ml-finance-python
python scripts for finance machine learning
git clone https://9o.is/git/ml-finance-python.git
02_fama_macbeth.ipynb
(299451B)
1 {
2 "cells": [
3 {
4 "cell_type": "markdown",
5 "metadata": {},
6 "source": [
7 "# How to build a linear factor model"
8 ]
9 },
10 {
11 "cell_type": "markdown",
12 "metadata": {},
13 "source": [
14 "Algorithmic trading strategies use linear factor models to quantify the relationship between the return of an asset and the sources of risk that represent the main drivers of these returns. Each factor risk carries a premium, and the total asset return can be expected to correspond to a weighted average of these risk premia."
15 ]
16 },
17 {
18 "cell_type": "markdown",
19 "metadata": {},
20 "source": [
21 "There are several practical applications of factor models across the portfolio management process from construction and asset selection to risk management and performance evaluation. The importance of factor models continues to grow as common risk factors are now tradeable:\n",
22 "\n",
23 "- A summary of the returns of many assets by a much smaller number of factors reduces the amount of data required to estimate the covariance matrix when optimizing a portfolio\n",
24 "- An estimate of the exposure of an asset or a portfolio to these factors allows for the management of the resultant risk, for instance by entering suitable hedges when risk factors are themselves traded\n",
25 "- A factor model also permits the assessment of the incremental signal content of new alpha factors\n",
26 "- A factor model can also help assess whether a manager's performance relative to a benchmark is indeed due to skill in selecting assets and timing the market, or if instead, the performance can be explained by portfolio tilts towards known return drivers that can today be replicated as low-cost, passively managed funds without incurring active management fees"
27 ]
28 },
29 {
30 "cell_type": "markdown",
31 "metadata": {},
32 "source": [
33 "## Imports & Settings"
34 ]
35 },
36 {
37 "cell_type": "code",
38 "execution_count": 9,
39 "metadata": {
40 "ExecuteTime": {
41 "end_time": "2018-10-31T19:06:59.441313Z",
42 "start_time": "2018-10-31T19:06:59.436355Z"
43 }
44 },
45 "outputs": [],
46 "source": [
47 "from pprint import pprint\n",
48 "from pandas_datareader.famafrench import get_available_datasets\n",
49 "import pandas as pd\n",
50 "import numpy as np\n",
51 "import matplotlib.pyplot as plt\n",
52 "import seaborn as sns\n",
53 "from statsmodels.api import OLS, add_constant\n",
54 "from pathlib import Path\n",
55 "import warnings\n",
56 "from linearmodels.asset_pricing import TradedFactorModel, LinearFactorModel, LinearFactorModelGMM"
57 ]
58 },
59 {
60 "cell_type": "code",
61 "execution_count": 10,
62 "metadata": {},
63 "outputs": [],
64 "source": [
65 "# due to https://stackoverflow.com/questions/50394873/import-pandas-datareader-gives-importerror-cannot-import-name-is-list-like\n",
66 "# may become obsolete when fixed\n",
67 "pd.core.common.is_list_like = pd.api.types.is_list_like\n",
68 "import pandas_datareader.data as web"
69 ]
70 },
71 {
72 "cell_type": "code",
73 "execution_count": 11,
74 "metadata": {
75 "ExecuteTime": {
76 "end_time": "2018-10-31T19:06:59.454106Z",
77 "start_time": "2018-10-31T19:06:59.442562Z"
78 }
79 },
80 "outputs": [],
81 "source": [
82 "warnings.filterwarnings('ignore')\n",
83 "plt.style.use('fivethirtyeight')"
84 ]
85 },
86 {
87 "cell_type": "markdown",
88 "metadata": {},
89 "source": [
90 "## Get Data"
91 ]
92 },
93 {
94 "cell_type": "markdown",
95 "metadata": {},
96 "source": [
97 "Fama and French make updated risk factor and research portfolio data available through their [website](http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html), and you can use the `pandas_datareader` package to obtain the data."
98 ]
99 },
100 {
101 "cell_type": "markdown",
102 "metadata": {},
103 "source": [
104 "### Risk Factors"
105 ]
106 },
107 {
108 "cell_type": "markdown",
109 "metadata": {},
110 "source": [
111 "In particular, we will be using the five Fama—French factors that result from sorting stocks first into three size groups and then into two for each of the remaining three firm-specific factors. \n",
112 "\n",
113 "Hence, the factors involve three sets of value-weighted portfolios formed as 3 x 2 sorts on size and book-to-market, size and operating profitability, and size and investment. The risk factor values computed as the average returns of the portfolios (PF) as outlined in the following table:"
114 ]
115 },
116 {
117 "cell_type": "markdown",
118 "metadata": {},
119 "source": [
120 "| Label | Name | Description |\n",
121 "|-------|-------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n",
122 "| SMB | Small Minus Big | Average return on the nine small stock portfolios minus the average return on the nine big stock portfolios |\n",
123 "| HML | High Minus Low | Average return on the two value portfolios minus the average return on the two growth portfolios |\n",
124 "| RMW | Robust minus Weak | Average return on the two robust operating profitability portfolios minus the average return on the two weak operating profitability portfolios |\n",
125 "| CMA | Conservative Minus Aggressive | Average return on the two conservative investment portfolios minus the average return on the two aggressive investment portfolios |\n",
126 "| Rm-Rf | Excess return on the market | Value-weight return of all firms incorporated in the US and listed on the NYSE, AMEX, or NASDAQ at the beginning of month t with 'good' data for t minus the one-month Treasury bill rate |"
127 ]
128 },
129 {
130 "attachments": {},
131 "cell_type": "markdown",
132 "metadata": {},
133 "source": [
134 "The Fama-French 5 factors are based on the 6 value-weight portfolios formed on size and book-to-market, the 6 value-weight portfolios formed on size and operating profitability, and the 6 value-weight portfolios formed on size and investment."
