Package evaluation of Grumps on Julia 1.10.8 (92f03a4775*) started at 2025-02-25T14:36:47.271 ################################################################################ # Set-up # Installing PkgEval dependencies (TestEnv)... Set-up completed after 5.29s ################################################################################ # Installation # Installing Grumps... Resolving package versions... Updating `~/.julia/environments/v1.10/Project.toml` [3967666a] + Grumps v0.2.4 Updating `~/.julia/environments/v1.10/Manifest.toml` [79e6a3ab] + Adapt v4.2.0 [66dad0bd] + AliasTables v1.1.3 [e36756a0] + Ansillary v0.1.0 [4fba245c] + ArrayInterface v7.18.0 [69666777] + Arrow v2.8.0 [31f734f8] + ArrowTypes v2.3.0 [c3b6d118] + BitIntegers v0.3.2 [62783981] + BitTwiddlingConvenienceFunctions v0.1.6 [2a0fbf3d] + CPUSummary v0.2.6 [336ed68f] + CSV v0.10.15 [fb6a15b2] + CloseOpenIntervals v0.1.13 [5ba52731] + CodecLz4 v0.4.5 [944b1d66] + CodecZlib v0.7.8 [6b39b394] + CodecZstd v0.8.6 [bbf7d656] + CommonSubexpressions v0.3.1 [f70d9fcc] + CommonWorldInvalidations v1.0.0 [34da2185] + Compat v4.16.0 [f0e56b4a] + ConcurrentUtilities v2.5.0 [187b0558] + ConstructionBase v1.5.8 [adafc99b] + CpuId v0.3.1 [a8cc5b0e] + Crayons v4.1.1 [9a962f9c] + DataAPI v1.16.0 [a93c6f00] + DataFrames v1.7.0 [864edb3b] + DataStructures v0.18.20 [e2d170a0] + DataValueInterfaces v1.0.0 [163ba53b] + DiffResults v1.1.0 [b552c78f] + DiffRules v1.15.1 [b4f34e82] + Distances v0.10.12 [ffbed154] + DocStringExtensions v0.9.3 [4e289a0a] + EnumX v1.0.4 [e2ba6199] + ExprTools v0.1.10 ⌅ [442a2c76] + FastGaussQuadrature v0.5.1 [48062228] + FilePathsBase v0.9.23 [1a297f60] + FillArrays v1.13.0 [6a86dc24] + FiniteDiff v2.27.0 [f6369f11] + ForwardDiff v0.10.38 [3967666a] + Grumps v0.2.4 [3e5b6fbb] + HostCPUFeatures v0.1.17 [34004b35] + HypergeometricFunctions v0.3.27 [615f187c] + IfElse v0.1.1 [842dd82b] + InlineStrings v1.4.3 [41ab1584] + InvertedIndices v1.3.1 [92d709cd] + IrrationalConstants v0.2.4 [82899510] + IteratorInterfaceExtensions v1.0.0 [1019f520] + JLFzf v0.1.9 [692b3bcd] + JLLWrappers v1.7.0 [70703baa] + JuliaSyntax v0.4.10 [b964fa9f] + LaTeXStrings v1.4.0 [10f19ff3] + LayoutPointers v0.1.17 [d3d80556] + LineSearches v7.3.0 [2ab3a3ac] + LogExpFunctions v0.3.29 [bdcacae8] + LoopVectorization v0.12.171 [1914dd2f] + MacroTools v0.5.15 [d125e4d3] + ManualMemory v0.1.8 [e1d29d7a] + Missings v1.2.0 [78c3b35d] + Mocking v0.8.1 [d41bc354] + NLSolversBase v7.8.3 [77ba4419] + NaNMath v1.1.2 [6fe1bfb0] + OffsetArrays v1.15.0 [5fb14364] + OhMyREPL v0.5.28 [429524aa] + Optim v1.11.0 [bac558e1] + OrderedCollections v1.8.0 [d96e819e] + Parameters v0.12.3 [69de0a69] + Parsers v2.8.1 [b98c9c47] + Pipe v1.3.0 [1d0040c9] + PolyesterWeave v0.2.2 [2dfb63ee] + PooledArrays v1.4.3 [85a6dd25] + PositiveFactorizations v0.2.4 [aea7be01] + PrecompileTools v1.2.1 [21216c6a] + Preferences v1.4.3 [08abe8d2] + PrettyTables v2.4.0 [43287f4e] + PtrArrays v1.3.0 [74087812] + Random123 v1.7.0 [e6cf234a] + RandomNumbers v1.6.0 [189a3867] + Reexport v1.2.2 [ae029012] + Requires v1.3.0 [79098fc4] + Rmath v0.8.0 [94e857df] + SIMDTypes v0.1.0 [476501e8] + SLEEFPirates v0.6.43 [6c6a2e73] + Scratch v1.2.1 [91c51154] + SentinelArrays v1.4.8 [efcf1570] + Setfield v1.1.1 [d1712120] + Smartphores v0.1.0 [a2af1166] + SortingAlgorithms v1.2.1 [276daf66] + SpecialFunctions v2.5.0 [aedffcd0] + Static v1.1.1 [0d7ed370] + StaticArrayInterface v1.8.0 [90137ffa] + StaticArrays v1.9.12 [1e83bf80] + StaticArraysCore v1.4.3 [82ae8749] + StatsAPI v1.7.0 [2913bbd2] + StatsBase v0.34.4 [4c63d2b9] + StatsFuns v1.3.2 [88034a9c] + StringDistances v0.11.3 [892a3eda] + StringManipulation v0.4.1 [354b36f9] + StringViews v1.3.4 [dc5dba14] + TZJData v1.4.0+2025a [3783bdb8] + TableTraits v1.0.1 [bd369af6] + Tables v1.12.0 [8290d209] + ThreadingUtilities v0.5.2 [f269a46b] + TimeZones v1.21.2 [3bb67fe8] + TranscodingStreams v0.11.3 [bc48ee85] + Tullio v0.3.8 [04da0e3b] + TypeTree v0.3.0 [3a884ed6] + UnPack v1.0.2 [3d5dd08c] + VectorizationBase v0.21.71 [ea10d353] + WeakRefStrings v1.4.2 [76eceee3] + WorkerUtilities v1.6.1 [5ced341a] + Lz4_jll v1.10.1+0 [efe28fd5] + OpenSpecFun_jll v0.5.6+0 [f50d1b31] + Rmath_jll v0.5.1+0 [3161d3a3] + Zstd_jll v1.5.7+1 [214eeab7] + fzf_jll v0.56.3+0 [0dad84c5] + ArgTools v1.1.1 [56f22d72] + Artifacts [2a0f44e3] + Base64 [ade2ca70] + Dates [8ba89e20] + Distributed [f43a241f] + Downloads v1.6.0 [7b1f6079] + FileWatching [9fa8497b] + Future [b77e0a4c] + InteractiveUtils [b27032c2] + LibCURL v0.6.4 [76f85450] + LibGit2 [8f399da3] + Libdl [37e2e46d] + LinearAlgebra [56ddb016] + Logging [d6f4376e] + Markdown [a63ad114] + Mmap [ca575930] + NetworkOptions v1.2.0 [44cfe95a] + Pkg v1.10.0 [de0858da] + Printf [3fa0cd96] + REPL [9a3f8284] + Random [ea8e919c] + SHA v0.7.0 [9e88b42a] + Serialization [6462fe0b] + Sockets [2f01184e] + SparseArrays v1.10.0 [10745b16] + Statistics v1.10.0 [fa267f1f] + TOML v1.0.3 [a4e569a6] + Tar v1.10.0 [cf7118a7] + UUIDs [4ec0a83e] + Unicode [e66e0078] + CompilerSupportLibraries_jll v1.1.1+0 [deac9b47] + LibCURL_jll v8.4.0+0 [e37daf67] + LibGit2_jll v1.6.4+0 [29816b5a] + LibSSH2_jll v1.11.0+1 [c8ffd9c3] + MbedTLS_jll v2.28.2+1 [14a3606d] + MozillaCACerts_jll v2023.1.10 [4536629a] + OpenBLAS_jll v0.3.23+4 [05823500] + OpenLibm_jll v0.8.1+4 [bea87d4a] + SuiteSparse_jll v7.2.1+1 [83775a58] + Zlib_jll v1.2.13+1 [8e850b90] + libblastrampoline_jll v5.11.0+0 [8e850ede] + nghttp2_jll v1.52.0+1 [3f19e933] + p7zip_jll v17.4.0+2 Info Packages marked with ⌅ have new versions available but compatibility constraints restrict them from upgrading. To see why use `status --outdated -m` Installation completed after 7.56s ################################################################################ # Precompilation # Precompiling PkgEval dependencies... Precompiling package dependencies... Precompilation completed after 91.63s ################################################################################ # Testing # Testing Grumps Status `/tmp/jl_g8i2i0/Project.toml` [e36756a0] Ansillary v0.1.0 [69666777] Arrow v2.8.0 [336ed68f] CSV v0.10.15 [adafc99b] CpuId v0.3.1 [a8cc5b0e] Crayons v4.1.1 [a93c6f00] DataFrames v1.7.0 ⌅ [442a2c76] FastGaussQuadrature v0.5.1 [3967666a] Grumps v0.2.4 [bdcacae8] LoopVectorization v0.12.171 [5fb14364] OhMyREPL v0.5.28 [429524aa] Optim v1.11.0 [74087812] Random123 v1.7.0 [d1712120] Smartphores v0.1.0 [2913bbd2] StatsBase v0.34.4 [4c63d2b9] StatsFuns v1.3.2 [88034a9c] StringDistances v0.11.3 [bc48ee85] Tullio v0.3.8 [04da0e3b] TypeTree v0.3.0 [ade2ca70] Dates [37e2e46d] LinearAlgebra [44cfe95a] Pkg v1.10.0 [de0858da] Printf [9a3f8284] Random [2f01184e] SparseArrays v1.10.0 [8dfed614] Test Status `/tmp/jl_g8i2i0/Manifest.toml` [79e6a3ab] Adapt v4.2.0 [66dad0bd] AliasTables v1.1.3 [e36756a0] Ansillary v0.1.0 [4fba245c] ArrayInterface v7.18.0 [69666777] Arrow v2.8.0 [31f734f8] ArrowTypes v2.3.0 [c3b6d118] BitIntegers v0.3.2 [62783981] BitTwiddlingConvenienceFunctions v0.1.6 [2a0fbf3d] CPUSummary v0.2.6 [336ed68f] CSV v0.10.15 [fb6a15b2] CloseOpenIntervals v0.1.13 [5ba52731] CodecLz4 