For this next stage in our team’s project, my role is to explore and understand better the variables in the College Scorecard data that are related to cost and aid. Let’s check it out.

Finding the Cost and Aid Variables

Let’s open up the College Scorecard data and remove the rows that are all NA.

library(readr)
colleges <- read_csv("data/merged_2013_PP.csv", na = c("NULL", "PrivacySuppressed"))
colleges <- Filter(function(x)!all(is.na(x)), colleges)
dim(colleges)
## [1] 7804  550

Now let’s open up the data dictionary.

dictionary <- read_csv("data/CollegeScorecardDataDictionary-09-08-2015.csv")
dim(dictionary)
## [1] 1953    9

The data dictionary will tell us which variables are the cost and aid variables. Let’s check out what we have in the data dictionary.

names(dictionary)
## [1] "NAME OF DATA ELEMENT"    "dev-category"            "developer-friendly name"
## [4] "API data type"           "VARIABLE NAME"           "VALUE"                  
## [7] "LABEL"                   "SOURCE"                  "NOTES"

It is dev-category that tells us which variables belong to which category. What are the categories?

levels(factor(dictionary$`dev-category`))
##  [1] "academics"  "admissions" "aid"        "completion" "cost"       "earnings"   "repayment" 
##  [8] "root"       "school"     "student"

Which variables belong to cost or aid?

library(dplyr)
cost_aid_names <- dictionary %>% 
    filter(`dev-category` %in% c("cost", "aid")) %>% 
    select(`VARIABLE NAME`, `NAME OF DATA ELEMENT`)

cost_aid_names
## # A tibble: 105 × 2
##    `VARIABLE NAME`
##              <chr>
## 1         NPT4_PUB
## 2        NPT4_PRIV
## 3        NPT4_PROG
## 4       NPT4_OTHER
## 5        NPT41_PUB
## 6        NPT42_PUB
## 7        NPT43_PUB
## 8        NPT44_PUB
## 9        NPT45_PUB
## 10      NPT41_PRIV
##                                                                                         `NAME OF DATA ELEMENT`
##                                                                                                          <chr>
## 1                                            Average net price for Title IV institutions (public institutions)
## 2                  Average net price for Title IV institutions (private for-profit and nonprofit institutions)
## 3                   Average net price for the largest program at the institution for program-year institutions
## 4  Average net price for the largest program at the institution for schools on "other" academic year calendars
## 5                                         Average net price for $0-$30,000 family income (public institutions)
## 6                                    Average net price for $30,001-$48,000 family income (public institutions)
## 7                                    Average net price for $48,001-$75,000 family income (public institutions)
## 8                                   Average net price for $75,001-$110,000 family income (public institutions)
## 9                                          Average net price for $110,000+ family income (public institutions)
## 10              Average net price for $0-$30,000 family income (private for-profit and nonprofit institutions)
## # ... with 95 more rows

You can see even from the first few lines of this that we’ll need to use some combination of these variables to make meaningful comparisons between colleges. For example, of course public universities have NA for NPT4_PRIV; that value is specifically for private universities.

Understanding the Cost Data

Let’s look in more detail at all the cost variables.

cost_names <- dictionary %>% 
    filter(`dev-category` == "cost") %>% 
    select(`VARIABLE NAME`, `NAME OF DATA ELEMENT`)

cost_names
## # A tibble: 65 × 2
##    `VARIABLE NAME`
##              <chr>
## 1         NPT4_PUB
## 2        NPT4_PRIV
## 3        NPT4_PROG
## 4       NPT4_OTHER
## 5        NPT41_PUB
## 6        NPT42_PUB
## 7        NPT43_PUB
## 8        NPT44_PUB
## 9        NPT45_PUB
## 10      NPT41_PRIV
##                                                                                         `NAME OF DATA ELEMENT`
##                                                                                                          <chr>
## 1                                            Average net price for Title IV institutions (public institutions)
## 2                  Average net price for Title IV institutions (private for-profit and nonprofit institutions)
## 3                   Average net price for the largest program at the institution for program-year institutions
## 4  Average net price for the largest program at the institution for schools on "other" academic year calendars
## 5                                         Average net price for $0-$30,000 family income (public institutions)
## 6                                    Average net price for $30,001-$48,000 family income (public institutions)
## 7                                    Average net price for $48,001-$75,000 family income (public institutions)
## 8                                   Average net price for $75,001-$110,000 family income (public institutions)
## 9                                          Average net price for $110,000+ family income (public institutions)
## 10              Average net price for $0-$30,000 family income (private for-profit and nonprofit institutions)
## # ... with 55 more rows

