Add Penalty, Regularized Least Squares and IPODRegression

[getzze]

Θ-IPOD Regression algorithm is based on "Outlier Detection Using Nonconvex Penalized Regression", 2011, Y. She, A.B. Owen

[codecov]

Codecov Report

Attention: Patch coverage is 85.40479% with 128 lines in your changes missing coverage. Please review.

Project coverage is 85.02%. Comparing base (b3ef64a) to head (0d3adee).
Report is 5 commits behind head on main.

Files with missing lines	Patch %	Lines
src/ipod.jl	80.66%	58 Missing ⚠️
src/penalties.jl	81.36%	30 Missing ⚠️
src/regularizedpred.jl	91.02%	29 Missing ⚠️
src/robustlinearmodel.jl	91.01%	8 Missing ⚠️
src/RobustModels.jl	33.33%	2 Missing ⚠️
src/linpred.jl	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #37      +/-   ##
==========================================
+ Coverage   84.12%   85.02%   +0.90%     
==========================================
  Files          12       14       +2     
  Lines        1776     2651     +875     
==========================================
+ Hits         1494     2254     +760     
- Misses        282      397     +115     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[github-actions]

Remaining comments which cannot be posted as a review comment to avoid GitHub Rate Limit

JuliaFormatter

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/ipod.jl

Lines 148 to 149 in 169baab

	(A isa FormulaTerm) ? "formula" :
	(A isa SparseMatrixCSC) ? "sparse " : "dense "

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/ipod.jl

Lines 211 to 212 in 169baab

	(A isa FormulaTerm) ? "formula" :
	(A isa SparseMatrixCSC) ? "sparse " : "dense "

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/ipod.jl

Lines 258 to 259 in 169baab

	(A isa FormulaTerm) ? "formula" :
	(A isa SparseMatrixCSC) ? "sparse " : "dense "

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/penalties.jl

Lines 138 to 139 in 169baab

	(A isa FormulaTerm) ? "formula" :
	(A isa SparseMatrixCSC) ? "sparse " : "dense "

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/penalties.jl

Lines 169 to 170 in 169baab

	# elseif f in (confint,)
	# @test isapprox(var1, var2; rtol=1e-1)

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 13 in 169baab

snr::Real = 3,

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 23 in 169baab

beta = vcat(beta, zeros(T, p-nonzero))

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 27 in 169baab

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Lines 31 to 32 in 169baab

	X .+= sqrt(rho/(1-rho)) * z
	X *= sqrt(1-rho)

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Lines 34 to 35 in 169baab

	ssd = sqrt((1-rho)*sum(abs2, beta) + rho*sum(abs, beta))

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 37 in 169baab

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 68 in 169baab

@test_throws Exception rlm(X3, y3, est1; method=method, initial_scale=1, dropcollinear=false)

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 72 in 169baab

m1 = rlm(X3, y3, pen; method=method, initial_scale=1, maxiter=1000, dropcollinear=true)

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 89 in 169baab

@test_throws Exception ipod(X3, y3, loss1, pen; method=method, initial_scale=1, dropcollinear=false)

---

[JuliaFormatter] _{reported by reviewdog 🐶}

RobustModels.jl/test/underdetermined.jl

Line 91 in 169baab

m2 = ipod(X3, y3, loss1, pen; method=method, initial_scale=1, maxiter=1000, dropcollinear=true)