v0.4.5 [944b1d66] CodecZlib v0.7.8 [6b39b394] CodecZstd v0.8.6 [bbf7d656] CommonSubexpressions v0.3.1 [f70d9fcc] CommonWorldInvalidations v1.0.0 [34da2185] Compat v4.16.0 [f0e56b4a] ConcurrentUtilities v2.5.0 [187b0558] ConstructionBase v1.5.8 [adafc99b] CpuId v0.3.1 [a8cc5b0e] Crayons v4.1.1 [9a962f9c] DataAPI v1.16.0 [a93c6f00] DataFrames v1.7.0 [864edb3b] DataStructures v0.18.20 [e2d170a0] DataValueInterfaces v1.0.0 [163ba53b] DiffResults v1.1.0 [b552c78f] DiffRules v1.15.1 [b4f34e82] Distances v0.10.12 [ffbed154] DocStringExtensions v0.9.3 [4e289a0a] EnumX v1.0.4 [e2ba6199] ExprTools v0.1.10 ⌅ [442a2c76] FastGaussQuadrature v0.5.1 [48062228] FilePathsBase v0.9.23 [1a297f60] FillArrays v1.13.0 [6a86dc24] FiniteDiff v2.27.0 [f6369f11] ForwardDiff v0.10.38 [3967666a] Grumps v0.2.4 [3e5b6fbb] HostCPUFeatures v0.1.17 [34004b35] HypergeometricFunctions v0.3.27 [615f187c] IfElse v0.1.1 [842dd82b] InlineStrings v1.4.3 [41ab1584] InvertedIndices v1.3.1 [92d709cd] IrrationalConstants v0.2.4 [82899510] IteratorInterfaceExtensions v1.0.0 [1019f520] JLFzf v0.1.9 [692b3bcd] JLLWrappers v1.7.0 [70703baa] JuliaSyntax v0.4.10 [b964fa9f] LaTeXStrings v1.4.0 [10f19ff3] LayoutPointers v0.1.17 [d3d80556] LineSearches v7.3.0 [2ab3a3ac] LogExpFunctions v0.3.29 [bdcacae8] LoopVectorization v0.12.171 [1914dd2f] MacroTools v0.5.15 [d125e4d3] ManualMemory v0.1.8 [e1d29d7a] Missings v1.2.0 [78c3b35d] Mocking v0.8.1 [d41bc354] NLSolversBase v7.8.3 [77ba4419] NaNMath v1.1.2 [6fe1bfb0] OffsetArrays v1.15.0 [5fb14364] OhMyREPL v0.5.28 [429524aa] Optim v1.11.0 [bac558e1] OrderedCollections v1.8.0 [d96e819e] Parameters v0.12.3 [69de0a69] Parsers v2.8.1 [b98c9c47] Pipe v1.3.0 [1d0040c9] PolyesterWeave v0.2.2 [2dfb63ee] PooledArrays v1.4.3 [85a6dd25] PositiveFactorizations v0.2.4 [aea7be01] PrecompileTools v1.2.1 [21216c6a] Preferences v1.4.3 [08abe8d2] PrettyTables v2.4.0 [43287f4e] PtrArrays v1.3.0 [74087812] Random123 v1.7.0 [e6cf234a] RandomNumbers v1.6.0 [189a3867] Reexport v1.2.2 [ae029012] Requires v1.3.0 [79098fc4] Rmath v0.8.0 [94e857df] SIMDTypes v0.1.0 [476501e8] SLEEFPirates v0.6.43 [6c6a2e73] Scratch v1.2.1 [91c51154] SentinelArrays v1.4.8 [efcf1570] Setfield v1.1.1 [d1712120] Smartphores v0.1.0 [a2af1166] SortingAlgorithms v1.2.1 [276daf66] SpecialFunctions v2.5.0 [aedffcd0] Static v1.1.1 [0d7ed370] StaticArrayInterface v1.8.0 [90137ffa] StaticArrays v1.9.12 [1e83bf80] StaticArraysCore v1.4.3 [82ae8749] StatsAPI v1.7.0 [2913bbd2] StatsBase v0.34.4 [4c63d2b9] StatsFuns v1.3.2 [88034a9c] StringDistances v0.11.3 [892a3eda] StringManipulation v0.4.1 [354b36f9] StringViews v1.3.4 [dc5dba14] TZJData v1.4.0+2025a [3783bdb8] TableTraits v1.0.1 [bd369af6] Tables v1.12.0 [8290d209] ThreadingUtilities v0.5.2 [f269a46b] TimeZones v1.21.2 [3bb67fe8] TranscodingStreams v0.11.3 [bc48ee85] Tullio v0.3.8 [04da0e3b] TypeTree v0.3.0 [3a884ed6] UnPack v1.0.2 [3d5dd08c] VectorizationBase v0.21.71 [ea10d353] WeakRefStrings v1.4.2 [76eceee3] WorkerUtilities v1.6.1 [5ced341a] Lz4_jll v1.10.1+0 [efe28fd5] OpenSpecFun_jll v0.5.6+0 [f50d1b31] Rmath_jll v0.5.1+0 [3161d3a3] Zstd_jll v1.5.7+1 [214eeab7] fzf_jll v0.56.3+0 [0dad84c5] ArgTools v1.1.1 [56f22d72] Artifacts [2a0f44e3] Base64 [ade2ca70] Dates [8ba89e20] Distributed [f43a241f] Downloads v1.6.0 [7b1f6079] FileWatching [9fa8497b] Future [b77e0a4c] InteractiveUtils [b27032c2] LibCURL v0.6.4 [76f85450] LibGit2 [8f399da3] Libdl [37e2e46d] LinearAlgebra [56ddb016] Logging [d6f4376e] Markdown [a63ad114] Mmap [ca575930] NetworkOptions v1.2.0 [44cfe95a] Pkg