135 ]
136 },
137 {
138 "cell_type": "markdown",
139 "metadata": {},
140 "source": [
141 "We will use returns at a monthly frequency that we obtain for the period 2010 – 2017 as follows:"
142 ]
143 },
144 {
145 "cell_type": "code",
146 "execution_count": 12,
147 "metadata": {
148 "ExecuteTime": {
149 "end_time": "2018-10-31T19:09:08.844990Z",
150 "start_time": "2018-10-31T19:09:08.788545Z"
151 }
152 },
153 "outputs": [
154 {
155 "name": "stdout",
156 "output_type": "stream",
157 "text": [
158 "<class 'pandas.core.frame.DataFrame'>\n",
159 "PeriodIndex: 96 entries, 2010-01 to 2017-12\n",
160 "Freq: M\n",
161 "Data columns (total 6 columns):\n",
162 "Mkt-RF 96 non-null float64\n",
163 "SMB 96 non-null float64\n",
164 "HML 96 non-null float64\n",
165 "RMW 96 non-null float64\n",
166 "CMA 96 non-null float64\n",
167 "RF 96 non-null float64\n",
168 "dtypes: float64(6)\n",
169 "memory usage: 5.2 KB\n"
170 ]
171 }
172 ],
173 "source": [
174 "ff_factor = 'F-F_Research_Data_5_Factors_2x3'\n",
175 "ff_factor_data = web.DataReader(ff_factor, 'famafrench', start='2010', end='2017-12')[0]\n",
176 "ff_factor_data.info()"
177 ]
178 },
179 {
180 "cell_type": "code",
181 "execution_count": 13,
182 "metadata": {
183 "ExecuteTime": {
184 "end_time": "2018-10-31T19:09:10.429747Z",
185 "start_time": "2018-10-31T19:09:10.409843Z"
186 }
187 },
188 "outputs": [
189 {
190 "data": {
191 "text/html": [
192 "<div>\n",
193 "<style scoped>\n",
194 " .dataframe tbody tr th:only-of-type {\n",
195 " vertical-align: middle;\n",
196 " }\n",
197 "\n",
198 " .dataframe tbody tr th {\n",
199 " vertical-align: top;\n",
200 " }\n",
201 "\n",
202 " .dataframe thead th {\n",
203 " text-align: right;\n",
204 " }\n",
205 "</style>\n",
206 "<table border=\"1\" class=\"dataframe\">\n",
207 " <thead>\n",
208 " <tr style=\"text-align: right;\">\n",
209 " <th></th>\n",
210 " <th>Mkt-RF</th>\n",
211 " <th>SMB</th>\n",
212 " <th>HML</th>\n",
213 " <th>RMW</th>\n",
214 " <th>CMA</th>\n",
215 " <th>RF</th>\n",
216 " </tr>\n",
217 " </thead>\n",
218 " <tbody>\n",
219 " <tr>\n",
220 " <th>count</th>\n",
221 " <td>96.000000</td>\n",
222 " <td>96.000000</td>\n",
223 " <td>96.000000</td>\n",
224 " <td>96.000000</td>\n",
225 " <td>96.000000</td>\n",
226 " <td>96.000000</td>\n",
227 " </tr>\n",
228 " <tr>\n",
229 " <th>mean</th>\n",
230 " <td>1.158437</td>\n",
231 " <td>0.055313</td>\n",
232 " <td>-0.064271</td>\n",
233 " <td>0.143437</td>\n",
234 " <td>0.044792</td>\n",
235 " <td>0.012604</td>\n",
236 " </tr>\n",
237 " <tr>\n",
238 " <th>std</th>\n",
239 " <td>3.579997</td>\n",
240 " <td>2.296648</td>\n",
241 " <td>2.197928</td>\n",
242 " <td>1.550179</td>\n",
243 " <td>1.410603</td>\n",
244 " <td>0.022583</td>\n",
245 " </tr>\n",
246 " <tr>\n",
247 " <th>min</th>\n",
248 " <td>-7.890000</td>\n",
249 " <td>-4.550000</td>\n",
250 " <td>-4.500000</td>\n",
251 " <td>-4.000000</td>\n",
252 " <td>-3.340000</td>\n",
253 " <td>0.000000</td>\n",
254 " </tr>\n",
255 " <tr>\n",
256 " <th>25%</th>\n",
257 " <td>-0.917500</td>\n",
258 " <td>-1.592500</td>\n",
259 " <td>-1.517500</td>\n",
260 " <td>-1.040000</td>\n",
261 " <td>-0.972500</td>\n",
262 " <td>0.000000</td>\n",
263 " </tr>\n",
264 " <tr>\n",
265 " <th>50%</th>\n",
266 " <td>1.235000</td>\n",
267 " <td>0.165000</td>\n",
268 " <td>-0.285000</td>\n",
269 " <td>0.120000</td>\n",
270 " <td>-0.030000</td>\n",
271 " <td>0.000000</td>\n",
272 " </tr>\n",
273 " <tr>\n",
274 " <th>75%</th>\n",
275 " <td>3.190000</td>\n",
276 " <td>1.502500</td>\n",
277 " <td>1.125000</td>\n",
278 " <td>1.140000</td>\n",
279 " <td>0.932500</td>\n",
280 " <td>0.010000</td>\n",
281 " </tr>\n",
282 " <tr>\n",
283 " <th>max</th>\n",
284 " <td>11.350000</td>\n",
285 " <td>6.870000</td>\n",
286 " <td>8.320000</td>\n",
287 " <td>3.510000</td>\n",
288 " <td>3.630000</td>\n",
289 " <td>0.090000</td>\n",
290 " </tr>\n",
291 " </tbody>\n",
292 "</table>\n",
293 "</div>"
294 ],
295 "text/plain": [
296 " Mkt-RF SMB HML RMW CMA RF\n",
297 "count 96.000000 96.000000 96.000000 96.000000 96.000000 96.000000\n",
298 "mean 1.158437 0.055313 -0.064271 0.143437 0.044792 0.012604\n",
299 "std 3.579997 2.296648 2.197928 1.550179 1.410603 0.022583\n",
300 "min -7.890000 -4.550000 -4.500000 -4.000000 -3.340000 0.000000\n",
301 "25% -0.917500 -1.592500 -1.517500 -1.040000 -0.972500 0.000000\n",
302 "50% 1.235000 0.165000 -0.285000 0.120000 -0.030000 0.000000\n",
303 "75% 3.190000 1.502500 1.125000 1.140000 0.932500 0.010000\n",
304 "max 11.350000 6.870000 8.320000 3.510000 3.630000 0.090000"
305 ]
306 },
307 "execution_count": 13,
308 "metadata": {},
309 "output_type": "execute_result"
310 }
311 ],
312 "source": [
313 "ff_factor_data.describe()"
314 ]
315 },
316 {
317 "cell_type": "markdown",
318 "metadata": {},
319 "source": [
320 "### Portfolios"
321 ]
322 },
323 {
324 "cell_type": "markdown",
325 "metadata": {},
326 "source": [
327 "Fama and French also make available numerous portfolios that we can illustrate the estimation of the factor exposures, as well as the value of the risk premia available in the market for a given time period. We will use a panel of the 17 industry portfolios at a monthly frequency. \n",
328 "\n",
329 "We will subtract the risk-free rate from the returns because the factor model works with excess returns:"
330 ]
331 },
332 {
333 "cell_type": "code",
334 "execution_count": 14,
335 "metadata": {
336 "ExecuteTime": {
337 "end_time": "2018-10-31T19:10:02.230357Z",