There are many ways the cost estimates are broken out, for different income levels at public vs. private institutions. It is true that often low-income students with high test scores can get better financial deals at private, very “expensive” schools than at state schools. I don’t know if it is realistic to build that kind of information into the specific model we are going for right now, though, at least on a first attempt. I suggest that the best estimates of cost for our first round of models are these two variables:

cost_aid_names[61:62,]
## # A tibble: 2 × 2
##   `VARIABLE NAME`                                  `NAME OF DATA ELEMENT`
##             <chr>                                                   <chr>
## 1        COSTT4_A Average cost of attendance (academic year institutions)
## 2        COSTT4_P  Average cost of attendance (program-year institutions)

If we use those two values to define a new average cost estimate, we get an estimator with the fewest NA values possible compared to using other variables available.

colleges <- colleges %>% 
    rowwise() %>%
    mutate(cost = sum(COSTT4_A, COSTT4_P, na.rm = TRUE)) %>%
    mutate(cost = ifelse(cost == 0, NA, cost)) %>%
    ungroup

colleges$cost
##    [1] 18888 19990 12300 20306 17400 26717 12103    NA 16556 23788 44512  6800 17655 28525 10193
##   [16] 11921 28485 10247 13482  8140 10822 14835 26656 31433 21160 12217 19202  9149 12943  9829
##   [31] 27815 12602 17959 13204 16520 21336 30108 20209  9111 15058  7860 34705 10701 24676  9693
##   [46] 10059 38835 11187 13007  9622 17125 43325 19127 24744 18758  9955 16877 32853    NA 13443
##   [61] 13180 13380 15035 16409 42925    NA 21163 12434 17095 25089    NA 15718 17171    NA 20601
##   [76] 21896 24417 26492 24529 26842 16550 32627 29302 21960 14337 23905 49519 15900  9205 24344
##   [91] 13838  9792 17217 16135 21809 14520 11649 45228    NA 12043 31613 32523 19268 22094 12673
##  [106] 12744 26194 26194 15718 23695 11396 22771 13342    NA 12521 17863 24167  7367 20448 21205
##  [121] 40206 22226 11811 20340  9389 12970 12343 34444 23058 25295 26118 17239 12610 19894    NA
##  [136]  9935 20024 14237 12603 33355 20360 13997 19917 15414 11558 18809 16126 16255 13640 18846
##  [151] 11401 17899 20386 11753 18790  8644  8767 14929 19884 13836  7631 25475 18033 50172 13708
##  [166]    NA 33326 15084 17711 10740 19282 13105 12538 14690 16982  9463  8855 31473 12215 11364
##  [181] 34532 11593 24877 16140  9672 10799 17064 14349 10415 24420 18967  7500 22330 17675 17738
##  [196] 16258  6876 14335 34512 26209    NA 24084 17164 10251 10735 51197    NA    NA 16486 29948
##  [211]    NA 12311 31438 11430 56400 22699 24413 44021  8732 14930 24879 11741 44573 32699 26313
##  [226] 24818 11493    NA    NA 12665 39026 53837    NA 56382 48630 23867 28901 18061 17161 17030
##  [241] 19402 22926 12957 16377 16663 20676 18085 14747 20899 19380 32715 31803 28980 31474 29787
##  [256] 29751    NA 31913 33208    NA 16818 17109 27138 23262 18954 56435 22223    NA  9010 11251
##  [271] 14912 29402 17902 17000  9931 17101 15243 16275 16468  9066 11064 11350 14156 57020 26941
##  [286] 41233 37696    NA  8257 12973  9757    NA 60065 22270 15638 11569 32243 29842    NA    NA
##  [301] 12210 30642 12723 15105 13537 16696 15304  7866 10174 10046 19031 17157    NA 14046 29477
##  [316] 14386 56165    NA 14906 19721 16018 32897 18490 19714    NA 17079 14405 42958 42052 38721
##  [331] 14923 20441    NA    NA 11467 10399    NA 13192 10821 33973    NA 10651 11544 33485  8875
##  [346] 22364    NA 16230    NA  7759 15526 14629 60613 24503 23046 23209 23587 22720 16721 46994
##  [361]    NA 23113 21029  9327 25900    NA 18063 16598 26686 26194 25603 29995    NA 46466 10026
##  [376] 24492 30521 45305 39713  9836 17079 14398 13925    