diff --git a/Project.toml b/Project.toml
index ec3193c..7750b76 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,6 +1,6 @@
 name = "Lasso"
 uuid = "b4fcebef-c861-5a0f-a7e2-ba9dc32b180a"
-version = "0.4.1"
+version = "0.5.0"
 
 [deps]
 DSP = "717857b8-e6f2-59f4-9121-6e50c889abd2"
@@ -15,19 +15,18 @@ StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 StatsModels = "3eaba693-59b7-5ba5-a881-562e759f1c8d"
 
 [compat]
-GLM = "1.2"
-StatsModels = "0.4, 0.5"
+GLM = "1.3"
+StatsModels = "0.6"
 julia = "0.7, 1"
 
 [extras]
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 GLMNet = "8d5ece8b-de18-5317-b113-243142960cc6"
-InteractiveUtils = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = ["CSV", "InteractiveUtils", "LinearAlgebra", "GLMNet", "DataFrames", "Random", "SparseArrays", "Test"]
+test = ["CSV", "LinearAlgebra", "GLMNet", "DataFrames", "Random", "SparseArrays", "Test"]
diff --git a/docs/src/index.md b/docs/src/index.md
index 0d3a3a1..237ec08 100644
--- a/docs/src/index.md
+++ b/docs/src/index.md
@@ -41,9 +41,9 @@ julia> data = DataFrame(X=[1,2,3], Y=[2,4,7])
 │ 3   │ 3     │ 7     │
 
 julia> m = fit(LassoModel, @formula(Y ~ X), data)
-StatsModels.DataFrameRegressionModel{LassoModel{LinearModel{GLM.LmResp{Array{Float64,1}},GLM.DensePredQR{Float64}}},Array{Float64,2}}
+StatsModels.TableRegressionModel{LassoModel{LinearModel{GLM.LmResp{Array{Float64,1}},GLM.DensePredQR{Float64}}},Array{Float64,2}}
 
-Formula: Y ~ +X
+Y ~ X
 
 Coefficients:
 ──────────────────────────────────────────────────────────────────
diff --git a/docs/src/lasso.md b/docs/src/lasso.md
index 3d20d90..ddab76e 100644
--- a/docs/src/lasso.md
+++ b/docs/src/lasso.md
@@ -73,9 +73,9 @@ julia> data = DataFrame(X=[1,2,3], Y=[2,4,7])
 │ 3   │ 3     │ 7     │
 
 julia> m = fit(LassoModel, @formula(Y ~ X), data; select=MinCVmse(Kfold(3,2)))
-StatsModels.DataFrameRegressionModel{LassoModel{LinearModel{GLM.LmResp{Array{Float64,1}},GLM.DensePredQR{Float64}}},Array{Float64,2}}
+StatsModels.TableRegressionModel{LassoModel{LinearModel{GLM.LmResp{Array{Float64,1}},GLM.DensePredQR{Float64}}},Array{Float64,2}}
 
-Formula: Y ~ +X
+Y ~ X
 
 Coefficients:
 ──────────────────────────────────────────────────────────────────
diff --git a/src/segselect.jl b/src/segselect.jl
index 41c641f..1f63a8a 100644
--- a/src/segselect.jl
+++ b/src/segselect.jl
@@ -284,7 +284,7 @@ newglm(m::GeneralizedLinearModel, pp) = GeneralizedLinearModel(m.rr, pp, true)
 # don't add an intercept when using a @formula because we use the intercept keyword arg to add an intercept
 StatsModels.drop_intercept(::Type{R}) where R<:RegularizedModel = true
 
-StatsModels.@delegate StatsModels.DataFrameRegressionModel.model [segselect, MinCVmse, MinCV1se]
+StatsModels.@delegate StatsModels.TableRegressionModel.model [segselect, MinCVmse, MinCV1se]
 for modeltype in (:LassoModel, :GammaLassoModel)
     @eval begin
         StatsModels.@delegate $modeltype.lpm [StatsBase.coef, StatsBase.confint,
diff --git a/test/gammalasso.jl b/test/gammalasso.jl
index d461b05..7d71aa8 100644
--- a/test/gammalasso.jl
+++ b/test/gammalasso.jl
@@ -41,7 +41,7 @@ Random.seed!(243214)
                 gcoefs = readcsvmat(joinpath(datapath,"gamlr.$family.$fitname.coefs.csv");types=[Float64 for i=1:100])
                 family = prms[1,Symbol("fit.family")]
                 γ = prms[1,Symbol("fit.gamma")]
-                λ = nothing #convert(Vector{Float64},fittable[Symbol("fit.lambda")]) # should be set to nothing evenatually
+                λ = nothing #convert(Vector{Float64},fittable[!, Symbol("fit.lambda")]) # should be set to nothing evenatually
 
                 # fit julia version
                 glp = fit(GammaLassoPath, X, y, dist, link; γ=γ, stopearly=false,
@@ -49,23 +49,23 @@ Random.seed!(243214)
                     standardize=false, standardizeω=false)
 