338 "start_time": "2018-10-31T19:10:01.966839Z"
339 }
340 },
341 "outputs": [
342 {
343 "name": "stdout",
344 "output_type": "stream",
345 "text": [
346 "<class 'pandas.core.frame.DataFrame'>\n",
347 "PeriodIndex: 96 entries, 2010-01 to 2017-12\n",
348 "Freq: M\n",
349 "Data columns (total 17 columns):\n",
350 "Food 96 non-null float64\n",
351 "Mines 96 non-null float64\n",
352 "Oil 96 non-null float64\n",
353 "Clths 96 non-null float64\n",
354 "Durbl 96 non-null float64\n",
355 "Chems 96 non-null float64\n",
356 "Cnsum 96 non-null float64\n",
357 "Cnstr 96 non-null float64\n",
358 "Steel 96 non-null float64\n",
359 "FabPr 96 non-null float64\n",
360 "Machn 96 non-null float64\n",
361 "Cars 96 non-null float64\n",
362 "Trans 96 non-null float64\n",
363 "Utils 96 non-null float64\n",
364 "Rtail 96 non-null float64\n",
365 "Finan 96 non-null float64\n",
366 "Other 96 non-null float64\n",
367 "dtypes: float64(17)\n",
368 "memory usage: 13.5 KB\n"
369 ]
370 }
371 ],
372 "source": [
373 "ff_portfolio = '17_Industry_Portfolios'\n",
374 "ff_portfolio_data = web.DataReader(ff_portfolio, 'famafrench', start='2010', end='2017-12')[0]\n",
375 "ff_portfolio_data = ff_portfolio_data.sub(ff_factor_data.RF, axis=0)\n",
376 "ff_portfolio_data.info()"
377 ]
378 },
379 {
380 "cell_type": "code",
381 "execution_count": 39,
382 "metadata": {
383 "ExecuteTime": {
384 "end_time": "2018-10-31T19:10:02.874556Z",
385 "start_time": "2018-10-31T19:10:02.814899Z"
386 }
387 },
388 "outputs": [
389 {
390 "data": {
391 "text/html": [
392 "<div>\n",
393 "<style scoped>\n",
394 " .dataframe tbody tr th:only-of-type {\n",
395 " vertical-align: middle;\n",
396 " }\n",
397 "\n",
398 " .dataframe tbody tr th {\n",
399 " vertical-align: top;\n",
400 " }\n",
401 "\n",
402 " .dataframe thead th {\n",
403 " text-align: right;\n",
404 " }\n",
405 "</style>\n",
406 "<table border=\"1\" class=\"dataframe\">\n",
407 " <thead>\n",
408 " <tr style=\"text-align: right;\">\n",
409 " <th></th>\n",
410 " <th>Food</th>\n",
411 " <th>Mines</th>\n",
412 " <th>Oil</th>\n",
413 " <th>Clths</th>\n",
414 " <th>Durbl</th>\n",
415 " <th>Chems</th>\n",
416 " <th>Cnsum</th>\n",
417 " <th>Cnstr</th>\n",
418 " <th>Steel</th>\n",
419 " <th>FabPr</th>\n",
420 " <th>Machn</th>\n",
421 " <th>Cars</th>\n",
422 " <th>Trans</th>\n",
423 " <th>Utils</th>\n",
424 " <th>Rtail</th>\n",
425 " <th>Finan</th>\n",
426 " <th>Other</th>\n",
427 " </tr>\n",
428 " </thead>\n",
429 " <tbody>\n",
430 " <tr>\n",
431 " <th>count</th>\n",
432 " <td>96.000000</td>\n",
433 " <td>96.000000</td>\n",
434 " <td>96.000000</td>\n",
435 " <td>96.000000</td>\n",
436 " <td>96.000000</td>\n",
437 " <td>96.000000</td>\n",
438 " <td>96.000000</td>\n",
439 " <td>96.000000</td>\n",
440 " <td>96.000000</td>\n",
441 " <td>96.000000</td>\n",
442 " <td>96.000000</td>\n",
443 " <td>96.000000</td>\n",
444 " <td>96.000000</td>\n",
445 " <td>96.000000</td>\n",
446 " <td>96.000000</td>\n",
447 " <td>96.000000</td>\n",
448 " <td>96.000000</td>\n",
449 " </tr>\n",
450 " <tr>\n",
451 " <th>mean</th>\n",
452 " <td>1.045625</td>\n",
453 " <td>0.203229</td>\n",
454 " <td>0.550833</td>\n",
455 " <td>1.396979</td>\n",
456 " <td>1.154896</td>\n",
457 " <td>1.303438</td>\n",
458 " <td>1.136875</td>\n",
459 " <td>1.731250</td>\n",
460 " <td>0.555625</td>\n",
461 " <td>1.351042</td>\n",
462 " <td>1.227604</td>\n",
463 " <td>1.278854</td>\n",
464 " <td>1.465521</td>\n",
465 " <td>0.891250</td>\n",
466 " <td>1.234375</td>\n",
467 " <td>1.243646</td>\n",
468 " <td>1.282187</td>\n",
469 " </tr>\n",
470 " <tr>\n",
471 " <th>std</th>\n",
472 " <td>2.795857</td>\n",
473 " <td>7.902683</td>\n",
474 " <td>5.573364</td>\n",
475 " <td>5.025167</td>\n",
476 " <td>5.137095</td>\n",
477 " <td>5.594231</td>\n",
478 " <td>3.174680</td>\n",
479 " <td>5.246562</td>\n",
480 " <td>7.389824</td>\n",
481 " <td>4.694688</td>\n",
482 " <td>4.811242</td>\n",
483 " <td>5.718887</td>\n",
484 " <td>4.151203</td>\n",
485 " <td>3.237306</td>\n",
486 " <td>3.508655</td>\n",
487 " <td>4.808350</td>\n",
488 " <td>3.711170</td>\n",
489 " </tr>\n",
490 " <tr>\n",
491 " <th>min</th>\n",
492 " <td>-5.170000</td>\n",
493 " <td>-24.380000</td>\n",
494 " <td>-11.990000</td>\n",
495 " <td>-10.000000</td>\n",
496 " <td>-13.210000</td>\n",
497 " <td>-17.390000</td>\n",
498 " <td>-7.300000</td>\n",
499 " <td>-13.960000</td>\n",
500 " <td>-20.490000</td>\n",
501 " <td>-11.960000</td>\n",
502 " <td>-9.080000</td>\n",
503 " <td>-11.650000</td>\n",
504 " <td>-8.560000</td>\n",
505 " <td>-6.990000</td>\n",
506 " <td>-9.180000</td>\n",
507 " <td>-11.020000</td>\n",
508 " <td>-7.920000</td>\n",
509 " </tr>\n",
510 " <tr>\n",
511 " <th>25%</th>\n",
512 " <td>-0.785000</td>\n",
513 " <td>-5.832500</td>\n",
514 " <td>-3.160000</td>\n",
515 " <td>-1.865000</td>\n",
516 " <td>-2.017500</td>\n",
517 " <td>-1.445000</td>\n",
518 " <td>-0.920000</td>\n",
519 " <td>-2.462500</td>\n",
520 " <td>-4.410000</td>\n",
521 " <td>-1.447500</td>\n",
522 " <td>-2.047500</td>\n",
523 " <td>-1.245000</td>\n",
524 " <td>-0.880000</td>\n",
525 " <td>-0.745000</td>\n",
526 " <td>-0.962500</td>\n",
527 " <td>-1.447500</td>\n",
528 " <td>-1.067500</td>\n",
529 " </tr>\n",
530 " <tr>\n",
531 " <th>50%</th>\n",
532 " <td>0.930000</td>\n",
533 " <td>-0.415000</td>\n",
534 " <td>1.050000</td>\n",
535 " <td>1.160000</td>\n",
536 " <td>1.205000</td>\n",
537 " <td>1.435000</td>\n",
538 " <td>1.475000</td>\n",
539 " <td>2.190000</td>\n",
