{ "cells": [ { "cell_type": "markdown", "id": "75c277ac", "metadata": {}, "source": [ "## Multivariate Linear Model - MultivariateLS\n", "\n", "This notebooks illustrates some features for the multivariate linear model estimated by least squares. \n", "The example is based on the UCLA stats example in https://stats.oarc.ucla.edu/stata/dae/multivariate-regression-analysis/ .\n", "\n", "The model assumes that a multivariate dependent variable depends linearly on the same set of explanatory variables.\n", "\n", "Y = X * B + u\n", "\n", "where \n", "- the dependent variable (endog) `Y` has shape (nobs, k_endog), \n", "- the matrix of explanatory variables including constant (exog) `X` has shape (nobs, k_exog), and\n", "- the parameter matrix `B` has shape (k_exog, k_endog), i.e. coefficients for explanatory variables in rows and dependent variables in columns.\n", "- the disturbance term `u` has the same shape as `Y`, (nobs, k_endog), and is assumed to have mean zero and to be uncorrelated with the exog `X`.\n", "\n", "Estimation is by least squares. The parameter estimates with common explanatory variables for each dependent variables corresponds to separate OLS estimates for each `endog`. The main advantage of the multivariate model is that we can make inference " ] }, { "cell_type": "code", "execution_count": 1, "id": "5e644acb", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:22.683061Z", "iopub.status.busy": "2026-07-29T11:31:22.682859Z", "iopub.status.idle": "2026-07-29T11:31:24.818238Z", "shell.execute_reply": "2026-07-29T11:31:24.814898Z" } }, "outputs": [], "source": [ "import os\n", "\n", "import pandas as pd\n", "\n", "from statsmodels.multivariate.manova import MANOVA\n", "from statsmodels.multivariate.multivariate_ols import MultivariateLS\n", "import statsmodels.multivariate.tests.results as path\n", "\n", "dir_path = os.path.dirname(os.path.abspath(path.__file__))\n", "csv_path = os.path.join(dir_path, \"mvreg.csv\")\n", "data_mvreg = pd.read_csv(csv_path)" ] }, { "cell_type": "code", "execution_count": 2, "id": "e851e0ca", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:24.820443Z", "iopub.status.busy": "2026-07-29T11:31:24.820217Z", "iopub.status.idle": "2026-07-29T11:31:24.851379Z", "shell.execute_reply": "2026-07-29T11:31:24.850549Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
locus_of_controlself_conceptmotivationreadwritescienceprog
0-1.1439550.7226410.36897337.40554839.03284533.532822academic
10.5041340.1113640.52031952.76078451.99504165.225044academic
21.6285460.6299340.43683859.77191554.65165364.604500academic
30.368096-0.138528-0.00432442.85432441.12135748.493809vocational
4-0.280190-0.4522261.25692454.75627949.94720850.381657academic
\n", "
" ], "text/plain": [ " locus_of_control self_concept motivation read write \\\n", "0 -1.143955 0.722641 0.368973 37.405548 39.032845 \n", "1 0.504134 0.111364 0.520319 52.760784 51.995041 \n", "2 1.628546 0.629934 0.436838 59.771915 54.651653 \n", "3 0.368096 -0.138528 -0.004324 42.854324 41.121357 \n", "4 -0.280190 -0.452226 1.256924 54.756279 49.947208 \n", "\n", " science prog \n", "0 33.532822 academic \n", "1 65.225044 academic \n", "2 64.604500 academic \n", "3 48.493809 vocational \n", "4 50.381657 academic " ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_mvreg.head()" ] }, { "cell_type": "code", "execution_count": 3, "id": "68ec2582", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:24.853173Z", "iopub.status.busy": "2026-07-29T11:31:24.852973Z", "iopub.status.idle": "2026-07-29T11:31:24.903993Z", "shell.execute_reply": "2026-07-29T11:31:24.900779Z" } }, "outputs": [], "source": [ "formula = \"locus_of_control + self_concept + motivation ~ read + write + science + prog\"\n", "mod = MultivariateLS.from_formula(formula, data=data_mvreg)\n", "res = mod.fit()" ] }, { "cell_type": "markdown", "id": "71687b33", "metadata": {}, "source": [ "### Multivariate hypothesis tests mv_test\n", "\n", "The `mv_test` method by default performs the hypothesis tests that each term in the formula has no effect on any of the dependent variables (`endog`). This is the same as the MANOVA test. \n", "Note, MANOVA in statsmodels is implemented as test on coefficients in the multivariate model and is not restricted to categorical variables. In the current example, we have three continuous and one categorical explanatory variables, in addition to the constant.\n", "\n", "Consequently, using mv_test in MultivariateLS and in MANOVA produces the same results.\n", "However. MANOVA only provides the hypothesis tests as feature, while MultivariateLS provide the usual model results.\n", "\n", "More general versions of the mv_test are for hypothesis in the form `L B M = C`.\n", "Here `L` are restrictions corresponding to explanatory variables, `M` are restrictions corresponding to dependent (endog) variables and `C` is a matrix of constants for affine restrictions. See docstrings for details." ] }, { "cell_type": "code", "execution_count": 4, "id": "6cb94da2", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:24.906131Z", "iopub.status.busy": "2026-07-29T11:31:24.905920Z", "iopub.status.idle": "2026-07-29T11:31:24.980639Z", "shell.execute_reply": "2026-07-29T11:31:24.979598Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
EffectStatistic
InterceptWilks' lambda0.8484673592.035.2428760.0
Pillai's trace0.1515333.0592.035.2428760.0
Hotelling-Lawley trace0.1785963592.035.2428760.0
Roy's greatest root0.178596359235.2428760.0
progWilks' lambda0.89143861184.011.6707650.0
Pillai's trace0.1086496.01186.011.3549630.0
Hotelling-Lawley trace0.1216856787.55806111.9961550.0
Roy's greatest root0.120878359323.8934560.0
readWilks' lambda0.9764253592.04.7644160.002727
Pillai's trace0.0235753.0592.04.7644160.002727
Hotelling-Lawley trace0.0241443592.04.7644160.002727