NA 20725    NA 39842    NA 10615    NA
##  [391] 13977 14213 11945 11030 13353 40815 11090    NA 13281 14140 33206 55432 13789 16790 13897
##  [406] 10335 12836 23653 15451 29485 27785 28147 13794 19438 44406 14316 51649  9094 15651 54668
##  [421]  9338 20245 13902 14441 25503 12734 12347    NA 12092  8501  9281 47905 12010 34305 39155
##  [436] 15178 31652 26658 28767 29186 33016 30050 30116 22545 27567 23859 43957 12408 18479 23706
##  [451] 24317 23539 47115 60655 13930 16039 16053 52397  9675 40303 25049    NA    NA    NA    NA
##  [466] 32140 38800 52406 12973 11208 14058 11751 58772 59266 40468 43060 57014  9019 29458 15735
##  [481]  8434    NA 14520 55268 11166 13965 14360 11181 12410 27325 10292    NA 12334 14906    NA
##  [496] 12291 26489 12796 11969 20252 56346 55809 52260 22267    NA 55812    NA 14951 26654 22188
##  [511] 34811 15067 21160 11925 23144 29745 21409 15367 57213 12202 12722    NA 58888 23105  7604
##  [526] 24984 10855 13157  7569 25046    NA 33889 13115  8900  9778 12483 56500 12671 23675 32649
##  [541]    NA 21711 41952 30815 10665    NA    NA 50373 59787    NA 11975    NA 35056 18565 24692
##  [556] 27724 23987 19281 24050  8895 17238 13359 12466    NA 11597 13472 13291 14565 20980    NA
##  [571] 51760 49920 42465    NA    NA    NA 23850 12017 14621 17759 13308 13086 24078 25950 18822
##  [586] 16707 25485 27854 36956 54200 24171 30664 14430 15455 29091 17259 21823 23475 17324 18238
##  [601] 22306 11003 18456 13908 21771    NA 24309 53614 15575 19565 14433 15882 15970    NA 15662
##  [616] 15591 18077 14034 16058 42575    NA    NA 25950 15982 19105 16404 25134 14717 19502 14679
##  [631] 14046 43058 39272    NA 18007 13453 17833 17431 16636 16320 18875 41520 19506 10520 29870
##  [646] 29502 25950 45640 20372    NA 20417 58690 26180 27518 25786 32844 20578 22633 56628 19872
##  [661] 13470    NA 17514    NA 47368 15930 10703    NA 36811  9000 10754  9053 43386  9055 22080
##  [676] 12940 48280 24215 13507 10289 17460 18915 29352 40723 11294 53476 50984 42885 11208 24452
##  [691] 18628 22589    NA 59865 11502 61167 19446    NA 59320    NA 24586  8161  8221  8203 20506
##  [706] 21748 32255 19839 35199 16978 55159 54023 47459 19873    NA 29852 58925 59900 40129 25718
##  [721]    NA 12848 30144    NA 33304 30805 11560 15748 41019    NA 27017 48735 17221  7415 10693
##  [736] 13383 31994 22158 13907 26241 19815 15064  9298 28463 15655 11307 28808 49802 15635 22929
##  [751] 45648 19191 19131 11430 28305 25690 25807 23208 24239 21358 52490    NA 18426 18699 25036
##  [766] 46564 18424 38413 20774 17829 11673 20456 27860  9723 35899 11866  5520  9810 21744  9858
##  [781] 12303 22524 23983  6709 22376 18933 30422 26761 42459 15982 26887 22761 13912  9879 11621
##  [796]  9570 11057 16166 11897 21726 22696 15137  9485 18317 11748    NA 12225 19850 57700 14518
##  [811] 21514 24209 25659 12132 25144 18478  9016 19415 33485 40783 13486 26001 17824 37535  7804
##  [826] 10355 12748 16553 13574  7430    NA 19449 54676 22684 12277 56309 13033 31609 12727 17499
##  [841] 12137 10220    NA 12953  8855 32000 11904 10402 19299 37090 27794 49939 30333 21695 18504
##  [856]  8985 25600 27608 27296 37714 11854 13978 16752 21986 17755 11491 28555 22141 34949 24315
##  [871] 18158 23589  8543 26350 10683 14080 44945 17032 16030  6867 11611 19025 26050 19802 32466
##  [886] 13583  9318 27497 15545    NA 17159 34201 14538  9775 24573 11056 40965 14607 34107 22499
##  [901] 28860 15501 10061 20421 17487    NA 14131 17029 10756 38510 10948 16424 29751 10852 23842
##  [916] 58180 10227 19801    NA 21980 17839 23052 19600 21513 23124 21162 13091 15228 19186 25384
##  [931] 11417    NA 20630 37305 11289 28609  7954 26341 46382 45451    NA 11410  8465 43689 21516
##  [946] 32031 38258 30734  9694 49179 15531 