540 " <td>0.660000</td>\n",
541 " <td>1.485000</td>\n",
542 " <td>1.545000</td>\n",
543 " <td>0.645000</td>\n",
544 " <td>1.505000</td>\n",
545 " <td>1.215000</td>\n",
546 " <td>0.880000</td>\n",
547 " <td>1.940000</td>\n",
548 " <td>1.580000</td>\n",
549 " </tr>\n",
550 " <tr>\n",
551 " <th>75%</th>\n",
552 " <td>3.187500</td>\n",
553 " <td>5.707500</td>\n",
554 " <td>3.912500</td>\n",
555 " <td>3.857500</td>\n",
556 " <td>4.315000</td>\n",
557 " <td>4.442500</td>\n",
558 " <td>3.317500</td>\n",
559 " <td>5.390000</td>\n",
560 " <td>4.220000</td>\n",
561 " <td>3.875000</td>\n",
562 " <td>4.657500</td>\n",
563 " <td>4.802500</td>\n",
564 " <td>4.227500</td>\n",
565 " <td>2.965000</td>\n",
566 " <td>3.355000</td>\n",
567 " <td>4.052500</td>\n",
568 " <td>3.525000</td>\n",
569 " </tr>\n",
570 " <tr>\n",
571 " <th>max</th>\n",
572 " <td>6.670000</td>\n",
573 " <td>21.920000</td>\n",
574 " <td>16.240000</td>\n",
575 " <td>17.200000</td>\n",
576 " <td>16.580000</td>\n",
577 " <td>18.370000</td>\n",
578 " <td>8.290000</td>\n",
579 " <td>15.550000</td>\n",
580 " <td>21.350000</td>\n",
581 " <td>17.660000</td>\n",
582 " <td>14.650000</td>\n",
583 " <td>20.860000</td>\n",
584 " <td>13.160000</td>\n",
585 " <td>7.900000</td>\n",
586 " <td>12.360000</td>\n",
587 " <td>13.430000</td>\n",
588 " <td>10.800000</td>\n",
589 " </tr>\n",
590 " </tbody>\n",
591 "</table>\n",
592 "</div>"
593 ],
594 "text/plain": [
595 " Food Mines Oil Clths Durbl Chems \\\n",
596 "count 96.000000 96.000000 96.000000 96.000000 96.000000 96.000000 \n",
597 "mean 1.045625 0.203229 0.550833 1.396979 1.154896 1.303438 \n",
598 "std 2.795857 7.902683 5.573364 5.025167 5.137095 5.594231 \n",
599 "min -5.170000 -24.380000 -11.990000 -10.000000 -13.210000 -17.390000 \n",
600 "25% -0.785000 -5.832500 -3.160000 -1.865000 -2.017500 -1.445000 \n",
601 "50% 0.930000 -0.415000 1.050000 1.160000 1.205000 1.435000 \n",
602 "75% 3.187500 5.707500 3.912500 3.857500 4.315000 4.442500 \n",
603 "max 6.670000 21.920000 16.240000 17.200000 16.580000 18.370000 \n",
604 "\n",
605 " Cnsum Cnstr Steel FabPr Machn Cars \\\n",
606 "count 96.000000 96.000000 96.000000 96.000000 96.000000 96.000000 \n",
607 "mean 1.136875 1.731250 0.555625 1.351042 1.227604 1.278854 \n",
608 "std 3.174680 5.246562 7.389824 4.694688 4.811242 5.718887 \n",
609 "min -7.300000 -13.960000 -20.490000 -11.960000 -9.080000 -11.650000 \n",
610 "25% -0.920000 -2.462500 -4.410000 -1.447500 -2.047500 -1.245000 \n",
611 "50% 1.475000 2.190000 0.660000 1.485000 1.545000 0.645000 \n",
612 "75% 3.317500 5.390000 4.220000 3.875000 4.657500 4.802500 \n",
613 "max 8.290000 15.550000 21.350000 17.660000 14.650000 20.860000 \n",
614 "\n",
615 " Trans Utils Rtail Finan Other \n",
616 "count 96.000000 96.000000 96.000000 96.000000 96.000000 \n",
617 "mean 1.465521 0.891250 1.234375 1.243646 1.282187 \n",
618 "std 4.151203 3.237306 3.508655 4.808350 3.711170 \n",
619 "min -8.560000 -6.990000 -9.180000 -11.020000 -7.920000 \n",
620 "25% -0.880000 -0.745000 -0.962500 -1.447500 -1.067500 \n",
621 "50% 1.505000 1.215000 0.880000 1.940000 1.580000 \n",
622 "75% 4.227500 2.965000 3.355000 4.052500 3.525000 \n",
623 "max 13.160000 7.900000 12.360000 13.430000 10.800000 "
624 ]
625 },
626 "execution_count": 39,
627 "metadata": {},
628 "output_type": "execute_result"
629 }
630 ],
631 "source": [
632 "ff_portfolio_data.describe()"
633 ]
634 },
635 {
636 "cell_type": "markdown",
637 "metadata": {},
638 "source": [
639 "### Equity Data"
640 ]
641 },
642 {
643 "cell_type": "code",
644 "execution_count": 69,
645 "metadata": {
646 "ExecuteTime": {
647 "end_time": "2018-10-31T19:14:10.382617Z",
648 "start_time": "2018-10-31T19:14:06.845523Z"
649 }
650 },
651 "outputs": [],
652 "source": [
653 "with pd.HDFStore('../../data/assets.h5') as store:\n",
654 " prices = store['/quandl/wiki/prices'].adj_close.unstack().loc['2010':'2017']\n",
655 " equities = store['/us_equities/stocks'].drop_duplicates()"
656 ]
657 },
658 {
659 "cell_type": "code",
660 "execution_count": 70,
661 "metadata": {
662 "ExecuteTime": {
663 "end_time": "2018-10-31T19:14:10.430544Z",
664 "start_time": "2018-10-31T19:14:10.383956Z"
665 }
666 },
667 "outputs": [],
668 "source": [
669 "sectors = equities.filter(prices.columns, axis=0).sector.to_dict()\n",
670 "prices = prices.filter(sectors.keys()).dropna(how='all', axis=1)"
671 ]
672 },
673 {
674 "cell_type": "code",
675 "execution_count": 71,
676 "metadata": {
677 "ExecuteTime": {
678 "end_time": "2018-10-31T19:14:10.494861Z",
679 "start_time": "2018-10-31T19:14:10.431531Z"
680 }
681 },
682 "outputs": [
683 {
684 "name": "stdout",
685 "output_type": "stream",
686 "text": [
687 "<class 'pandas.core.frame.DataFrame'>\n",
688 "PeriodIndex: 95 entries, 2010-02 to 2017-12\n",
689 "Freq: M\n",
690 "Columns: 1936 entries, A to ZUMZ\n",
691 "dtypes: float64(1936)\n",
692 "memory usage: 1.4 MB\n"
693 ]
694 }
695 ],
696 "source": [
697 "returns = prices.resample('M').last().pct_change().mul(100).to_period('M')\n",
698 "returns = returns.dropna(how='all').dropna(axis=1)\n",
699 "returns.info()"
700 ]
701 },
702 {
703 "cell_type": "markdown",
704 "metadata": {},
705 "source": [
706 "### Align data"
707 ]
708 },
709 {
710 "cell_type": "code",
711 "execution_count": 75,
712 "metadata": {
713 "ExecuteTime": {
714 "end_time": "2018-10-31T19:15:04.345235Z",
715 "start_time": "2018-10-31T19:15:04.341908Z"
716 }
717 },
718 "outputs": [],
719 "source": [