Roy's greatest root0.02414435924.7644160.002727
writeWilks' lambda0.9473943592.010.9573380.000001
Pillai's trace0.0526063.0592.010.9573380.000001
Hotelling-Lawley trace0.0555273592.010.9573380.000001
Roy's greatest root0.055527359210.9573380.000001
scienceWilks' lambda0.9834053592.03.3299110.019305
Pillai's trace0.0165953.0592.03.3299110.019305
Hotelling-Lawley trace0.0168753592.03.3299110.019305
Roy's greatest root0.01687535923.3299110.019305
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value \\\n", "Effect Statistic \n", "Intercept Wilks' lambda 0.848467 3 592.0 35.242876 \n", " Pillai's trace 0.151533 3.0 592.0 35.242876 \n", " Hotelling-Lawley trace 0.178596 3 592.0 35.242876 \n", " Roy's greatest root 0.178596 3 592 35.242876 \n", "prog Wilks' lambda 0.891438 6 1184.0 11.670765 \n", " Pillai's trace 0.108649 6.0 1186.0 11.354963 \n", " Hotelling-Lawley trace 0.121685 6 787.558061 11.996155 \n", " Roy's greatest root 0.120878 3 593 23.893456 \n", "read Wilks' lambda 0.976425 3 592.0 4.764416 \n", " Pillai's trace 0.023575 3.0 592.0 4.764416 \n", " Hotelling-Lawley trace 0.024144 3 592.0 4.764416 \n", " Roy's greatest root 0.024144 3 592 4.764416 \n", "write Wilks' lambda 0.947394 3 592.0 10.957338 \n", " Pillai's trace 0.052606 3.0 592.0 10.957338 \n", " Hotelling-Lawley trace 0.055527 3 592.0 10.957338 \n", " Roy's greatest root 0.055527 3 592 10.957338 \n", "science Wilks' lambda 0.983405 3 592.0 3.329911 \n", " Pillai's trace 0.016595 3.0 592.0 3.329911 \n", " Hotelling-Lawley trace 0.016875 3 592.0 3.329911 \n", " Roy's greatest root 0.016875 3 592 3.329911 \n", "\n", " Pr > F \n", "Effect Statistic \n", "Intercept Wilks' lambda 0.0 \n", " Pillai's trace 0.0 \n", " Hotelling-Lawley trace 0.0 \n", " Roy's greatest root 0.0 \n", "prog Wilks' lambda 0.0 \n", " Pillai's trace 0.0 \n", " Hotelling-Lawley trace 0.0 \n", " Roy's greatest root 0.0 \n", "read Wilks' lambda 0.002727 \n", " Pillai's trace 0.002727 \n", " Hotelling-Lawley trace 0.002727 \n", " Roy's greatest root 0.002727 \n", "write Wilks' lambda 0.000001 \n", " Pillai's trace 0.000001 \n", " Hotelling-Lawley trace 0.000001 \n", " Roy's greatest root 0.000001 \n", "science Wilks' lambda 0.019305 \n", " Pillai's trace 0.019305 \n", " Hotelling-Lawley trace 0.019305 \n", " Roy's greatest root 0.019305 " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mvt = res.mv_test()\n", "mvt.summary_frame" ] }, { "cell_type": "code", "execution_count": 5, "id": "b999e805", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:24.984427Z", "iopub.status.busy": "2026-07-29T11:31:24.984218Z", "iopub.status.idle": "2026-07-29T11:31:25.102454Z", "shell.execute_reply": "2026-07-29T11:31:25.101612Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
EffectStatistic
InterceptWilks' lambda0.8484673592.035.2428760.0
Pillai's trace0.1515333.0592.035.2428760.0
Hotelling-Lawley trace0.1785963592.035.2428760.0
Roy's greatest root0.178596359235.2428760.0
progWilks' lambda0.89143861184.011.6707650.0
Pillai's trace0.1086496.01186.011.3549630.0
Hotelling-Lawley trace0.1216856787.55806111.9961550.0
Roy's greatest root0.120878359323.8934560.0
readWilks' lambda0.9764253592.04.7644160.002727
Pillai's trace0.0235753.0592.04.7644160.002727
Hotelling-Lawley trace0.0241443592.04.7644160.002727
Roy's greatest root0.02414435924.7644160.002727
writeWilks' lambda0.9473943592.010.9573380.000001
Pillai's trace0.0526063.0592.010.9573380.000001
Hotelling-Lawley trace0.0555273592.010.9573380.000001
Roy's greatest root0.055527359210.9573380.000001
scienceWilks' lambda0.9834053592.03.3299110.019305
Pillai's trace0.0165953.0592.03.3299110.019305
Hotelling-Lawley trace0.0168753592.03.3299110.019305
Roy's greatest root0.01687535923.3299110.019305
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value \\\n", "Effect Statistic \n", "Intercept Wilks' lambda 0.848467 3 592.0 35.242876 \n", " Pillai's trace 0.151533 3.0 592.0 35.242876 \n", " Hotelling-Lawley trace 0.178596 3 592.0 35.242876 \n", " Roy's greatest root 0.178596 3 592 35.242876 \n", "prog Wilks' lambda 0.891438 6 1184.0 11.670765 \n", " Pillai's trace 0.108649 6.0 1186.0 11.354963 \n", " Hotelling-Lawley trace 0.121685 6 787.558061 11.996155 \n", " Roy's greatest root 0.120878 3 593 23.893456 \n", "read Wilks' lambda 0.976425 3 592.0 4.764416 \n", " Pillai's trace 0.023575 3.0 592.0 4.764416 \n", " Hotelling-Lawley trace 0.024144 3 592.0 4.764416 \n", " Roy's greatest root 0.024144 3 592 4.764416 \n", "write Wilks' lambda 0.947394 3 592.0 10.957338 \n", " Pillai's trace 0.052606 3.0 592.0 10.957338 \n", " Hotelling-Lawley trace 0.055527 3 592.0 10.957338 \n", " Roy's greatest root 0.055527 3 592 10.957338 \n", "science Wilks' lambda 0.983405 3 592.0 3.329911 \n", " Pillai's trace 0.016595 3.0 592.0 3.329911 \n", " Hotelling-Lawley trace 0.016875 3 592.0 3.329911 \n", " Roy's greatest root 0.016875 3 592 3.329911 \n", "\n", " Pr > F \n", "Effect Statistic \n", "Intercept Wilks' lambda 0.0 \n", " Pillai's trace 0.0 \n", " Hotelling-Lawley trace 0.0 \n", " Roy's greatest root 0.0 \n", "prog Wilks' lambda 0.0 \n", " Pillai's trace 0.0 \n", " Hotelling-Lawley trace 0.0 \n", " Roy's greatest root 0.0 \n", "read Wilks' lambda 0.002727 \n", " Pillai's trace 0.002727 \n", " Hotelling-Lawley trace 0.002727 \n", " Roy's greatest root 0.002727 \n", "write Wilks' lambda 0.000001 \n", " Pillai's trace 0.000001 \n", " Hotelling-Lawley trace 0.000001 \n", " Roy's greatest root 0.000001 \n", "science Wilks' lambda 0.019305 \n", " Pillai's trace 0.019305 \n", " Hotelling-Lawley trace 0.019305 \n", " Roy's greatest root 0.019305 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "manova = MANOVA.from_formula(formula, data=data_mvreg)\n", "manova.mv_test().summary_frame" ] }, { "cell_type": "markdown", "id": "ff1664a9", "metadata": {}, "source": [ "The core multivariate regression results are displayed by the `summary` method." ] }, { "cell_type": "code", "execution_count": 6, "id": "015cd62b", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.104926Z", "iopub.status.busy": "2026-07-29T11:31:25.104481Z", "iopub.status.idle": "2026-07-29T11:31:25.150810Z", "shell.execute_reply": "2026-07-29T11:31:25.150194Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " MultivariateLS Regression Results \n", "==============================================================================================================\n", "Dep. Variable: ['locus_of_control', 'self_concept', 'motivation'] No. Observations: 600\n", "Model: MultivariateLS Df Residuals: 594\n", "Method: Least Squares Df Model: 15\n", "Date: Wed, 29 Jul 2026 \n", "Time: 11:31:25 \n", "======================================================================================\n", " locus_of_control coef std err t P>|t| [0.025 0.975]\n", "--------------------------------------------------------------------------------------\n", "Intercept -1.4970 0.157 -9.505 0.000 -1.806 -1.188\n", "prog[T.general] -0.1278 0.064 -1.998 0.046 -0.253 -0.002\n", "prog[T.vocational] 0.1239 0.058 2.150 0.032 0.011 0.237\n", "read 0.0125 0.004 3.363 0.001 0.005 0.020\n", "write 0.0121 0.003 3.581 0.000 0.005 0.019\n", "science 0.0058 0.004 1.582 0.114 -0.001 0.013\n", "--------------------------------------------------------------------------------------\n", " self_concept coef std err t P>|t| [0.025 0.975]\n", "--------------------------------------------------------------------------------------\n", "Intercept -0.0959 0.179 -0.536 0.592 -0.447 0.255\n", "prog[T.general] -0.2765 0.073 -3.808 0.000 -0.419 -0.134\n", "prog[T.vocational] 0.1469 0.065 2.246 0.025 0.018 0.275\n", "read 0.0013 0.004 0.310 0.757 -0.007 0.010\n", "write -0.0043 0.004 -1.115 0.265 -0.012 0.003\n", "science 0.0053 0.004 1.284 0.200 -0.003 0.013\n", "--------------------------------------------------------------------------------------\n", " motivation coef std err t P>|t| [0.025 0.975]\n", "--------------------------------------------------------------------------------------\n", "Intercept -0.9505 0.198 -4.811 0.000 -1.339 -0.563\n", "prog[T.general] -0.3603 0.080 -4.492 0.000 -0.518 -0.203\n", "prog[T.vocational] 0.2594 0.072 3.589 0.000 0.117 0.401\n", "read 0.0097 0.005 2.074 0.038 0.001 0.019\n", "write 0.0175 0.004 4.122 0.000 0.009 0.026\n", "science -0.0090 0.005 -1.971 0.049 -0.018 -3.13e-05\n", "======================================================================================\n" ] } ], "source": [ "print(res.summary())" ] }, { "cell_type": "markdown", "id": "4fb028ed", "metadata": {}, "source": [ "The the standard results attributes for the parameter estimates like `params`, `bse`, `tvalues` and `pvalues`, are two dimensional arrays or dataframes with explanatory variables (`exog`) in rows and dependend (`endog`) variables in columns." ] }, { "cell_type": "code", "execution_count": 7, "id": "d1295b73", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.154860Z", "iopub.status.busy": "2026-07-29T11:31:25.152949Z", "iopub.status.idle": "2026-07-29T11:31:25.168078Z", "shell.execute_reply": "2026-07-29T11:31:25.167288Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
012
Intercept-1.496970-0.095858-0.950513
prog[T.general]-0.127795-0.276483-0.360329
prog[T.vocational]0.1238750.1468760.259367
read0.0125050.0013080.009674
write0.012145-0.0042930.017535
science0.0057610.005306-0.009001
\n", "
" ], "text/plain": [ " 0 1 2\n", "Intercept -1.496970 -0.095858 -0.950513\n", "prog[T.general] -0.127795 -0.276483 -0.360329\n", "prog[T.vocational] 0.123875 0.146876 0.259367\n", "read 0.012505 0.001308 0.009674\n", "write 0.012145 -0.004293 0.017535\n", "science 0.005761 0.005306 -0.009001" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.params" ] }, { "cell_type": "code", "execution_count": 8, "id": "cbb9042d", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.171858Z", "iopub.status.busy": "2026-07-29T11:31:25.170131Z", "iopub.status.idle": "2026-07-29T11:31:25.185209Z", "shell.execute_reply": "2026-07-29T11:31:25.183158Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
012
Intercept0.1574990.1787940.197563
prog[T.general]0.0639550.0726020.080224
prog[T.vocational]0.0576070.0653960.072261
read0.0037180.0042200.004664
write0.0033910.0038500.004254
science0.0036410.0041330.004567
\n", "
" ], "text/plain": [ " 0 1 2\n", "Intercept 0.157499 0.178794 0.197563\n", "prog[T.general] 0.063955 0.072602 0.080224\n", "prog[T.vocational] 0.057607 0.065396 0.072261\n", "read 0.003718 0.004220 0.004664\n", "write 0.003391 0.003850 0.004254\n", "science 0.003641 0.004133 0.004567" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.bse" ] }, { "cell_type": "code", "execution_count": 9, "id": "b9929394", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.189292Z", "iopub.status.busy": "2026-07-29T11:31:25.189060Z", "iopub.status.idle": "2026-07-29T11:31:25.207282Z", "shell.execute_reply": "2026-07-29T11:31:25.206330Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
012
Intercept4.887129e-200.5920660.000002
prog[T.general]4.615006e-020.0001550.000008
prog[T.vocational]3.193055e-020.0250750.000359
read8.192738e-040.7568010.038481
write3.700449e-040.2652140.000043
science1.141093e-010.1997650.049209
\n", "