30642  9440 27185 41635 16546  8138 24734 30178 26484
##  [961]  8762 20958 30878 18879 34007 23216 30801 15284 18491 15847 29762  8230  9242 10801  5931
##  [976] 11240 25248    NA 17309  9874 10933 25566 23036 18227 12995 18077 19700 34555 16184 27490
##  [991] 16552 14238 12063 34498 16400 10438 10390    NA 11828 11966 32415 55551 45364 31145 14803
## [1006] 11804    NA 10031 24126    NA    NA 40330 11513 18889 11241 11820 10482 11588 20177 16923
## [1021] 24378  8961    NA 22396    NA    NA 18472    NA 62425 13006 11493 12270 10206  9687  9503
## [1036]  8832 37546 34774 20436 23769 10840 14931 46375 12289 12788 30965 23346  8025 41472 28799
## [1051] 15142 25011    NA 14601    NA 24018 33675 20385 23471 23779 29650 33966 10024    NA 25248
## [1066] 35481    NA 28564 48522 10289 36829  5827 48940 23972 25416 11075    NA 19484  7550    NA
## [1081] 11970  7979 37635 10428 10332 41411 12107 46291 13654  8490 49743    NA  9506    NA  8571
## [1096] 34079 37604 25309 28702  9677 16185 47727    NA    NA 15688 19646 23685 30843    NA 10565
## [1111] 37004    NA 33354 26994 39576 40578 25537  9651 24050  8699 14519 30180    NA 12298 41218
## [1126] 31065    NA 27621 29184 60729 22273  9574 12668 39125 10394 18745 10990 16247 36948 22192
## [1141] 31746 10756 10285 32074  9736 24888 37253 43650 36307    NA    NA 36226    NA 35284 21385
## [1156]  9836 14783 45030 14859    NA 12498 16390    NA 14977    NA 16686 24234 21137 23100 17585
## [1171]  9697 11018 33611 37929  9066 17756 37343  8991    NA 24375 41394 12390 25473 37937  6519
## [1186] 21101 33617 47010 19530    NA 22489    NA 19337 51050 14246 14918 50930 42674 37962 37707
## [1201] 32506 13303 21725 42198 13849 33660 15225 34764 13547 18837 20846 24768 36158 35911 17996
## [1216] 19549 15874 17377 23043 18092 16753 15334 21604 21258 26064 24682 27249 18900  7429  9597
## [1231] 23508 24039 17479 20877 38505 39369 33770 22038 13753    NA 13001 23513 12303  7672 57805
## [1246] 31104 15225 16727 13713 19605 13541 55413 15843 31516 37135 40349 45920 24929    NA 31927
## [1261] 38845 40679 43185 11857 15780 44750 29905 22469 37066 39011 17831 16440 14900 43491 38062
## [1276] 45387 46135 15284 13927 17945 37080 42477 34206 14594 23620 13251 24930 11868 34494 31761
## [1291] 53318 25840 24916 17577 14121 14343 13733 10958 13967 11064 14702 15053 18820 36102 13456
## [1306] 21832 14491 17971 17882 15783 18828 37622 46548 38334 13162 24333 36280 37183 26047 11412
## [1321] 19233 37884 14427 14703    NA 13912 24669 16206 38189 25370 18075 17451 40186 11772 11220
## [1336] 15809 14126 11742 35190 30300 43312    NA 12211 10900 33081  9977 37485 13481 36805 34042
## [1351] 33781 23573 24272 23526 11479    NA 28170  9748  8831 11426 12715 17464 11074 13682 15612
## [1366] 19991 15395 24990 33388  9778  9135  8056 16094 34390  7535 11659  9460 10688 23705 18419
## [1381] 21971 33524 18034 20140 34402 16169 13320  9170 16279 25439 34534 32388 12587 14424 13953
## [1396] 35017    NA 15211 10618 31515 10457  9236 13977 36472 30722 35960 16176 12928 14764 26067
## [1411] 19450 33966    NA 11665 13462 47609 30396  9223 11295 27219 31545 11544 46400 13615 12576
## [1426]  6985    NA 30993 17801 10803    NA 42036 12815 11591 17885 10789 11678 28820 11113  8339
## [1441] 13736 24722 15618 18387 29725 22420 29246    NA 33342 36357 21922    NA 10669 11940 29971
## [1456] 33132 17805 16397 11335 14603 12890 28943 10661  9230 31005 11404 23759 14911 30957 15855
## [1471] 16746 15270 22799 11298 11439 31021 29666 29648 36843 41374 17537 31769 16538 12082 17930
## [1486] 24992    NA    NA    NA 11931 12889 14337 40578  6705 16056 19287 12335 23274 11029 13405
## [1501] 25343 12684 20881 15999 21899  8352 11562    NA 14276 20422 11914 15066 12832 16331 17400
## [1516] 13534 22940 13144 16983 