720 "ff_factor_data = ff_factor_data.loc[returns.index]\n",
721 "ff_portfolio_data = ff_portfolio_data.loc[returns.index]"
722 ]
723 },
724 {
725 "cell_type": "code",
726 "execution_count": 76,
727 "metadata": {
728 "ExecuteTime": {
729 "end_time": "2018-10-31T19:15:11.542289Z",
730 "start_time": "2018-10-31T19:15:11.525921Z"
731 }
732 },
733 "outputs": [
734 {
735 "data": {
736 "text/html": [
737 "<div>\n",
738 "<style scoped>\n",
739 " .dataframe tbody tr th:only-of-type {\n",
740 " vertical-align: middle;\n",
741 " }\n",
742 "\n",
743 " .dataframe tbody tr th {\n",
744 " vertical-align: top;\n",
745 " }\n",
746 "\n",
747 " .dataframe thead th {\n",
748 " text-align: right;\n",
749 " }\n",
750 "</style>\n",
751 "<table border=\"1\" class=\"dataframe\">\n",
752 " <thead>\n",
753 " <tr style=\"text-align: right;\">\n",
754 " <th></th>\n",
755 " <th>Mkt-RF</th>\n",
756 " <th>SMB</th>\n",
757 " <th>HML</th>\n",
758 " <th>RMW</th>\n",
759 " <th>CMA</th>\n",
760 " <th>RF</th>\n",
761 " </tr>\n",
762 " </thead>\n",
763 " <tbody>\n",
764 " <tr>\n",
765 " <th>count</th>\n",
766 " <td>95.000000</td>\n",
767 " <td>95.000000</td>\n",
768 " <td>95.000000</td>\n",
769 " <td>95.000000</td>\n",
770 " <td>95.000000</td>\n",
771 " <td>95.000000</td>\n",
772 " </tr>\n",
773 " <tr>\n",
774 " <th>mean</th>\n",
775 " <td>1.206000</td>\n",
776 " <td>0.052947</td>\n",
777 " <td>-0.069789</td>\n",
778 " <td>0.155263</td>\n",
779 " <td>0.041579</td>\n",
780 " <td>0.012737</td>\n",
781 " </tr>\n",
782 " <tr>\n",
783 " <th>std</th>\n",
784 " <td>3.568367</td>\n",
785 " <td>2.312798</td>\n",
786 " <td>2.208966</td>\n",
787 " <td>1.554671</td>\n",
788 " <td>1.418197</td>\n",
789 " <td>0.022665</td>\n",
790 " </tr>\n",
791 " <tr>\n",
792 " <th>min</th>\n",
793 " <td>-7.890000</td>\n",
794 " <td>-4.570000</td>\n",
795 " <td>-4.500000</td>\n",
796 " <td>-4.030000</td>\n",
797 " <td>-3.340000</td>\n",
798 " <td>0.000000</td>\n",
799 " </tr>\n",
800 " <tr>\n",
801 " <th>25%</th>\n",
802 " <td>-0.565000</td>\n",
803 " <td>-1.600000</td>\n",
804 " <td>-1.530000</td>\n",
805 " <td>-0.920000</td>\n",
806 " <td>-0.995000</td>\n",
807 " <td>0.000000</td>\n",
808 " </tr>\n",
809 " <tr>\n",
810 " <th>50%</th>\n",
811 " <td>1.290000</td>\n",
812 " <td>0.140000</td>\n",
813 " <td>-0.290000</td>\n",
814 " <td>0.130000</td>\n",
815 " <td>-0.030000</td>\n",
816 " <td>0.000000</td>\n",
817 " </tr>\n",
818 " <tr>\n",
819 " <th>75%</th>\n",
820 " <td>3.260000</td>\n",
821 " <td>1.555000</td>\n",
822 " <td>1.130000</td>\n",
823 " <td>1.150000</td>\n",
824 " <td>0.935000</td>\n",
825 " <td>0.010000</td>\n",
826 " </tr>\n",
827 " <tr>\n",
828 " <th>max</th>\n",
829 " <td>11.350000</td>\n",
830 " <td>6.930000</td>\n",
831 " <td>8.270000</td>\n",
832 " <td>3.510000</td>\n",
833 " <td>3.670000</td>\n",
834 " <td>0.090000</td>\n",
835 " </tr>\n",
836 " </tbody>\n",
837 "</table>\n",
838 "</div>"
839 ],
840 "text/plain": [
841 " Mkt-RF SMB HML RMW CMA RF\n",
842 "count 95.000000 95.000000 95.000000 95.000000 95.000000 95.000000\n",
843 "mean 1.206000 0.052947 -0.069789 0.155263 0.041579 0.012737\n",
844 "std 3.568367 2.312798 2.208966 1.554671 1.418197 0.022665\n",
845 "min -7.890000 -4.570000 -4.500000 -4.030000 -3.340000 0.000000\n",
846 "25% -0.565000 -1.600000 -1.530000 -0.920000 -0.995000 0.000000\n",
847 "50% 1.290000 0.140000 -0.290000 0.130000 -0.030000 0.000000\n",
848 "75% 3.260000 1.555000 1.130000 1.150000 0.935000 0.010000\n",
849 "max 11.350000 6.930000 8.270000 3.510000 3.670000 0.090000"
850 ]
851 },
852 "execution_count": 76,
853 "metadata": {},
854 "output_type": "execute_result"
855 }
856 ],
857 "source": [
858 "ff_factor_data.describe()"
859 ]
860 },
861 {
862 "cell_type": "markdown",
863 "metadata": {},
864 "source": [
865 "### Compute excess Returns"
866 ]
867 },
868 {
869 "cell_type": "code",
870 "execution_count": 77,
871 "metadata": {
872 "ExecuteTime": {
873 "end_time": "2018-10-31T19:15:13.859868Z",
874 "start_time": "2018-10-31T19:15:13.813456Z"
875 }
876 },
877 "outputs": [
878 {
879 "name": "stdout",
880 "output_type": "stream",
881 "text": [
882 "<class 'pandas.core.frame.DataFrame'>\n",
883 "PeriodIndex: 95 entries, 2010-02 to 2017-12\n",
884 "Freq: M\n",
885 "Columns: 1936 entries, A to ZUMZ\n",
886 "dtypes: float64(1936)\n",
887 "memory usage: 1.4 MB\n"
888 ]
889 }
890 ],
891 "source": [
892 "excess_returns = returns.sub(ff_factor_data.RF, axis=0)\n",
893 "excess_returns.info()"
894 ]
895 },
896 {
897 "cell_type": "code",
898 "execution_count": 78,
899 "metadata": {
900 "ExecuteTime": {
901 "end_time": "2018-10-31T19:15:13.969603Z",
902 "start_time": "2018-10-31T19:15:13.948025Z"
903 }
904 },
905 "outputs": [],
906 "source": [
907 "excess_returns = excess_returns.clip(lower=np.percentile(excess_returns, 1),\n",
908 " upper=np.percentile(excess_returns, 99))"
909 ]
910 },
911 {
912 "cell_type": "markdown",
913 "metadata": {},
914 "source": [
915 "## Fama-Macbeth Regression"
916 ]
917 },
918 {
919 "cell_type": "markdown",
920 "metadata": {},
921 "source": [
922 "Given data on risk factors and portfolio returns, it is useful to estimate the portfolio's exposure, that is, how much the risk factors drive portfolio returns, as well as how much the exposure to a given factor is worth, that is, the what market's risk factor premium is. The risk premium then permits to estimate the return for any portfolio provided the factor exposure is known or can be assumed."