" ], "text/plain": [ " 0 1 2\n", "Intercept 4.887129e-20 0.592066 0.000002\n", "prog[T.general] 4.615006e-02 0.000155 0.000008\n", "prog[T.vocational] 3.193055e-02 0.025075 0.000359\n", "read 8.192738e-04 0.756801 0.038481\n", "write 3.700449e-04 0.265214 0.000043\n", "science 1.141093e-01 0.199765 0.049209" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.pvalues" ] }, { "cell_type": "markdown", "id": "fd52087a", "metadata": {}, "source": [ "### General MV and Wald tests \n", "\n", "The multivariate linear model allows for multivariate test in the `L B M` form as well as standard wald tests on linear combination of parameters. \n", "\n", "The multivariate tests are based on eigenvalues or trace of the matrices. Wald tests are standard test base on the flattened (stacked) parameter array and their covariance, hypothesis are of the form `R b = c` where `b` is the column stacked parameter array. The tests are asymptotically equivalent under the model assumptions but differ in small samples.\n", "\n", "The linear restriction can be defined either as hypothesis matrices (numpy arrays) or as strings or list of strings.\n", "\n" ] }, { "cell_type": "code", "execution_count": 10, "id": "a0a1d9f2", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.210535Z", "iopub.status.busy": "2026-07-29T11:31:25.209593Z", "iopub.status.idle": "2026-07-29T11:31:25.222512Z", "shell.execute_reply": "2026-07-29T11:31:25.221766Z" } }, "outputs": [ { "data": { "text/plain": [ "(['locus_of_control', 'self_concept', 'motivation'],\n", " ['Intercept',\n", " 'prog[T.general]',\n", " 'prog[T.vocational]',\n", " 'read',\n", " 'write',\n", " 'science'])" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "yn = res.model.endog_names\n", "xn = res.model.exog_names\n", "yn, xn" ] }, { "cell_type": "code", "execution_count": 11, "id": "02982602", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.225447Z", "iopub.status.busy": "2026-07-29T11:31:25.225233Z", "iopub.status.idle": "2026-07-29T11:31:25.265288Z", "shell.execute_reply": "2026-07-29T11:31:25.264589Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
EffectStatistic
coefWilks' lambda0.9958031594.02.503730.114109
Pillai's trace0.0041971.0594.02.503730.114109
Hotelling-Lawley trace0.0042151594.02.503730.114109
Roy's greatest root0.00421515942.503730.114109
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value Pr > F\n", "Effect Statistic \n", "coef Wilks' lambda 0.995803 1 594.0 2.50373 0.114109\n", " Pillai's trace 0.004197 1.0 594.0 2.50373 0.114109\n", " Hotelling-Lawley trace 0.004215 1 594.0 2.50373 0.114109\n", " Roy's greatest root 0.004215 1 594 2.50373 0.114109" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# test for an individual coefficient\n", "\n", "mvt = res.mv_test(hypotheses=[(\"coef\", [\"science\"], [\"locus_of_control\"])])\n", "mvt.summary_frame" ] }, { "cell_type": "code", "execution_count": 12, "id": "b31d01db", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.268994Z", "iopub.status.busy": "2026-07-29T11:31:25.268776Z", "iopub.status.idle": "2026-07-29T11:31:25.286301Z", "shell.execute_reply": "2026-07-29T11:31:25.284770Z" } }, "outputs": [ { "data": { "text/plain": [ "(\n", " Test for Constraints \n", " ==============================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", " ------------------------------------------------------------------------------\n", " c0 0.0058 0.004 1.582 0.114 -0.001 0.013\n", " ==============================================================================,\n", " array(0.11410929))" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tt = res.t_test(\"ylocus_of_control_science\")\n", "tt, tt.pvalue" ] }, { "cell_type": "markdown", "id": "c22a61e4", "metadata": {}, "source": [ "We can use either mv_test or wald_test for the joint hypothesis that an explanatory variable has no effect on any of the dependent variables, that is all coefficient for the explanatory variable are zero.\n", "\n", "In this example, the pvalues agree at 3 decimals." ] }, { "cell_type": "code", "execution_count": 13, "id": "80b1e726", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.288353Z", "iopub.status.busy": "2026-07-29T11:31:25.288150Z", "iopub.status.idle": "2026-07-29T11:31:25.307715Z", "shell.execute_reply": "2026-07-29T11:31:25.306186Z" } }, "outputs": [ { "data": { "text/plain": [ "\n", "" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "wt = res.wald_test(\n", " [\"ylocus_of_control_science\", \"yself_concept_science\", \"ymotivation_science\"],\n", " scalar=True,\n", ")\n", "wt" ] }, { "cell_type": "code", "execution_count": 14, "id": "12c0f058", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.312663Z", "iopub.status.busy": "2026-07-29T11:31:25.312321Z", "iopub.status.idle": "2026-07-29T11:31:25.352807Z", "shell.execute_reply": "2026-07-29T11:31:25.351800Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
EffectStatistic
scienceWilks' lambda0.9834053592.03.3299110.019305
Pillai's trace0.0165953.0592.03.3299110.019305
Hotelling-Lawley trace0.0168753592.03.3299110.019305
Roy's greatest root0.01687535923.3299110.019305
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value Pr > F\n", "Effect Statistic \n", "science Wilks' lambda 0.983405 3 592.0 3.329911 0.019305\n", " Pillai's trace 0.016595 3.0 592.0 3.329911 0.019305\n", " Hotelling-Lawley trace 0.016875 3 592.0 3.329911 0.019305\n", " Roy's greatest root 0.016875 3 592 3.329911 0.019305" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mvt = res.mv_test(hypotheses=[(\"science\", [\"science\"], yn)])\n", "mvt.summary_frame" ] }, { "cell_type": "code", "execution_count": 15, "id": "335d0361", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.355064Z", "iopub.status.busy": "2026-07-29T11:31:25.354817Z", "iopub.status.idle": "2026-07-29T11:31:25.378135Z", "shell.execute_reply": "2026-07-29T11:31:25.376738Z" } }, "outputs": [ { "data": { "text/plain": [ "(\n", " Test for Constraints \n", " ==============================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", " ------------------------------------------------------------------------------\n", " c0 0.0058 0.004 1.582 0.114 -0.001 0.013\n", " c1 0.0053 0.004 1.284 0.200 -0.003 0.013\n", " c2 -0.0090 0.005 -1.971 0.049 -0.018 -3.13e-05\n", " ==============================================================================,\n", " array([0.11410929, 0.19976543, 0.0492095 ]))" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# t_test provides a vectorized results for each of the simple hypotheses\n", "\n", "tt = res.t_test(\n", " [\"ylocus_of_control_science\", \"yself_concept_science\", \"ymotivation_science\"]\n", ")\n", "tt, tt.pvalue" ] }, { "cell_type": "markdown", "id": "caf162f5", "metadata": {}, "source": [ "**Warning:** the naming pattern for the flattened parameter names used in `t_test` and `wald_test` might still change.