
 
 function RegressionTables.other_stats(x::MixedModel, s::Symbol)
     if s == :randomeffects

diff --git a/src/RegressionStatistics.jl b/src/RegressionStatistics.jl
@@ -462,44 +462,57 @@ abstract type AbstractUnderStatistic <: AbstractRegressionData end
     struct TStat <: AbstractUnderStatistic
         val::Float64
     end
-    TStat(se, coef, dof=0)
+    TStat(rr::RegressionModel, k::Int; vargs...)
 
 The t-statistic of a coefficient.
 """
 struct TStat <: AbstractUnderStatistic
     val::Float64
 end
-TStat(se, coef, dof=0) = TStat(coef / se)
+TStat(rr::RegressionModel, k::Int; vargs...) = TStat(_coef(rr)[k] / _stderror(rr)[k])
 
 """
     struct StdError <: AbstractUnderStatistic
         val::Float64
     end
-    StdError(se, coef, dof=0)
+    StdError(rr::RegressionModel, k::Int; standardize=false, vargs...)
 
 The standard error of a coefficient.
 """
 struct StdError <: AbstractUnderStatistic
     val::Float64
 end
-StdError(se, coef, dof=0) = StdError(se)
+function StdError(rr::RegressionModel, k::Int; standardize=false, vargs...)
+    if standardize
+        StdError(standardize_coef_values(rr, _stderror(rr)[k], k))
+    else
+        StdError(_stderror(rr)[k])
+    end
+end
 
 """
     struct ConfInt <: AbstractUnderStatistic
         val::Tuple{Float64, Float64}
     end
-    ConfInt(se, coef, dof; level=default_confint_level())
+    ConfInt(rr::RegressionModel, k::Int; level=0.95, standardize=false, vargs...)
 
 The confidence interval of a coefficient. The default confidence
 level is 95% (can be changed by setting 
-`RegressionTable.default_confint_level() = 0.90` or similar).
+`RegressionTable.default_confint_level(render::AbstractRenderType, rr) = 0.90` or similar).
 """
 struct ConfInt <: AbstractUnderStatistic
     val::Tuple{Float64, Float64}
 end
-default_confint_level() = 0.95
-function ConfInt(se, coef, dof; level=default_confint_level())
+
+function ConfInt(rr::RegressionModel, k::Int; level=0.95, standardize=false, vargs...)
     @assert 0 < level < 1 "Confidence level must be between 0 and 1"
+    se = _stderror(rr)[k]
+    coef = _coef(rr)[k]
+    dof = _dof_residual(rr)
+    if standardize
+        se = standardize_coef_values(rr, se, k)
+        coef = standardize_coef_values(rr, coef, k)
+    end
     scale = quantile(TDist(dof), 1 - (1-level) / 2)
     ConfInt((coef - scale * se, coef + scale * se))
 end
@@ -519,6 +532,14 @@ struct CoefValue <: AbstractRegressionData
     val::Float64
     pvalue::Float64
 end
+function CoefValue(rr::RegressionModel, k::Int; standardize=false, vargs...)
+    val = _coef(rr)[k]
+    p = _pvalue(rr)[k]
+    if standardize
+        val = standardize_coef_values(rr, val, k)
+    end
+    CoefValue(val, p)
+end
 value(x::CoefValue) = x.val
 value_pvalue(x::CoefValue) = x.pvalue
 value_pvalue(x::Missing) = missing