923 ]
924 },
925 {
926 "cell_type": "code",
927 "execution_count": 79,
928 "metadata": {
929 "ExecuteTime": {
930 "end_time": "2018-10-31T19:15:14.246452Z",
931 "start_time": "2018-10-31T19:15:14.236339Z"
932 }
933 },
934 "outputs": [
935 {
936 "name": "stdout",
937 "output_type": "stream",
938 "text": [
939 "<class 'pandas.core.frame.DataFrame'>\n",
940 "PeriodIndex: 95 entries, 2010-02 to 2017-12\n",
941 "Freq: M\n",
942 "Data columns (total 17 columns):\n",
943 "Food 95 non-null float64\n",
944 "Mines 95 non-null float64\n",
945 "Oil 95 non-null float64\n",
946 "Clths 95 non-null float64\n",
947 "Durbl 95 non-null float64\n",
948 "Chems 95 non-null float64\n",
949 "Cnsum 95 non-null float64\n",
950 "Cnstr 95 non-null float64\n",
951 "Steel 95 non-null float64\n",
952 "FabPr 95 non-null float64\n",
953 "Machn 95 non-null float64\n",
954 "Cars 95 non-null float64\n",
955 "Trans 95 non-null float64\n",
956 "Utils 95 non-null float64\n",
957 "Rtail 95 non-null float64\n",
958 "Finan 95 non-null float64\n",
959 "Other 95 non-null float64\n",
960 "dtypes: float64(17)\n",
961 "memory usage: 15.9 KB\n"
962 ]
963 }
964 ],
965 "source": [
966 "ff_portfolio_data.info()"
967 ]
968 },
969 {
970 "cell_type": "code",
971 "execution_count": 80,
972 "metadata": {
973 "ExecuteTime": {
974 "end_time": "2018-10-31T19:15:14.402622Z",
975 "start_time": "2018-10-31T19:15:14.394908Z"
976 }
977 },
978 "outputs": [
979 {
980 "name": "stdout",
981 "output_type": "stream",
982 "text": [
983 "<class 'pandas.core.frame.DataFrame'>\n",
984 "PeriodIndex: 95 entries, 2010-02 to 2017-12\n",
985 "Freq: M\n",
986 "Data columns (total 6 columns):\n",
987 "Mkt-RF 95 non-null float64\n",
988 "SMB 95 non-null float64\n",
989 "HML 95 non-null float64\n",
990 "RMW 95 non-null float64\n",
991 "CMA 95 non-null float64\n",
992 "RF 95 non-null float64\n",
993 "dtypes: float64(6)\n",
994 "memory usage: 5.2 KB\n"
995 ]
996 }
997 ],
998 "source": [
999 "ff_factor_data.info()"
1000 ]
1001 },
1002 {
1003 "cell_type": "markdown",
1004 "metadata": {},
1005 "source": [
1006 "To address the inference problem caused by the correlation of the residuals, Fama and MacBeth proposed a two-step methodology for a cross-sectional regression of returns on factors. The two-stage Fama—Macbeth regression is designed to estimate the premium rewarded for the exposure to a particular risk factor by the market. The two stages consist of:\n",
1007 "\n",
1008 "- First stage: N time-series regression, one for each asset or portfolio, of its excess returns on the factors to estimate the factor loadings.\n",
1009 "\n",
1010 "- Second stage: T cross-sectional regression, one for each time period, to estimate the risk premium.\n",
1011 "\n",
1012 "See corresponding section in Chapter 7 of [Machine Learning for Trading](https://www.amazon.com/Hands-Machine-Learning-Algorithmic-Trading-ebook/dp/B07JLFH7C5/ref=sr_1_2?ie=UTF8&qid=1548455634&sr=8-2&keywords=machine+learning+algorithmic+trading) for details."
1013 ]
1014 },
1015 {
1016 "cell_type": "markdown",
1017 "metadata": {},
1018 "source": [
1019 "Now we can compute the factor risk premia as the time average and get t-statistic to assess their individual significance, using the assumption that the risk premia estimates are independent over time.\n",
1020 "\n",
1021 "If we had a very large and representative data sample on traded risk factors we could use the sample mean as a risk premium estimate. However, we typically do not have a sufficiently long history to and the margin of error around the sample mean could be quite large. \n",
1022 "\n",
1023 "The Fama—Macbeth methodology leverages the covariance of the factors with other assets to determine the factor premia. The second moment of asset returns is easier to estimate than the first moment, and obtaining more granular data improves estimation considerably, which is not true of mean estimation."