v1.10.0 [de0858da] Printf [3fa0cd96] REPL [9a3f8284] Random [ea8e919c] SHA v0.7.0 [9e88b42a] Serialization [6462fe0b] Sockets [2f01184e] SparseArrays v1.10.0 [10745b16] Statistics v1.10.0 [fa267f1f] TOML v1.0.3 [a4e569a6] Tar v1.10.0 [8dfed614] Test [cf7118a7] UUIDs [4ec0a83e] Unicode [e66e0078] CompilerSupportLibraries_jll v1.1.1+0 [deac9b47] LibCURL_jll v8.4.0+0 [e37daf67] LibGit2_jll v1.6.4+0 [29816b5a] LibSSH2_jll v1.11.0+1 [c8ffd9c3] MbedTLS_jll v2.28.2+1 [14a3606d] MozillaCACerts_jll v2023.1.10 [4536629a] OpenBLAS_jll v0.3.23+4 [05823500] OpenLibm_jll v0.8.1+4 [bea87d4a] SuiteSparse_jll v7.2.1+1 [83775a58] Zlib_jll v1.2.13+1 [8e850b90] libblastrampoline_jll v5.11.0+0 [8e850ede] nghttp2_jll v1.52.0+1 [3f19e933] p7zip_jll v17.4.0+2 Info Packages marked with ⌅ have new versions available but compatibility constraints restrict them from upgrading. Testing Running tests... ________ _____ __________ _________ / _____/______ __ __ / \\______ \/ _____/ / \ __\_ __ \ | \/ \ / \| ___/\_____ \ \ \_\ \ | \/ | / Y \ | / \ \______ /__| |____/\____|__ /____| /_______ / \/ \/ \/ Please note: 1: read the manual at https://nittanylion.github.io/Grumps.jl completely 2: read the paper at http://joris.pinkse.org/paper/grumps/ 3: if you see unexpected behavior, please send me code and data so that I can replicate 4: all of the user-level commands are documented; e.g. use ?Save 5: please check the memory conservation documentation if memory becomes an issue 6: please direct all questions/suggestions/comments to Joris Pinkse at joris@psu.edu This is Grumps version 0.2.4 (2023-09-14) Your version of Grumps is 530 days old: please check for updates regularly! ┌ Note: number of BLAS threads used = 1 └ [ Info: no randomization chosen for macro integrator: just selecting from the start of the draws data if provided ┌ Note: no separate random number generator implemented for replicable = true; just using the first one └ [ Info: will compute ξ variance matrix for next stage assuming homoskedasticity ┌ Note: you are only using one Julia thread │ which is typically slow: │ start Julia with e.g. julia -t 8 to get 8 threads └ ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ Summary ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ ―――――――――――――――――――――――――――――――― Specification ――――――――――――――――――――――――――――――――― Uᵢⱼₘ = θ₁incomeᵢₘ + θ₂incomeᵢₘibuⱼₘ + θ₃ageᵢₘibuⱼₘ + θ₄νᵢ₁ₘibuⱼₘ + θ₅νᵢ₂ₘabvⱼₘ + β₁ + β₂ibuⱼₘ + β₃abvⱼₘ + ξⱼₘ + ϵᵢⱼₘ instruments: IVgh_ibu, IVgh_abv ―――――――――――――――――――――――――――――――――― Data Sizes ―――――――――――――――――――――――――――――――――― 5 markets; 55 products; 495,000 consumers; 5,000 micro consumers; 3 interactions; 2 random coefficients; 3 product regressors; 5 instruments ―――――――――――――――――――――――― Detailed Estimator Description ―――――――――――――――――――――――― The estimator used here is the Conformant Likelihood with Exogeneity Restrictions estimator. It minimizes an objective function of the form Ω̂( θ, δ, β ) = ℒ ᵐⁱᶜ( θ, δ ) + ℒ ᵐᵃᶜ( θ, δ ) + Π( δ, β ) where the first two components are (minus) a micro likelihood and a macro likelihood and the last component is a GMM style objective function. This is the full version of this estimator which takes longer to compute than the asymptotically equivalent cheap version. The main advantage of the full CLER estimator compared to the cheap version is that there is somewhat greater robustness to small shares. ――――――――――――――――――――――――――――――― Nodes and Draws ―――――――――――――――――――――――――――――――― 605 micro nodes/draws; 50,000 macro nodes/draws ――――――――――――――――――――――――――――― Optimization Options ――――――――――――――――――――――――――――― tolerances f_tol g_tol x_tol iterations maxrepeats δ 0 1e-8 0 25 θ 1e-8 1e-4 1e-5 50 3 threads machcpus machthr specthr blasthr mktthr inthr 32 64 1 1 1 1 loop vectorization true ――――――――――――――――――――――――――――― Memory Conservation ―――――――――――――――――――――――――――――― memsave false ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ End of Summary ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ ■ ■ ■ Conformant Likelihood with Exogeneity Restrictions ■ ■ ■ __________________________________________________ itr obj fun value gradient norm time theta coefficients --- -------------- -------------- ------- 0 +6492.88162702 950.22851859 0.00 +0.00 +0.00 +0.00 +0.50 +0.50 1 +5778.32829141 198.73916216 11.83 +0.48 +0.24 +0.31 +0.28 +0.46 2 +5709.65876424 24.23383458 20.91 +1.17 +0.09 +0.52 +0.22 +0.34 3 +5708.97909167 1.09132076 27.07 +1.22 +0.09 +0.54 +0.22 +0.38 4 +5708.97909167 1.09132076 29.56 +1.22 +0.09 +0.54 +0.22 +0.38 5 +5708.97909167 1.09132076 33.70 +1.22 +0.09 +0.54 +0.22 +0.38 6 +5708.95712041 1.00035797 39.53 +1.23 +0.10 +0.55 +0.25 +0.39 7 +5708.92553725 4.87689373 48.75 +1.22 +0.12 +0.57 +0.32 +0.39 8 +5708.85303998 2.37526035 54.92 +1.22 +0.14 +0.59 +0.37 +0.39 9 +5708.81900168 6.91069173 61.14 +1.22 +0.18 +0.62 +0.46 +0.39 10 +5708.71794805 0.98171301 70.94 +1.21 +0.20 +0.64 +0.50 +0.39 11 +5708.71794805 0.98171301 74.45 +1.21 +0.20 +0.64 +0.50 +0.39 12 +5708.69250237 0.63833166 80.68 +1.22 +0.21 +0.65 +0.52 +0.39 13 +5708.65149992 1.95449788 86.88 +1.22 +0.24 +0.68 +0.58 +0.38 14 +5708.61881908 4.21800233 93.19 +1.21 +0.29 +0.73 +0.68 +0.38 15 +5708.57221160 0.47125135 99.48 +1.21 +0.31 +0.75 +0.71 +0.38 16 +5708.57221160 0.47125135 102.21 +1.21 +0.31 +0.75 +0.71 +0.38 17 +5708.56331612 0.31895777 108.38 +1.22 +0.32 +0.76 +0.74 +0.38 18 +5708.55331055 0.94081935 114.60 +1.22 +0.35 +0.79 +0.79 +0.37 19 +5708.54941405 0.21998523 120.84 +1.22 +0.36 +0.80 +0.81 +0.37 20 +5708.54896707 0.05809610 127.01 +1.22 +0.37 +0.81 +0.82 +0.37 21 +5708.54895790 0.00069997 133.24 +1.22 +0.37 +0.81 +0.83 +0.37 22 +5708.54895789 0.00000071 139.31 +1.22 +0.37 +0.81 +0.83 +0.37 [ Info: computing asymptotic variance if requested [ Info: no randomization chosen for macro integrator: just selecting from the start of the draws data if provided ┌ Note: no separate random number generator implemented for replicable = true; just using the first one └ [ Info: will compute ξ variance matrix for next stage assuming homoskedasticity ┌ Note: you are only using one Julia thread │ which is typically slow: │ start Julia with e.g. julia -t 8 to get 8 threads └ ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ Summary ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ ―――――――――――――――――――――――――――――――― Specification ――――――――――――――――――――――――――――――――― Uᵢⱼₘ = θ₁incomeᵢₘ + θ₂incomeᵢₘibuⱼₘ + θ₃ageᵢₘibuⱼₘ + θ₄νᵢ₁ₘibuⱼₘ + θ₅νᵢ₂ₘabvⱼₘ + β₁ + β₂ibuⱼₘ + β₃abvⱼₘ + ξⱼₘ + ϵᵢⱼₘ instruments: IVgh_ibu, IVgh_abv ―――――――――――――――――――――――――――――――――― Data Sizes ―――――――――――――――――――――――――――――――――― 5 markets; 55 products; 495,000 consumers; 5,000 micro consumers; 3 interactions; 2 random coefficients; 3 product regressors; 5 instruments ―――――――――――――――――――――――― Detailed Estimator Description ―――――――――――――――――――――――― The estimator used here is the cheap version of the Conformant Likelihood with Exogeneity Restrictions estimator. It minimizes an objective function of the form Ω̂( θ, δ, β ) = ℒ ᵐⁱᶜ( θ, δ ) + ℒ ᵐᵃᶜ( θ, δ ) with respect to δ in the inner loop