46676 14823 16212 16071 14925 12524    NA 16605 17887 21335 13994
## [1531] 14881 10505 12374 17753 30965 15630 16374 13510 26145 12978 16600 15729 17928 10889 13623
## [1546] 15342 12007 58904 27550 12645 21396 48639 59285 16266 58200 15526 12756 57300 13030 25019
## [1561] 14210 36025 13927 20415 17314 17380 22461 23673 16492 47931 15685 17052 43313 43119 14228
## [1576] 15054 22290 33792 34137 11173 12677 19607 13997 16950 25359 16476 15897 12348 24835 18581
## [1591] 30826  9816 12644 13112 27990 16147 21768 22113  9205 19454 11372 50840 26958  9809  7963
## [1606] 45230 12617 17335 58980 24506 27191 56736 15877 13222    NA 22024 22933 52649 20587 20841
## [1621] 15997 12291 20108 45896 20300 16727 41871  9936 25329 17176 15946 20916 29174 26170 56867
## [1636] 25648 21596    NA 21577 38785 52243 45866 13127    NA 14275 40803 59060    NA 42770 21764
## [1651] 46763 58450    NA 31101 40447 32975 28929 44041 54806 56335 13345 18111 36082    NA 58639
## [1666] 59631 59036 58850 19303  9237 18463 12219 26815 13268 16703 33880 47248    NA 47519 19184
## [1681] 46673 16898 19742 36567 51158 49487 44177    NA 16879 41383 17686 21402 25164 43140    NA
## [1696] 14787 76806 57765 57950    NA 38080 14417 56706 11963    NA 17188 18037 16162 43854    NA
## [1711] 47788 18042 22861 19426 17090 24949 25665 19763 16109 43966 25384 57010 22420    NA    NA
## [1726] 15998 13154 46532    NA  8397 37866 55496 41565 13092 24012 52303 25805 18935 54125    NA
## [1741]    NA    NA 45733 40611 44886 20025 30069 12526 33728 55914 12455 40802 36852    NA 15981
## [1756] 10587 47432  7312    NA 20601 27771 51093 59385 57913 15113 44829 13496 23763 50677 45280
## [1771] 17118 58752 57164 43850 45850 19468 56934 45591 59412 55866 18494 40199 45690  9483 29725
## [1786] 43157  7229 33653 34593 18035 18241 12614  7166 11841 39013    NA 17746    NA 21523 12138
## [1801] 16261 17823 33441    NA 46095 25439 15880  8696    NA    NA 16919 48027 30517 28379 18905
## [1816] 21498  8914 10394 49303 12540 20912 33912 29589  8382 21512 25506  9498 38593 26994 11636
## [1831]  6773 48547 10156  9222 11482 10895 11762 19571 11373 39890  7239 10964 22629 25733 26399
## [1846] 25760 11931 23740 24724 15831 16731 10136  7479 10782 13169 18466  9042 29177 27422  6204
## [1861] 18466 19504 12840 32803 10055 19198 31515 12358 26213 22731 21516 22636    NA 17876  8550
## [1876] 31980 10118 13118    NA 32709 20625 29377    NA 17013    NA 10498 10234 20199  7734 22483
## [1891]    NA 12240 26704 17952 14750 19562 16272 42531 13823 14542 18166 32531 42692    NA 14585
## [1906] 58275 39803 40267 17876 20740 17179 16769 29911 15188 28684 14665 48422 43433    NA 18165
## [1921] 16769 13853 19274 15152 15255 31098    NA 55393 15134 17578 22487    NA    NA 23047 11634
## [1936] 18170 24278 21549 18922 41935 18789 22451 18296 25235 22796 22853 30125 15582 18028 19425
## [1951] 22631 23700 17455 28800 15429    NA 37803 23983 25300 22621 15646 13190 18591 47734 12704
## [1966] 24563 17892 46397 38470 50550 34574 40685 48421 17171 43356 25387 18578 19109 10900    NA
## [1981] 14819 31006 13045 19177 20449    NA 13047 20330 33375 16926 16844  6136 26145  8947 19232
## [1996]  8566 17749 10087  9564 13669 10932  8395  9907 10991 18724  9855 11036 44435  8165 21526
## [2011]    NA 15935 17758 25976 11725 12021 20796 11011  8243  5285 14466  6753 10568 18781 16129
## [2026] 20179    NA 23962 25224    NA    NA 34898 26033 16646 15994 24355 18781    NA 26620 32000
## [2041] 18355  8576 14936 38183 18810 17611 30766    NA 26065    NA  9341 33741 32556 11225    NA
## [2056] 15422 24933 30988 30833    NA 22133 11118 27560 15610 21015 15170 14444 10234 13479    NA
## [2071] 45824    NA    NA  5719 17365 14906 30193 15178    NA 12433    NA 37968 19081 16348 23512
## [2086] 19623 11179 29479 