1024 ]
1025 },
1026 {
1027 "cell_type": "markdown",
1028 "metadata": {},
1029 "source": [
1030 "### Step 1: Factor Exposures"
1031 ]
1032 },
1033 {
1034 "cell_type": "markdown",
1035 "metadata": {},
1036 "source": [
1037 "We can implement the first stage to obtain the 17 factor loading estimates as follows:"
1038 ]
1039 },
1040 {
1041 "cell_type": "code",
1042 "execution_count": 81,
1043 "metadata": {
1044 "ExecuteTime": {
1045 "end_time": "2018-10-31T19:15:14.765388Z",
1046 "start_time": "2018-10-31T19:15:14.700127Z"
1047 }
1048 },
1049 "outputs": [],
1050 "source": [
1051 "betas = []\n",
1052 "for industry in ff_portfolio_data:\n",
1053 " step1 = OLS(endog=ff_portfolio_data.loc[ff_factor_data.index, industry], \n",
1054 " exog=add_constant(ff_factor_data)).fit()\n",
1055 " betas.append(step1.params.drop('const'))"
1056 ]
1057 },
1058 {
1059 "cell_type": "code",
1060 "execution_count": 82,
1061 "metadata": {
1062 "ExecuteTime": {
1063 "end_time": "2018-10-31T19:15:14.854849Z",
1064 "start_time": "2018-10-31T19:15:14.842975Z"
1065 }
1066 },
1067 "outputs": [
1068 {
1069 "name": "stdout",
1070 "output_type": "stream",
1071 "text": [
1072 "<class 'pandas.core.frame.DataFrame'>\n",
1073 "Index: 17 entries, Food to Other\n",
1074 "Data columns (total 6 columns):\n",
1075 "Mkt-RF 17 non-null float64\n",
1076 "SMB 17 non-null float64\n",
1077 "HML 17 non-null float64\n",
1078 "RMW 17 non-null float64\n",
1079 "CMA 17 non-null float64\n",
1080 "RF 17 non-null float64\n",
1081 "dtypes: float64(6)\n",
1082 "memory usage: 1.6+ KB\n"
1083 ]
1084 }
1085 ],
1086 "source": [
1087 "betas = pd.DataFrame(betas, \n",
1088 " columns=ff_factor_data.columns, \n",
1089 " index=ff_portfolio_data.columns)\n",
1090 "betas.info()"
1091 ]
1092 },
1093 {
1094 "cell_type": "markdown",
1095 "metadata": {},
1096 "source": [
1097 "### Step 2: Risk Premia"
1098 ]
1099 },
1100 {
1101 "cell_type": "markdown",
1102 "metadata": {},
1103 "source": [
1104 "For the second stage, we run 96 regressions of the period returns for the cross section of portfolios on the factor loadings"
1105 ]
1106 },
1107 {
1108 "cell_type": "code",
1109 "execution_count": 83,
1110 "metadata": {
1111 "ExecuteTime": {
1112 "end_time": "2018-10-31T19:15:15.236842Z",
1113 "start_time": "2018-10-31T19:15:15.125640Z"
1114 }
1115 },
1116 "outputs": [],
1117 "source": [
1118 "lambdas = []\n",
1119 "for period in ff_portfolio_data.index:\n",
1120 " step2 = OLS(endog=ff_portfolio_data.loc[period, betas.index], \n",
1121 " exog=betas).fit()\n",
1122 " lambdas.append(step2.params)"
1123 ]
1124 },
1125 {
1126 "cell_type": "code",
1127 "execution_count": 84,
1128 "metadata": {
1129 "ExecuteTime": {
1130 "end_time": "2018-10-31T19:15:15.287100Z",
1131 "start_time": "2018-10-31T19:15:15.272535Z"
1132 }
1133 },
1134 "outputs": [
1135 {
1136 "name": "stdout",
1137 "output_type": "stream",
1138 "text": [
1139 "<class 'pandas.core.frame.DataFrame'>\n",
1140 "PeriodIndex: 95 entries, 2010-02 to 2017-12\n",
1141 "Freq: M\n",
1142 "Data columns (total 6 columns):\n",
1143 "Mkt-RF 95 non-null float64\n",
1144 "SMB 95 non-null float64\n",
1145 "HML 95 non-null float64\n",
1146 "RMW 95 non-null float64\n",
1147 "CMA 95 non-null float64\n",
1148 "RF 95 non-null float64\n",
1149 "dtypes: float64(6)\n",
1150 "memory usage: 7.7 KB\n"
1151 ]
1152 }
1153 ],
1154 "source": [
1155 "lambdas = pd.DataFrame(lambdas, \n",
1156 " index=ff_portfolio_data.index,\n",
1157 " columns=betas.columns.tolist())\n",
1158 "lambdas.info()"
1159 ]
1160 },
1161 {
1162 "cell_type": "code",
1163 "execution_count": 85,
1164 "metadata": {
1165 "ExecuteTime": {
1166 "end_time": "2018-10-31T19:15:15.431714Z",
1167 "start_time": "2018-10-31T19:15:15.420391Z"
1168 }
1169 },
1170 "outputs": [
1171 {
1172 "data": {
1173 "text/plain": [
1174 "Mkt-RF 1.244610\n",
1175 "SMB 0.007380\n",
1176 "HML -0.696972\n",
1177 "RMW -0.255768\n",
1178 "CMA -0.308635\n",
1179 "RF -0.013344\n",
1180 "dtype: float64"
1181 ]
1182 },
1183 "execution_count": 85,
1184 "metadata": {},
1185 "output_type": "execute_result"
1186 }
1187 ],
1188 "source": [
1189 "lambdas.mean()"
1190 ]
1191 },
1192 {
1193 "cell_type": "code",
1194 "execution_count": 86,
1195 "metadata": {
1196 "ExecuteTime": {
1197 "end_time": "2018-10-31T19:15:17.688273Z",
1198 "start_time": "2018-10-31T19:15:17.683712Z"
1199 }
1200 },
1201 "outputs": [
1202 {
1203 "data": {
1204 "text/plain": [
1205 "Mkt-RF 0.347112\n",
1206 "SMB 0.001895\n",
1207 "HML -0.200648\n",
1208 "RMW -0.082556\n",
1209 "CMA -0.105439\n",
1210 "RF -0.160318\n",
1211 "dtype: float64"
1212 ]
1213 },
1214 "execution_count": 86,
1215 "metadata": {},
1216 "output_type": "execute_result"
1217 }
1218 ],
1219 "source": [
1220 "t = lambdas.mean().div(lambdas.std())\n",
1221 "t"
1222 ]
1223 },
1224 {
1225 "cell_type": "markdown",
1226 "metadata": {},
1227 "source": [
1228 "#### Results"
1229 ]
1230 },
1231 {
1232 "cell_type": "code",
1233 "execution_count": 87,
1234 "metadata": {
1235 "ExecuteTime": {
1236 "end_time": "2018-10-31T19:15:18.393596Z",
1237 "start_time": "2018-10-31T19:15:17.963791Z"
1238 },
1239 "scrolled": true
1240 },
1241 "outputs": [
1242 {
1243 "data": {
1244 "image/png": "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\n",
1245 "text/plain": [
1246 "<Figure size 1008x720 with 2 Axes>"
1247 ]
1248 },
1249 "metadata": {},
1250 "output_type": "display_data"
1251 }
1252 ],
1253 "source": [
1254 "ax1 = plt.subplot2grid((1, 3), (0, 0))\n",
1255 "ax2 = plt.subplot2grid((1, 3), (0, 1), colspan=2)\n",
1256 "lambdas.mean().plot.barh(ax=ax1)\n",
1257 "lambdas.rolling(60).mean().plot(lw=2, figsize=(14,10), sharey=True, ax=ax2);"
1258 ]
1259 },
1260 {
1261 "cell_type": "code",
1262 "execution_count": 88,
1263 "metadata": {
1264 "ExecuteTime": {
1265 "end_time": "2018-10-31T19:15:19.182873Z",
1266 "start_time": "2018-10-31T19:15:18.395007Z"
1267 }
1268 },
1269 "outputs": [
1270 {
1271 "data": {
1272 "image/png": "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\n",
1273 "text/plain": [
1274 "<Figure size 1008x720 with 6 Axes>"
1275 ]
1276 },
1277 "metadata": {},
1278 "output_type": "display_data"
1279 }
1280 ],
1281 "source": [
1282 "lambdas.rolling(60).mean().plot(lw=2, figsize=(14,10), subplots=True,sharey=True);"
1283 ]
1284 },
1285 {
1286 "cell_type": "markdown",
1287 "metadata": {},
1288 "source": [
1289 "## Fama-Macbeth with the LinearModels library"
1290 ]
1291 },
1292 {
1293 "cell_type": "markdown",
1294 "metadata": {},
1295 "source": [
1296 "The linear_models library extends statsmodels with various models for panel data and also implements the two-stage Fama—MacBeth procedure:"
1297 ]
1298 },
1299 {
1300 "cell_type": "code",
1301 "execution_count": 92,
1302 "metadata": {
1303 "ExecuteTime": {
1304 "end_time": "2018-10-31T19:15:52.081027Z",
1305 "start_time": "2018-10-31T19:15:52.064888Z"
1306 }
1307 },
1308 "outputs": [
1309 {
1310 "name": "stdout",
1311 "output_type": "stream",
1312 "text": [
1313 " LinearFactorModel Estimation Summary \n",
1314 "================================================================================\n",
1315 "No. Test Portfolios: 17 R-squared: 0.6943\n",
1316 "No. Factors: 6 J-statistic: 19.155\n",
1317 "No. Observations: 95 P-value 0.0584\n",
1318 "Date: Wed, Oct 31 2018 Distribution: chi2(11)\n",
1319 "Time: 15:15:52 \n",
1320 "Cov. Estimator: robust \n",
1321 " \n",
1322 " Risk Premia Estimates \n",
1323 "==============================================================================\n",
1324 " Parameter Std. Err. T-stat P-value Lower CI Upper CI\n",
1325 "------------------------------------------------------------------------------\n",
1326 "Mkt-RF 1.2446 0.3928 3.1689 0.0015 0.4748 2.0144\n",
1327 "SMB 0.0074 0.7055 0.0105 0.9917 -1.3753 1.3901\n",
1328 "HML -0.6970 0.5334 -1.3067 0.1913 -1.7424 0.3484\n",
1329 "RMW -0.2558 0.6888 -0.3713 0.7104 -1.6057 1.0942\n",
1330 "CMA -0.3086 0.4737 -0.6515 0.5147 -1.2371 0.6198\n",
1331 "RF -0.0133 0.0132 -1.0092 0.3129 -0.0393 0.0126\n",
1332 "==============================================================================\n",
1333 "\n",
1334 "Covariance estimator:\n",
1335 "HeteroskedasticCovariance\n",
1336 "See full_summary for complete results\n"
1337 ]
1338 }
1339 ],
1340 "source": [
1341 "mod = LinearFactorModel(portfolios=ff_portfolio_data, \n",
1342 " factors=ff_factor_data)\n",
1343 "res = mod.fit()\n",
1344 "print(res)"
1345 ]
1346 },
1347 {
1348 "cell_type": "code",
1349 "execution_count": 93,
1350 "metadata": {
1351 "ExecuteTime": {
1352 "end_time": "2018-10-31T19:15:55.327250Z",
1353 "start_time": "2018-10-31T19:15:53.919680Z"
1354 }
1355 },
1356 "outputs": [
1357 {
1358 "data": {
1359 "image/png": "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\n",
1360 "text/plain": [
1361 "<Figure size 864x504 with 1 Axes>"
1362 ]
1363 },
1364 "metadata": {},
1365 "output_type": "display_data"
1366 }
1367 ],
1368 "source": [
1369 "plt.rc('figure', figsize=(12, 7))\n",
1370 "plt.text(0.01, 0.05, str(res), {'fontsize': 14}, fontproperties = 'monospace')\n",
1371 "plt.axis('off')\n",
1372 "plt.tight_layout()\n",
1373 "plt.subplots_adjust(left=0.2, right=0.8, top=0.8, bottom=0.1)\n",
1374 "plt.savefig('factor_model.png', bbox_inches='tight', dpi=300);"
1375 ]
1376 },
1377 {
1378 "cell_type": "markdown",
1379 "metadata": {},
1380 "source": [
1381 "This provides us with the same result:"
1382 ]
1383 },
1384 {
1385 "cell_type": "code",
1386 "execution_count": 91,
1387 "metadata": {
1388 "ExecuteTime": {
1389 "end_time": "2018-10-31T19:15:20.706381Z",
1390 "start_time": "2018-10-31T19:15:20.703156Z"
1391 }
1392 },
1393 "outputs": [
1394 {
1395 "data": {
1396 "text/plain": [
1397 "Mkt-RF 1.244610\n",
1398 "SMB 0.007380\n",
1399 "HML -0.696972\n",
1400 "RMW -0.255768\n",
1401 "CMA -0.308635\n",
1402 "RF -0.013344\n",
1403 "dtype: float64"
1404 ]
1405 },
1406 "execution_count": 91,
1407 "metadata": {},
1408 "output_type": "execute_result"
1409 }
1410 ],
1411 "source": [
1412 "lambdas.mean()"
1413 ]
1414 }
1415 ],
1416 "metadata": {
1417 "kernelspec": {
1418 "display_name": "Python 3",
1419 "language": "python",
1420 "name": "python3"
1421 },
1422 "language_info": {
1423 "codemirror_mode": {
1424 "name": "ipython",
1425 "version": 3
1426 },
1427 "file_extension": ".py",
1428 "mimetype": "text/x-python",
1429 "name": "python",
1430 "nbconvert_exporter": "python",
1431 "pygments_lexer": "ipython3",
1432 "version": "3.7.0"
1433 },
1434 "toc": {
1435 "base_numbering": 1,
1436 "nav_menu": {},
1437 "number_sections": true,
1438 "sideBar": true,
1439 "skip_h1_title": true,
1440 "title_cell": "Table of Contents",
1441 "title_sidebar": "Contents",
1442 "toc_cell": false,
1443 "toc_position": {},
1444 "toc_section_display": true,
1445 "toc_window_display": true
1446 }
1447 },
1448 "nbformat": 4,
1449 "nbformat_minor": 2
1450 }