                 # compare
-                @test true==issimilarhead(glp.λ,fittable[Symbol("fit.lambda")];rtol=rtol)
-                @test true==issimilarhead(glp.b0,fittable[Symbol("fit.alpha")];rtol=rtol)
+                @test true==issimilarhead(glp.λ,fittable[!, Symbol("fit.lambda")];rtol=rtol)
+                @test true==issimilarhead(glp.b0,fittable[!, Symbol("fit.alpha")];rtol=rtol)
                 @test true==issimilarhead(convert(Matrix{Float64},glp.coefs'),gcoefs';rtol=rtol)
                 # we follow GLM.jl convention where deviance is scaled by nobs, while in gamlr it is not
-                @test true==issimilarhead(deviance(glp),fittable[Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
-                @test true==issimilarhead(deviance(glp,X,y),fittable[Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
+                @test true==issimilarhead(deviance(glp),fittable[!, Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
+                @test true==issimilarhead(deviance(glp,X,y),fittable[!, Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
                 # @test true==issimilarhead(round(df(glp)[2:end]),round(fittable[2:end,Symbol("fit.df")]))
-                @test true==issimilarhead(loglikelihood(glp),fittable[Symbol("fit.logLik")];rtol=rtol)
-                @test true==issimilarhead(aicc(glp),fittable[Symbol("fit.AICc")];rtol=rtol)
+                @test true==issimilarhead(loglikelihood(glp),fittable[!, Symbol("fit.logLik")];rtol=rtol)
+                @test true==issimilarhead(aicc(glp),fittable[!, Symbol("fit.AICc")];rtol=rtol)
 
                 # TODO: figure out why these are so off, maybe because most are corner solutions
                 # and stopping rules for lambda are different
                 # # what we really need all these stats for is that the AICc identifies the same minima:
-                # if argmin(aicc(glp)) != lastindex(aicc(glp)) && argmin(fittable[Symbol("fit.AICc")]) != lastindex(fittable[Symbol("fit.AICc")])
+                # if argmin(aicc(glp)) != lastindex(aicc(glp)) && argmin(fittable[!, Symbol("fit.AICc")]) != lastindex(fittable[!, Symbol("fit.AICc")])
                 #     # interior minima
                 #     println("comparing intereior AICc")
-                #     @test argmin(aicc(glp)) == argmin(fittable[Symbol("fit.AICc")])
+                #     @test argmin(aicc(glp)) == argmin(fittable[!, Symbol("fit.AICc")])
                 # end
 
                 # comparse CV, NOTE: this involves a random choice of train subsamples
@@ -116,7 +116,7 @@ end
 # gcoefs = readcsvmat(joinpath(datapath,"gamlr.$family.$fitname.coefs.csv");types=[Float64 for i=1:100])
 # family = prms[1,Symbol("fit.family")]
 # γ = prms[1,Symbol("fit.gamma")]
-# λ = nothing #convert(Vector{Float64},fittable[Symbol("fit.lambda")]) # should be set to nothing evenatually
+# λ = nothing #convert(Vector{Float64},fittable[!, Symbol("fit.lambda")]) # should be set to nothing evenatually
 #
 # # fit julia version
 # glp = fit(GammaLassoPath, X, y, dist, link; γ=γ, stopearly=false,
@@ -156,23 +156,23 @@ end
 # predict(m)
 #
 # # compare
-# @test true==issimilarhead(glp.λ,fittable[Symbol("fit.lambda")];rtol=rtol)
-# @test true==issimilarhead(glp.b0,fittable[Symbol("fit.alpha")];rtol=rtol)
+# @test true==issimilarhead(glp.λ,fittable[!, Symbol("fit.lambda")];rtol=rtol)
+# @test true==issimilarhead(glp.b0,fittable[!, Symbol("fit.alpha")];rtol=rtol)
 # @test true==issimilarhead(convert(Matrix{Float64},glp.coefs'),gcoefs';rtol=rtol)
 # # we follow GLM.jl convention where deviance is scaled by nobs, while in gamlr it is not
-# @test true==issimilarhead(deviance(glp),fittable[Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
-# @test true==issimilarhead(deviance(glp,X,y),fittable[Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
+# @test true==issimilarhead(deviance(glp),fittable[!, Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
+# @test true==issimilarhead(deviance(glp,X,y),fittable[!, Symbol("fit.deviance")]/nobs(glp);rtol=rtol)
 # # @test true==issimilarhead(round(df(glp)[2:end]),round(fittable[2:end,Symbol("fit.df")]))
-# @test true==issimilarhead(loglikelihood(glp),fittable[Symbol("fit.logLik")];rtol=rtol)
-# @test true==issimilarhead(aicc(glp),fittable[Symbol("fit.AICc")];rtol=rtol)
+# @test true==issimilarhead(loglikelihood(glp),fittable[!, Symbol("fit.logLik")];rtol=rtol)
+# @test true==issimilarhead(aicc(glp),fittable[!, Symbol("fit.AICc")];rtol=rtol)
 #
 # # TODO: figure out why these are so off, maybe because most are corner solutions
 # # and stopping rules for lambda are different
 # # # what we really need all these stats for is that the AICc identifies the same minima:
-# # if argmin(aicc(glp)) != lastindex(aicc(glp)) && argmin(fittable[Symbol("fit.AICc")]) != lastindex(fittable[Symbol("fit.AICc")])
+# # if argmin(aicc(glp)) != lastindex(aicc(glp)) && argmin(fittable[!, Symbol("fit.AICc")]) != lastindex(fittable[!, Symbol("fit.AICc")])
 # #     # interior minima
 # #     println("comparing intereior AICc")
-# #     @test argmin(aicc(glp)) == argmin(fittable[Symbol("fit.AICc")])
+# #     @test argmin(aicc(glp)) == argmin(fittable[!, Symbol("fit.AICc")])
 # # end
 #
 # # comparse CV, NOTE: this involves a random choice of train subsamples