30542 13178 22730 15057 14143 28830 28754 15242 22387 23437 22102 22474
## [2101] 12188    NA 13957    NA 12718    NA 19689 17005 18674 26813 21351 21834 15422 23593    NA
## [2116] 40582 17471 25923 52413  8707    NA 16087 18500 28581 39916 11846    NA 28948 16448    NA
## [2131]    NA 28298  9929 41309 17093 19117 12683 12075 13773    NA    NA 62594 37363 30945 33354
## [2146] 42688 33016 11500 15055 13265 14096  9594 38575 12338  9017 15753 12769 12189  8958 13562
## [2161] 31310 14664 13463 10878 11260 16434 18486 17440 17290 32987 13301 14947 18555 20250 22322
## [2176] 26429 10671 15402 13073 33226 46248 36370 27873 35673    NA 16388 19212 25840 23987 11490
## [2191] 10126 36214 22658 16860 24424 10728    NA 36429 21024 11324 15207 36592 10071 30383 21473
## [2206] 15731 15002    NA 11346 26127 16926 15268 11838 29598 26616 18529 17478 21398 12845 19245
## [2221] 30711 44600 12067 13918 50644 15380 27321 61398 15726 15448 44410    NA 20578 17006 24678
## [2236] 21585 46261 26715 39677 19197 29520 24614 21507 24828 19062 19858 23322 18684 16905 16741
## [2251] 18859 21319 39525 48016 21198 17576 31300 26062 20918 23880 11917 34369    NA 38858 11196
## [2266] 11534 38223 10511 44586 19231 27704 25861 23821 18265    NA 10866 13884 33495 25714 56932
## [2281] 13011 18048  8554 19377 43227 41750 51159 19274 38533 26970 11530 18476 30112 33787 35434
## [2296] 11853 19058 31388 19462 23496 19192 19857  8484 10545 42307 22773    NA 25206 22923 19342
## [2311]    NA 25152 26700 13635 24593 20977 19003 11420 21934    NA 55430 22000 27781 35223 48163
## [2326] 27637 22048 28011 22046    NA    NA 40921 10053 46869 26024 43899  8611 59479 26086 17520
## [2341] 13337    NA 28943 26992  9211 21990 20153  8946  9178 12509 11190 11844 15021 12146 15287
## [2356] 15611 11954 14200 12542 17600 11743 16822  9582  9653  9923 17290 11069 10358 11305 15349
## [2371] 41417 24154    NA 12228 13022 14010 15174 15121 30790 41559 10166 25718 21093 40718    NA
## [2386]    NA 38830 28132 33155 49143 17167 29577 44526 22022 18064 18138 15973    NA 60280 59581
## [2401] 18824 36229 15275 12900    NA 20563 26225 18696 22104 18791 10608    NA 10787 20973 20548
## [2416] 22390 21458 21309 32556 42796 18229 34237 11746 41576 23043 17325    NA 38575 54772 12126
## [2431]    NA    NA 57745 28391 61540 10391 19105 36593 16049 17674 18708 56735 59572    NA 11647
## [2446] 15993 40694 15112 13310 14170 13903 14298 14041    NA 13674 14478 13308 12563 13625 12957
## [2461] 15240 13584 13676 10784    NA 13967 11599 32741 32649    NA 35825 39399 10654 13631 27982
## [2476] 50608 10056 16428 14529 31557 56604 60451 12343 34385    NA 11590 57420 48699    NA 13277
## [2491] 25575 57699 49604 38352 12832 20534 13172 22166 44623    NA 25648 53521 13481 17684 10467
## [2506] 32130 53212 16975 11900 42008 41111 42068 42712 44701 18641 19536    NA    NA 18525 25639
## [2521] 44895 53903 49907 17344    NA 45962 16410 45323 30598 15659    NA 26740 21283 16625 14400
## [2536] 26658 23043 20857 12587 17215 12635 36702 21039 12121 38808 37738    NA 11811 41298 12038
## [2551] 43273 57203 11905    NA 26711    NA    NA 18025    NA 60059  9451 38829 17557 13533    NA
## [2566] 39014 41178 34586 17600 14775 10197 21500 50625 38860 17454 18845 50199 21593 54582 29568
## [2581] 18400 13955 13100 18750    NA    NA 17300 59470 18141 38826 23703 45772 59156 13302 19217
## [2596] 40437    NA 41265 24739 23992 57423 40267 36823 19232 62636  9626 18300 45452    NA 58562
## [2611] 25290    NA    NA 23250    NA 39014 28127 12704 50233 19079 23438 13710 21127 19394 20134
## [2626] 21178 15258 22083 21249 21966 20885 20611 22550 19843 19511 18088 21840 20802 21004 20428
## [2641] 20762 21222 19829 22381    NA 15888 20371    NA 19755 21493    NA 24281 55600 17708 13000
## [2656]    NA 