\n", "\n", "The current pattern is `\"y{endog_name}_{exog_name}\"`.\n", "\n", "examples:" ] }, { "cell_type": "code", "execution_count": 16, "id": "6ca87db4", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.380003Z", "iopub.status.busy": "2026-07-29T11:31:25.379807Z", "iopub.status.idle": "2026-07-29T11:31:25.390714Z", "shell.execute_reply": "2026-07-29T11:31:25.390145Z" } }, "outputs": [ { "data": { "text/plain": [ "['ylocus_of_control_science', 'yself_concept_science', 'ymotivation_science']" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "[f\"y{endog_name}_{exog_name}\" for endog_name in yn for exog_name in [\"science\"]]" ] }, { "cell_type": "code", "execution_count": 17, "id": "f6f7418d", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.395471Z", "iopub.status.busy": "2026-07-29T11:31:25.395241Z", "iopub.status.idle": "2026-07-29T11:31:25.403749Z", "shell.execute_reply": "2026-07-29T11:31:25.403178Z" } }, "outputs": [ { "data": { "text/plain": [ "['ylocus_of_control_prog[T.general]',\n", " 'ylocus_of_control_prog[T.vocational]',\n", " 'yself_concept_prog[T.general]',\n", " 'yself_concept_prog[T.vocational]',\n", " 'ymotivation_prog[T.general]',\n", " 'ymotivation_prog[T.vocational]']" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "c = [\n", " f\"y{endog_name}_{exog_name}\"\n", " for endog_name in yn\n", " for exog_name in [\"prog[T.general]\", \"prog[T.vocational]\"]\n", "]\n", "c" ] }, { "cell_type": "markdown", "id": "9d0d1529", "metadata": {}, "source": [ "The previous restriction corresponds to the MANOVA type test that the categorical variable \"prog\" has no effect." ] }, { "cell_type": "code", "execution_count": 18, "id": "960cb28e", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.409248Z", "iopub.status.busy": "2026-07-29T11:31:25.406375Z", "iopub.status.idle": "2026-07-29T11:31:25.472220Z", "shell.execute_reply": "2026-07-29T11:31:25.470771Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
Statistic
Wilks' lambda0.89143861184.011.6707650.0
Pillai's trace0.1086496.01186.011.3549630.0
Hotelling-Lawley trace0.1216856787.55806111.9961550.0
Roy's greatest root0.120878359323.8934560.0
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value Pr > F\n", "Statistic \n", "Wilks' lambda 0.891438 6 1184.0 11.670765 0.0\n", "Pillai's trace 0.108649 6.0 1186.0 11.354963 0.0\n", "Hotelling-Lawley trace 0.121685 6 787.558061 11.996155 0.0\n", "Roy's greatest root 0.120878 3 593 23.893456 0.0" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mant = manova.mv_test().summary_frame\n", "mant.loc[\"prog\"] # [\"Pr > F\"].to_numpy()" ] }, { "cell_type": "code", "execution_count": 19, "id": "c2b5ae70", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.474283Z", "iopub.status.busy": "2026-07-29T11:31:25.474079Z", "iopub.status.idle": "2026-07-29T11:31:25.499201Z", "shell.execute_reply": "2026-07-29T11:31:25.497549Z" } }, "outputs": [ { "data": { "text/plain": [ "\n", "" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.wald_test(c, scalar=True)" ] }, { "cell_type": "markdown", "id": "ab386919", "metadata": {}, "source": [ "**Note:** The degrees of freedom differ across hypothesis test methods.\n", "The model can be considered as a multivariate model with nobs=600 in this case, or as a stacked model with \n", "nobs_total = nobs * k_endog = 1800.\n", "\n", "\n", "For within endog restriction, inference is based on the same covariance of the parameter estimates in MultivariateLS and OLS. The degrees of freedom in a single output OLS are df_resid = 600 - 6 = 594. Using the same degrees of freedom in MultivariateLS preserves the equivalence for the analysis of each endog. Using the total df_resid for hypothesis tests would make them more liberal.\n", "\n", "Asymptotic inference based on normal and chisquare distribution (`use_t=False`) is not affected by how df_resid are defined.\n", "\n", "It is not yet decided whether there will be additional options to choose different degrees of freedom in the Wald tests." ] }, { "cell_type": "code", "execution_count": 20, "id": "b0854ceb", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.502580Z", "iopub.status.busy": "2026-07-29T11:31:25.501555Z", "iopub.status.idle": "2026-07-29T11:31:25.513014Z", "shell.execute_reply": "2026-07-29T11:31:25.511551Z" } }, "outputs": [ { "data": { "text/plain": [ "594" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.df_resid" ] }, { "cell_type": "markdown", "id": "0b5411b1", "metadata": {}, "source": [ "Both mv_test and wald_test can be used to test hypothesis on contrasts between coefficients" ] }, { "cell_type": "code", "execution_count": 21, "id": "8deb82c3", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.515170Z", "iopub.status.busy": "2026-07-29T11:31:25.514964Z", "iopub.status.idle": "2026-07-29T11:31:25.524173Z", "shell.execute_reply": "2026-07-29T11:31:25.522763Z" } }, "outputs": [ { "data": { "text/plain": [ "['ylocus_of_control_prog[T.general] - ylocus_of_control_prog[T.vocational]',\n", " 'yself_concept_prog[T.general] - yself_concept_prog[T.vocational]',\n", " 'ymotivation_prog[T.general] - ymotivation_prog[T.vocational]']" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "c = [\n", " f\"y{endog_name}_prog[T.general] - y{endog_name}_prog[T.vocational]\"\n", " for endog_name in yn\n", "]\n", "c" ] }, { "cell_type": "code", "execution_count": 22, "id": "0e0ee5d7", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.527500Z", "iopub.status.busy": "2026-07-29T11:31:25.527299Z", "iopub.status.idle": "2026-07-29T11:31:25.545219Z", "shell.execute_reply": "2026-07-29T11:31:25.543616Z" } }, "outputs": [ { "data": { "text/plain": [ "\n", "" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.wald_test(c, scalar=True)" ] }, { "cell_type": "code", "execution_count": 23, "id": "cf983044", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.549224Z", "iopub.status.busy": "2026-07-29T11:31:25.548979Z", "iopub.status.idle": "2026-07-29T11:31:25.588372Z", "shell.execute_reply": "2026-07-29T11:31:25.585545Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
EffectStatistic
diff_progWilks' lambda0.8921763592.023.8488390.0
Pillai's trace0.1078243.0592.023.8488390.0
Hotelling-Lawley trace0.1208563592.023.8488390.0
Roy's greatest root0.120856359223.8488390.0
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value Pr > F\n", "Effect Statistic \n", "diff_prog Wilks' lambda 0.892176 3 592.0 23.848839 0.0\n", " Pillai's trace 0.107824 3.0 592.0 23.848839 0.0\n", " Hotelling-Lawley trace 0.120856 3 592.0 23.848839 0.0\n", " Roy's greatest root 0.120856 3 592 23.848839 0.0" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mvt = res.mv_test(\n", " hypotheses=[(\"diff_prog\", [\"prog[T.general] - prog[T.vocational]\"], yn)]\n", ")\n", "mvt.summary_frame" ] }, { "cell_type": "markdown", "id": "a1569e45", "metadata": {}, "source": [ "Example: hypothesis that coefficients are the same across endog equations.\n", "\n", "We can test that the difference between the parameters of the later two equation with the first equation are zero." ] }, { "cell_type": "code", "execution_count": 24, "id": "75ec5fe9", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.590606Z", "iopub.status.busy": "2026-07-29T11:31:25.590351Z", "iopub.status.idle": "2026-07-29T11:31:25.637519Z", "shell.execute_reply": "2026-07-29T11:31:25.635904Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
EffectStatistic
diff_progWilks' lambda0.867039121186.07.3078790.0
Pillai's trace0.1371412.01188.07.288190.0
Hotelling-Lawley trace0.1485312919.363217.3310420.0
Roy's greatest root0.10062565949.9618980.0
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value Pr > F\n", "Effect Statistic \n", "diff_prog Wilks' lambda 0.867039 12 1186.0 7.307879 0.0\n", " Pillai's trace 0.13714 12.0 1188.0 7.28819 0.0\n", " Hotelling-Lawley trace 0.14853 12 919.36321 7.331042 0.0\n", " Roy's greatest root 0.100625 6 594 9.961898 0.0" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mvt = res.mv_test(\n", " hypotheses=[\n", " (\n", " \"diff_prog\",\n", " xn,\n", " [\"self_concept - locus_of_control\", \"motivation - locus_of_control\"],\n", " )\n", " ]\n", ")\n", "mvt.summary_frame" ] }, { "cell_type": "markdown", "id": "1a0b8193", "metadata": {}, "source": [ "In a similar hypothesis test, we can test that equation have the same slope coefficients but can have different constants." ] }, { "cell_type": "code", "execution_count": 25, "id": "1c8aa712", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.640399Z", "iopub.status.busy": "2026-07-29T11:31:25.640177Z", "iopub.status.idle": "2026-07-29T11:31:25.650748Z", "shell.execute_reply": "2026-07-29T11:31:25.649333Z" } }, "outputs": [ { "data": { "text/plain": [ "['prog[T.general]', 'prog[T.vocational]', 'read', 'write', 'science']" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "xn[1:]" ] }, { "cell_type": "code", "execution_count": 26, "id": "04315196", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.654880Z", "iopub.status.busy": "2026-07-29T11:31:25.654596Z", "iopub.status.idle": "2026-07-29T11:31:25.700890Z", "shell.execute_reply": "2026-07-29T11:31:25.700152Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ValueNum DFDen DFF ValuePr > F
EffectStatistic
diff_progWilks' lambda0.879133101186.07.8903220.0
Pillai's trace0.12421210.01188.07.8667380.0
Hotelling-Lawley trace0.13367910886.754437.9182840.0
Roy's greatest root0.092581559410.9986790.0
\n", "
" ], "text/plain": [ " Value Num DF Den DF F Value Pr > F\n", "Effect Statistic \n", "diff_prog Wilks' lambda 0.879133 10 1186.0 7.890322 0.0\n", " Pillai's trace 0.124212 10.0 1188.0 7.866738 0.0\n", " Hotelling-Lawley trace 0.133679 10 886.75443 7.918284 0.0\n", " Roy's greatest root 0.092581 5 594 10.998679 0.0" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mvt = res.mv_test(\n", " hypotheses=[\n", " (\n", " \"diff_prog\",\n", " xn[1:],\n", " [\"self_concept - locus_of_control\", \"motivation - locus_of_control\"],\n", " )\n", " ]\n", ")\n", "mvt.summary_frame" ] }, { "cell_type": "markdown", "id": "3c55852a", "metadata": {}, "source": [ "### Prediction\n", "\n", "\n", "The regression model and its results instance have methods for prediction and residuals.\n", "\n", "Note, because the parameter estimates are the same as in the OLS estimate for individual endog, the predictions will also be the same between the MultivariateLS model and the set of individual OLS models." ] }, { "cell_type": "code", "execution_count": 27, "id": "ba92e621", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.706123Z", "iopub.status.busy": "2026-07-29T11:31:25.705854Z", "iopub.status.idle": "2026-07-29T11:31:25.730916Z", "shell.execute_reply": "2026-07-29T11:31:25.729352Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
locus_of_controlself_conceptmotivation
0-0.7819810.7592490.575027
10.3340750.0153880.635811
21.3421260.5394880.432337
30.426497-0.326337-0.012298
4-0.364810-0.4808461.255411
............