and then minimizes an objective function of the form Ω̂( θ, δ, β ) = ℒ ᵐⁱᶜ( θ, δ ) + ℒ ᵐᵃᶜ( θ, δ ) + Π( δ, β ) in the outer loop. Here, the first two components are (minus) a micro likelihood and a macro likelihood and the last component is a GMM style objective function. The cheap version computes faster and has the same asymptotic distribution as the full CLER estimator. The only difference is that the full CLER estimator has somewhat greater robustness to small shares. ――――――――――――――――――――――――――――――― Nodes and Draws ―――――――――――――――――――――――――――――――― 605 micro nodes/draws; 50,000 macro nodes/draws ――――――――――――――――――――――――――――― Optimization Options ――――――――――――――――――――――――――――― tolerances f_tol g_tol x_tol iterations maxrepeats δ 0 1e-8 0 25 θ 1e-8 1e-4 1e-5 50 3 threads machcpus machthr specthr blasthr mktthr inthr 32 64 1 1 1 1 loop vectorization true ――――――――――――――――――――――――――――― Memory Conservation ―――――――――――――――――――――――――――――― memsave false ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ End of Summary ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ ■ ■ □ Conformant Likelihood with Exogeneity Restrictions (cheap version) ■ ■ ■ __________________________________________________________________ itr obj fun value gradient norm time theta coefficients --- -------------- -------------- ------- 0 +6492.88266336 950.22850294 0.00 +0.00 +0.00 +0.00 +0.50 +0.50 1 +5778.33086028 198.67999972 6.10 +0.48 +0.24 +0.31 +0.28 +0.46 2 +5709.66725778 24.29126567 11.70 +1.17 +0.09 +0.52 +0.22 +0.33 3 +5708.98088741 1.09780708 17.21 +1.22 +0.09 +0.54 +0.22 +0.38 4 +5708.98088741 1.09780708 19.10 +1.22 +0.09 +0.54 +0.22 +0.38 5 +5708.98088741 1.09780708 21.15 +1.22 +0.09 +0.54 +0.22 +0.38 6 +5708.95764618 0.96808265 26.81 +1.23 +0.10 +0.55 +0.25 +0.39 7 +5708.92619344 4.86337998 32.34 +1.22 +0.12 +0.57 +0.32 +0.39 8 +5708.85412842 2.33117916 37.81 +1.22 +0.14 +0.59 +0.37 +0.39 9 +5708.82010659 6.90144249 43.44 +1.21 +0.18 +0.62 +0.46 +0.39 10 +5708.71938817 0.98442571 49.01 +1.21 +0.20 +0.64 +0.50 +0.38 11 +5708.71938817 0.98442571 51.42 +1.21 +0.20 +0.64 +0.50 +0.38 12 +5708.69389775 0.63873759 57.43 +1.22 +0.21 +0.65 +0.52 +0.38 13 +5708.65271854 1.95737702 62.73 +1.22 +0.24 +0.68 +0.58 +0.38 14 +5708.61969489 4.22890644 67.96 +1.21 +0.29 +0.73 +0.68 +0.38 15 +5708.57263335 0.50059700 72.96 +1.21 +0.31 +0.75 +0.71 +0.37 16 +5708.57263335 0.50059700 74.94 +1.21 +0.31 +0.75 +0.71 +0.37 17 +5708.56373236 0.31414353 79.56 +1.22 +0.32 +0.76 +0.74 +0.37 18 +5708.55360693 0.90498968 83.88 +1.22 +0.35 +0.79 +0.79 +0.37 19 +5708.54957392 0.27438176 88.99 +1.22 +0.36 +0.80 +0.81 +0.37 20 +5708.54913315 0.05561802 93.95 +1.22 +0.37 +0.81 +0.83 +0.37 21 +5708.54912295 0.00217700 99.06 +1.22 +0.37 +0.81 +0.83 +0.37 22 +5708.54912143 0.00026997 104.36 +1.22 +0.37 +0.81 +0.83 +0.37 [ Info: computing asymptotic variance if requested [ Info: no randomization chosen for macro integrator: just selecting from the start of the draws data if provided ┌ Note: no separate random number generator implemented for replicable = true; just using the first one └ [ Info: will compute ξ variance matrix for next stage assuming homoskedasticity ┌ Note: you are only using one Julia thread │ which is typically slow: │ start Julia with e.g. julia -t 8 to get 8 threads └ ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ Summary ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ ―――――――――――――――――――――――――――――――― Specification ――――――――――――――――――――――――――――――――― Uᵢⱼₘ = θ₁incomeᵢₘ + θ₂incomeᵢₘibuⱼₘ + θ₃ageᵢₘibuⱼₘ + θ₄νᵢ₁ₘibuⱼₘ + θ₅νᵢ₂ₘabvⱼₘ + β₁ + β₂ibuⱼₘ + β₃abvⱼₘ + ξⱼₘ + ϵᵢⱼₘ instruments: IVgh_ibu, IVgh_abv ―――――――――――――――――――――――――――――――――― Data Sizes ―――――――――――――――――――――――――――――――――― 5 markets; 55 products; 495,000 consumers; 5,000 micro consumers; 3 interactions; 2 random coefficients; 3 product regressors; 5 instruments ―――――――――――――――――――――――― Detailed Estimator Description ―――――――――――――――――――――――― The estimator used here is the Mixed Data Likelihood Estimator. It minimizes an objective function of the form Ω̂( θ, δ ) = ℒ ᵐⁱᶜ( θ, δ ) + ℒ ᵐᵃᶜ( θ, δ ) with respect to θ and δ and then minimizes a GMM style objective function Π̂( δ̂, β ) with respect to β in a second step. Unlike the CLER estimator (both the full and cheap version), the MDLE is not fully robust. Moreover, in some circumstances it is also less efficient, even converge at a slower rate. ――――――――――――――――――――――――――――――― Nodes and Draws ―――――――――――――――――――――――――――――――― 605 micro nodes/draws; 50,000 macro nodes/draws ――――――――――――――――――――――――――――― Optimization Options ――――――――――――――――――――――――――――― tolerances f_tol g_tol x_tol iterations maxrepeats δ 0 1e-8 0 25 θ 1e-8 1e-4 1e-5 50 3 threads machcpus machthr specthr blasthr mktthr inthr 32 64 1 1 1 1 loop vectorization true ――――――――――――――――――――――――――――― Memory Conservation ―――――――――――――――――――――――――――――― memsave false ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ End of Summary ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ ■ ■ □ Mixed data likelihood estimator ■ ■ □ _______________________________ itr obj fun value gradient norm time theta coefficients --- -------------- -------------- ------- 0 +6492.35361923 950.23590246 0.00 +0.00 +0.00 +0.00 +0.50 +0.50 1 +5777.98177646 198.68843711 6.04 +0.48 +0.24 +0.31 +0.28 +0.46 2 +5709.57367762 24.22156677 11.64 +1.17 +0.09 +0.52 +0.22 +0.34 3 +5708.80575343 2.22482177 17.08 +1.24 +0.09 +0.54 +0.22 +0.43 4 +5708.80575343 2.22482177 19.45 +1.24 +0.09 +0.54 +0.22 +0.43 5 +5708.77875249 1.32586806 25.05 +1.25 +0.09 +0.55 +0.25 +0.43 6 +5708.76199070 6.45853395 30.60 +1.24 +0.12 +0.57 +0.34 +0.43 7 +5708.67857322 1.10297666 35.53 +1.24 +0.13 +0.59 +0.37 +0.43 8 +5708.67857322 1.10297666 38.40 +1.24 +0.13 +0.59 +0.37 +0.43 9 +5708.65364880 0.65584822 43.92 +1.24 +0.14 +0.60 +0.39 +0.43 10 +5708.61079109 2.37863901 49.45 +1.24 +0.17 +0.62 +0.45 +0.43 11 +5708.58229317 5.95775235 55.05 +1.23 +0.21 +0.66 +0.55 +0.43 12 +5708.50678526 0.59044700 60.52 +1.24 +0.23 +0.68 +0.57 +0.43 13 +5708.50678526 0.59044700 62.99 +1.24 +0.23 +0.68 +0.57 +0.43 14 +5708.48785232 0.70178983 68.46 +1.24 +0.25 +0.70 +0.61 +0.43 15 +5708.46710617 2.17584511 73.95 +1.24 +0.28 +0.73 +0.68 +0.44 16 +5708.45057561 0.43535381 79.52 +1.24 +0.30 +0.75 +0.71 +0.43 17 +5708.44584272 0.85559774 84.98 +1.24 +0.33 +0.78 +0.76 +0.43 18 +5708.44441526 0.02149074 90.42 +1.24 +0.33 +0.78 +0.76 +0.43 19 +5708.44438028 0.00734241 95.10 +1.24 +0.33 +0.78 +0.77 +0.43 20 +5708.44438019 0.00000053 99.54 +1.24 +0.33 +0.78 +0.77 +0.43 [ Info: computing asymptotic variance if requested [ Info: no randomization chosen for macro integrator: just selecting from the start of the draws data if provided ┌ Note: no separate random number generator implemented for replicable = true; just using the first one └ [ Info: will compute ξ variance matrix for next stage assuming homoskedasticity ┌ Note: you are only using one Julia thread │ which is typically slow: │ start Julia with e.g. julia -t 8 to get 8 threads └ ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ Summary ∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨∨ ―――――――――――――――――――――――――――――――― Specification ――――――――――――――――――――――――――――――――― Uᵢⱼₘ = θ₁incomeᵢₘ + θ₂incomeᵢₘibuⱼₘ + θ₃ageᵢₘibuⱼₘ + θ₄νᵢ₁ₘibuⱼₘ + θ₅νᵢ₂ₘabvⱼₘ + β₁ + β₂ibuⱼₘ + β₃abvⱼₘ + ξⱼₘ + ϵᵢⱼₘ instruments: IVgh_ibu, IVgh_abv ―――――――――――――――――――――――――――――――――― Data Sizes ―――――――――――――――――――――――――――――――――― 5 markets; 55 products; 495,000 consumers; 5,000 micro consumers; 3 interactions; 2 random coefficients; 3 product regressors; 5 instruments ―――――――――――――――――――――――― Detailed Estimator Description ―――――――――――――――――――――――― The estimator used here is the Share Constraint Estimator. It minimizes an objective function of the form Ω̂( θ, δ ) = ℒ ᵐᵃᶜ( θ, δ ) with respect to δ in an inner loop, then minimizes ℒ ᵐⁱᶜ( θ, δ̂ ) with respect to θ in an outer loop and finally minimizes a GMM style objective function Π̂( δ̂, β ) with respect to β in a final step. This estimator is dominated by several other choices. ――――――――――――――――――――――――――――――― Nodes and Draws ―――――――――――――――――――――――――――――――― 605 micro nodes/draws; 50,000 macro nodes/draws ――――――――――――――――――――――――――――― Optimization Options ――――――――――――――――――――――――――――― tolerances f_tol g_tol x_tol iterations maxrepeats δ 0 1e-8 0 25 θ 1e-8 1e-4 1e-5 50 3 threads machcpus machthr specthr blasthr mktthr inthr 32 64 1 1 1 1 loop vectorization true ――――――――――――――――――――――――――――― Memory Conservation ―――――――――――――――――――――――――――――― memsave false ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ End of Summary ∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧∧ □ ■ □ Mixed Logit with Share Constraint ■ ■ □ _________________________________ itr obj fun value gradient norm time theta coefficients --- -------------- -------------- ------- 0 +6492.62849893 950.27078449 0.00 +0.00 +0.00 +0.00 +0.50 +0.50 1 +5777.83860039 196.74651712 2.37 +0.48 +0.24 +0.31 +0.28 +0.46 2 +5709.84022660 22.84682628 4.36 +1.12 +0.11 +0.53 +0.21 +0.32 3 +5709.37981728 6.63514772 6.30 +1.26 +0.08 +0.54 +0.21 +0.52 4 +5709.09583070 4.70282001 8.41 +1.26 +0.09 +0.55 +0.26 +0.45 5 +5709.09583070 4.70282001 9.09 +1.26 +0.09 +0.55 +0.26 +0.45 6 +5709.09583070 4.70282001 9.81 +1.26 +0.09 +0.55 +0.26 +0.45 7 +5709.03722061 5.46384391 11.80 +1.25 +0.12 +0.57 +0.34 +0.43 8 +5708.98499849 6.96195867 13.73 +1.25 +0.15 +0.61 +0.43 +0.43 9 +5708.92226810 7.60488809 15.64 +1.24 +0.20 +0.65 +0.53 +0.43 10 +5708.85501459 7.04994434 17.60 +1.23 +0.26 +0.71 +0.65 +0.43 11 +5708.74998705 0.66515208 19.61 +1.24 +0.28 +0.73 +0.68 +0.43 12 +5708.74998705 0.66515208 20.27 +1.24 +0.28 +0.73 +0.68 +0.43 13 +5708.74196849 0.63226295 21.87 +1.24 +0.30 +0.75 +0.71 +0.43 14 +5708.73727047 0.58017832 23.75 +1.24 +0.32 +0.77 +0.74 +0.43 15 +5708.73604639 0.61369009 25.57 +1.25 +0.34 +0.79 +0.78 +0.43 16 +5708.73529069 0.03789562 27.46 +1.24 +0.33 +0.78 +0.77 +0.43 17 +5708.73529069 0.03789562 28.14 +1.24 +0.33 +0.78 +0.77 +0.43 18 +5708.73527830 0.01533739 30.09 +1.24 +0.33 +0.78 +0.77 +0.43 19 +5708.73527830 0.01533739 30.81 +1.24 +0.33 +0.78 +0.77 +0.43 20 +5708.73527781 0.00424492 32.80 +1.24 +0.33 +0.78 +0.77 +0.43 21 +5708.73527764 0.00102334 34.77 +1.24 +0.33 +0.78 +0.77 +0.43 [ Info: computing asymptotic variance if requested ┌ Warning: standard errors not yet implemented for this case └ @ Grumps ~/.julia/packages/Grumps/IRWfl/src/common/inference/ingredients.jl:14 Test Summary: | Pass Total Time Grumps.jl | 21 21 11m12.2s Testing Grumps tests passed Testing completed after 690.26s PkgEval succeeded after 805.31s