22032 14886 16030 23347 21346    NA  9927 22776 58023    NA 15572  6603 44394 21465
## [2671] 59320 22374 48993 49453 18520 48142 32487 11769 14625 21209 14910 12927 16800 17260 14737
## [2686] 16360 53825 15573 18100 11908 32230 12956 17780 14840 37437 14383 39328 28398 12281 12877
## [2701] 35062 26627 12230 19688 22646 40323 14454 23742 12843 37818 15402 35177 14513 15275 32188
## [2716]  5111 13567 12170 12419 54930 59528 10210 19851 11539 10620 41679 13825  9451 13188 10733
## [2731] 35790 15539 37497 44255 17563  8075 13302 13840 42300 11031 11484 17288 30314 11797 37299
## [2746] 10134 39425 12346 25050 26459 36669 10256 15351 10080    NA 39296 45011 26443 14266 13915
## [2761]  9190 13742 11249 33963 26161 15460 10933 15313 17468 23069 17767 17362 17873 19666 20511
## [2776] 36686 18165 11897 37712 15784 34515 22699 14632  9925 40930 13724 11265 24257  8909 10738
## [2791] 11982  9724 31095 39859 15407 13165 27079 15666 38467 17709 12282 13252 16627    NA 13655
## [2806] 15608 11835 12680 58260 13068 41000    NA  7060 12507 10201 12868 35465 12300 10149 15990
## [2821] 17805 24818 11009 13314 13310 15165 12369 27712 14849 12414 10829 22936 15452    NA 14549
## [2836] 11052 20538 13048 12174 18277 13375 19261  9241 24764 11907 11699 16086 16905 32193 30103
## [2851] 23483 21338 14969 13993 11857 24023 12978 32485 12292 40835 14997 20087 24311 37504  8948
## [2866] 40078 25172 13130 22416 21115 10039 22291 19010 42600 10861 19249 16619 17158 55783 33652
## [2881] 13727 18708 17380 16142 19851 25338 25900    NA 25799  9626 16442 16185 33077 10638 10151
## [2896] 50146 12798 59724 22041  7834 22572 39478  9823 10552 29961 12017 46250 38824 54490 20179
## [2911] 11194 12554 21527 25719 38941 26710 10776 14597 25222 18795 14781 16197    NA 35668 42672
## [2926] 26363 13367 38286 19766 25406 28122  7896 45714 32923 13271 15505 14496 13118 14558 14423
## [2941] 14088 23995 12967 57910 19993 39085 10421  9798 13888 21675 21223  7566 27429 35213 42205
## [2956] 11486 14330 22624    NA 17107 18054 30858 29769 11808 13520 25491 37502 33321 31989 13100
## [2971] 33630 27901 23835 15879  8873  9103 13795 16210 36250    NA 20431 59683 25618 25305 40370
## [2986] 25556 49618 20810 15637 18551 15170 18554 10694 14219 17892 16383 24524 12274 14342 14192
## [3001] 14041 23605 12661 18163    NA 52819 41646 10364 14236 24818    NA 35748 30617    NA 15660
## [3016] 13768 26549 30944 37702 17742  7788 18570    NA 29943 29943 29943 23598 23295 26020 24963
## [3031] 18123 20242 32761 11258 23584 11609 12723 34771 21263 28455    NA 14644 20242    NA 28555
## [3046] 24093    NA 22824 31686 35976  7880 25839 34994 12040 21542 24400 39415    NA 50728 51300
## [3061] 20762 14608 45080 26360 17350 17256 26400 32241 31210 13831 11321 14852 10449 17256 16684
## [3076]  8793 13115 13735  8757 11719 21251 15059 23637 14566 13531 13665 26339 13296  8950 10498
## [3091] 12946 13065    NA 29359    NA 15439 21338  9634 31759 12221 41431 23263 18274 12161 35070
## [3106] 14930 22795 17213 12390 32671 17791 15440 14233  6862 14050 22983 16660 11414 28819 46560
## [3121]  9419 11478 11634 17111 10833 14010 23847    NA 31642 12315 14325 13931 11615  7448 11193
## [3136] 11988 23703 35963 20819    NA 18959 14188 21311 41836 12413 27139 13732 53455 45708 12996
## [3151] 15418 34155 12856 15296 31917 14521 33878    NA 14386 34807    NA 18801 35850 22974 22390
## [3166] 43235 47922 12921 12670 13161 14070 17529 12483 19843 51036 57701 13643 10907 24261 12970
## [3181] 18285 13915 13633 12972 30830 38834 12249 27177    NA 52665 21732    NA    NA 17001 19725
## [3196] 25576    NA 46170 15706 10100 50044 18284 45331 11193 39999 19863 30947 31192 31690 14169
## [3211] 33201 17886 28001 11837 48907    NA 19939 21732 23835 57586 59090 11979 14519 18723  7849