595-1.8495660.920851-0.318799
596-1.278212-1.080592-0.031575
597-1.060668-1.065596-1.577958
598-0.6619460.3681920.132774
599-0.1297600.7026981.020835
\n", "

600 rows × 3 columns

\n", "
" ], "text/plain": [ " locus_of_control self_concept motivation\n", "0 -0.781981 0.759249 0.575027\n", "1 0.334075 0.015388 0.635811\n", "2 1.342126 0.539488 0.432337\n", "3 0.426497 -0.326337 -0.012298\n", "4 -0.364810 -0.480846 1.255411\n", ".. ... ... ...\n", "595 -1.849566 0.920851 -0.318799\n", "596 -1.278212 -1.080592 -0.031575\n", "597 -1.060668 -1.065596 -1.577958\n", "598 -0.661946 0.368192 0.132774\n", "599 -0.129760 0.702698 1.020835\n", "\n", "[600 rows x 3 columns]" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.resid" ] }, { "cell_type": "code", "execution_count": 28, "id": "aa8885f4", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.735350Z", "iopub.status.busy": "2026-07-29T11:31:25.732831Z", "iopub.status.idle": "2026-07-29T11:31:25.743424Z", "shell.execute_reply": "2026-07-29T11:31:25.741980Z" } }, "outputs": [ { "data": { "text/plain": [ "array([[-0.36197321, -0.03660735, -0.2060539 ],\n", " [ 0.17005867, 0.09597616, -0.11549243],\n", " [ 0.28641963, 0.09044546, 0.00450077],\n", " ...,\n", " [ 0.6252098 , -0.23716973, 0.11864199],\n", " [-0.3024846 , -0.29586741, -0.47584179],\n", " [ 0.77574136, 0.2878978 , 0.42480766]], shape=(600, 3))" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.predict()" ] }, { "cell_type": "code", "execution_count": 29, "id": "bda82cf8", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.748943Z", "iopub.status.busy": "2026-07-29T11:31:25.748695Z", "iopub.status.idle": "2026-07-29T11:31:25.791101Z", "shell.execute_reply": "2026-07-29T11:31:25.789636Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
012
0-0.361973-0.036607-0.206054
10.1700590.095976-0.115492
20.2864200.0904450.004501
3-0.0584000.1878090.007974
40.0846210.0286200.001513
............
5950.1854580.0368970.034498
5960.3304080.0973290.489407
5970.625210-0.2371700.118642
598-0.302485-0.295867-0.475842
5990.7757410.2878980.424808
\n", "

600 rows × 3 columns

\n", "
" ], "text/plain": [ " 0 1 2\n", "0 -0.361973 -0.036607 -0.206054\n", "1 0.170059 0.095976 -0.115492\n", "2 0.286420 0.090445 0.004501\n", "3 -0.058400 0.187809 0.007974\n", "4 0.084621 0.028620 0.001513\n", ".. ... ... ...\n", "595 0.185458 0.036897 0.034498\n", "596 0.330408 0.097329 0.489407\n", "597 0.625210 -0.237170 0.118642\n", "598 -0.302485 -0.295867 -0.475842\n", "599 0.775741 0.287898 0.424808\n", "\n", "[600 rows x 3 columns]" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.predict(data_mvreg)" ] }, { "cell_type": "code", "execution_count": 30, "id": "2b0fec2d", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.793503Z", "iopub.status.busy": "2026-07-29T11:31:25.793229Z", "iopub.status.idle": "2026-07-29T11:31:25.817997Z", "shell.execute_reply": "2026-07-29T11:31:25.815102Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
locus_of_controlself_conceptmotivation
0-0.361973-0.036607-0.206054
10.1700590.095976-0.115492
20.2864200.0904450.004501
3-0.0584000.1878090.007974
40.0846210.0286200.001513
............
5950.1854580.0368970.034498
5960.3304080.0973290.489407
5970.625210-0.2371700.118642
598-0.302485-0.295867-0.475842
5990.7757410.2878980.424808
\n", "

600 rows × 3 columns

\n", "
" ], "text/plain": [ " locus_of_control self_concept motivation\n", "0 -0.361973 -0.036607 -0.206054\n", "1 0.170059 0.095976 -0.115492\n", "2 0.286420 0.090445 0.004501\n", "3 -0.058400 0.187809 0.007974\n", "4 0.084621 0.028620 0.001513\n", ".. ... ... ...\n", "595 0.185458 0.036897 0.034498\n", "596 0.330408 0.097329 0.489407\n", "597 0.625210 -0.237170 0.118642\n", "598 -0.302485 -0.295867 -0.475842\n", "599 0.775741 0.287898 0.424808\n", "\n", "[600 rows x 3 columns]" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.fittedvalues" ] }, { "cell_type": "markdown", "id": "fa6d30de", "metadata": {}, "source": [ "The predict methods can take user provided data for the explanatory variables, but currently are not able to automatically create sets of explanatory variables for interesting effects.\n", "\n", "In the following, we construct at dataframe that we can use to predict the conditional expectation of the dependent variables for each level of the categorical variable \"prog\" at the sample means of the continuous variables. " ] }, { "cell_type": "code", "execution_count": 31, "id": "7ae189fc", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.820372Z", "iopub.status.busy": "2026-07-29T11:31:25.820114Z", "iopub.status.idle": "2026-07-29T11:31:25.848812Z", "shell.execute_reply": "2026-07-29T11:31:25.848060Z" } }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
progreadwritescience
0academic51.90183352.38483351.763333
1vocational51.90183352.38483351.763333
2general51.90183352.38483351.763333
\n", "
" ], "text/plain": [ " prog read write science\n", "0 academic 51.901833 52.384833 51.763333\n", "1 vocational 51.901833 52.384833 51.763333\n", "2 general 51.901833 52.384833 51.763333" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_exog = data_mvreg[[\"read\", \"write\", \"science\", \"prog\"]]\n", "\n", "ex = pd.DataFrame(data_exog[\"prog\"].unique(), columns=[\"prog\"])\n", "mean_ex = data_mvreg[[\"read\", \"write\", \"science\"]].mean()\n", "\n", "ex.loc[:, [\"read\", \"write\", \"science\"]] = mean_ex.values\n", "ex" ] }, { "cell_type": "code", "execution_count": 32, "id": "773618e1", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.854749Z", "iopub.status.busy": "2026-07-29T11:31:25.854465Z", "iopub.status.idle": "2026-07-29T11:31:25.928587Z", "shell.execute_reply": "2026-07-29T11:31:25.927622Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "predicted mean by 'prog':\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
locus_of_controlself_conceptmotivation
prog
academic0.0864930.0217520.004209
vocational0.2103680.1686280.263575
general-0.041303-0.254731-0.356121
\n", "
" ], "text/plain": [ " locus_of_control self_concept motivation\n", "prog \n", "academic 0.086493 0.021752 0.004209\n", "vocational 0.210368 0.168628 0.263575\n", "general -0.041303 -0.254731 -0.356121" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pred = res.predict(ex)\n", "\n", "pred.index = ex[\"prog\"]\n", "pred.columns = res.fittedvalues.columns\n", "print(\"predicted mean by 'prog':\")\n", "pred" ] }, { "cell_type": "markdown", "id": "69a05b73", "metadata": {}, "source": [ "## Outlier-Influence\n", "\n", "This is currently in draft version. \n", "`resid_distance` is a one dimensional residual measure based on Mahalanobis distance for each sample observation. \n", "The hat matrix in the MultivariateLS model is the same as in OLS, the diagonal of the hat matrix is temporarily attached as `results._hat_matrix_diag`.\n", "\n", "Note, individual components of the multivariate dependent variable can be analyzed with OLS and are available in the corresponding post-estimation methods like `OLSInfluence`." ] }, { "cell_type": "code", "execution_count": 33, "id": "d69a12c7", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.931398Z", "iopub.status.busy": "2026-07-29T11:31:25.931154Z", "iopub.status.idle": "2026-07-29T11:31:25.941632Z", "shell.execute_reply": "2026-07-29T11:31:25.940253Z" } }, "outputs": [ { "data": { "text/plain": [ "array([3.74332128, 0.95395412, 5.15221877, 0.82580531, 4.5260778 ])" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.resid_distance[:5]" ] }, { "cell_type": "code", "execution_count": 34, "id": "1f885722", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.948913Z", "iopub.status.busy": "2026-07-29T11:31:25.945517Z", "iopub.status.idle": "2026-07-29T11:31:25.957475Z", "shell.execute_reply": "2026-07-29T11:31:25.955919Z" } }, "outputs": [ { "data": { "text/plain": [ "array([[0.36844484, 0.05748939, 0.06050103],\n", " [0.05748939, 0.4748153 , 0.13103368],\n", " [0.06050103, 0.13103368, 0.57973305]])" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "res.cov_resid" ] }, { "cell_type": "code", "execution_count": 35, "id": "542b5eb3", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:25.964315Z", "iopub.status.busy": "2026-07-29T11:31:25.964085Z", "iopub.status.idle": "2026-07-29T11:31:27.036569Z", "shell.execute_reply": "2026-07-29T11:31:27.035784Z" } }, "outputs": [], "source": [ "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 36, "id": "3d21fc8c", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:27.043602Z", "iopub.status.busy": "2026-07-29T11:31:27.039701Z", "iopub.status.idle": "2026-07-29T11:31:27.488374Z", "shell.execute_reply": "2026-07-29T11:31:27.485592Z" } }, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot(res.resid_distance)" ] }, { "cell_type": "code", "execution_count": 37, "id": "adff83a3", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:27.491029Z", "iopub.status.busy": "2026-07-29T11:31:27.490786Z", "iopub.status.idle": "2026-07-29T11:31:27.870554Z", "shell.execute_reply": "2026-07-29T11:31:27.866445Z" } }, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot(res._hat_matrix_diag)" ] }, { "cell_type": "code", "execution_count": 38, "id": "b56d845f", "metadata": { "execution": { "iopub.execute_input": "2026-07-29T11:31:27.875563Z", "iopub.status.busy": "2026-07-29T11:31:27.875334Z", "iopub.status.idle": "2026-07-29T11:31:28.029469Z", "shell.execute_reply": "2026-07-29T11:31:28.028689Z" } }, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot(res._hat_matrix_diag, res.resid_distance, \".\")" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.14.6" } }, "nbformat": 4, "nbformat_minor": 5 }