## [3226] 43541 23081    NA 21896 35640 59710 41240 24548 44591 42663 21605 24929    NA 20478 12240
## [3241]    NA 20185 16803 24396 10914 44778 58149    NA 31385 53831 19227 23298 42280 20282 39764
## [3256] 19886 47390 17215 18065 18383 17636 18026 17146 16864 18367 18320 17709 17541 17995 18708
## [3271] 14885 22890    NA    NA 20712 58518 37572 34818 55770 17389 18914 18811    NA 39051 33543
## [3286] 14041 59654 30930 31949 20583 22907 45011 22936    NA 15814 17137 23767 47269 31012 28583
## [3301] 41453 20755 23130 35493 47134 20649 57688 27372    NA 15234 20877 14655 46169  8729 21759
## [3316] 55441 17567 23262 19641 22497 19145    NA    NA    NA  9879 44256 11909 23119 21432 41657
## [3331] 20387    NA 42367 41341 33375 21756 38504 11472 47675 45863 30884 53637 26486 37314 13487
## [3346] 10525 16629 21058 19665    NA 16794 27759    NA    NA 20315 21867 20301 20183 19456 27591
## [3361] 22942 25931 26651 19297 21299 19753 25745 31625 24415 25553 19611 24227 19761 14409 19700
## [3376] 28652 20241 16840 43656 24273 45982 18065 28860 59600 46451 52401 32509    NA 49327 11539
## [3391] 23732 23343 23709 30410 22596 20904 26732 18912 27593    NA 40651 36726    NA 10979 14208
## [3406] 21912    NA    NA 34280 24158 38274 26481 45067 42492 52779 41591    NA 15427 51962 40497
## [3421] 29814    NA 12977 20840 21303 36410 19371 26582    NA 18601 49025 58481 13650 17900 27247
## [3436] 39573    NA 26097 26420 25506 21659 25457    NA 57163 29736 43500 20165 56265 24119    NA
## [3451] 49507 28822 16301 24997 17603 20044 42474    NA  6230 50294 42612 39818 13975 27266 12524
## [3466] 23415 18504 58140 50858 40136    NA 30656 12754    NA 56184 14858 10617 26262 59597 48476
## [3481] 48219 23520 17265 23281 10179 21447 35340 33245  9742 30534 25781 31054 17115 25086 16848
## [3496] 13226 24827 29849 27944 11215 32029 28141 37599 39748 11709 45198 11747 22865 19965 55434
## [3511] 13716 12890 17750 21127 21628 34658    NA    NA 11399 20419 37837 28373 12312 13076 45130
## [3526] 18466 19354 23685 16937 19403 16781 17501 21601 25265 20848    NA 25085 12676 13550 12973
## [3541] 16086 12239 24486 14439 24595 47856 13006 36828 11458 15906 24803 17201 31596 14582 15109
## [3556]    NA 14263 33103 21387 21551    NA 17334  8996 26676    NA 20234 18547 20101 33909    NA
## [3571] 10346 15085 11033 18843 14726 26086 31324 18874 12173 18852 19745 41450 26864 29489 32446
## [3586] 13039 34413    NA 10764 11572 24355 12744 33402 37181 13159 28539 14428 22485 24954 13687
## [3601]    NA 16490 38893 25413 32814 14538 10844 27295 15673 14007 14503 19114 19898 18973 36533
## [3616] 34415  9600 17406 16427 23554 31241  9608 31701 41481 13202 14778    NA 37855 11895 20899
## [3631]    NA 23179 17501    NA 36252 13972 12466 13774 18541 25932 11144 15014 35632 13131 16688
## [3646] 13271 50659 12537 13454 10896  9956  8801 46530  9586 15655 12815 14921 12199 19775 13678
## [3661] 29085    NA 28119 19192 24746 16227 29878 14873 16903 19900 23217 30820 11771 32783 40415
## [3676] 14245 59890 13268 13933  9931 16740 13738 39811 11617 10206 35448 23130 10274 19511 16405
## [3691] 24783 30536 45800 13622    NA 12441    NA    NA    NA    NA 51086 10646 13458 27742 18534
## [3706]  9026 11714 31270 31401 10583  9477 18747 12321 11314 37394  9901  9734 17782 22118 26868
## [3721] 32489 24499 20182    NA 47437 10405 27557 30172 14147 18487 11702 10902  9466 25633 23561
## [3736] 13836 31013 14187 11024  8025 14438 19102 32001 11924 13463 36095    NA 13488 18879 17508
## [3751] 22215 11349 32861 25894 34487 20907 16633 27612 26525 13572 22395 24478  9809 21142  8118
## [3766] 14715  8915  9558 15272 11869 37031 22168 16419 28493 12693 35000 13062 34650    NA  9844
## [3781] 11318 15704 11322 26394 30001 11832 27295 14243 13668  9732 10231 11528 18593 11979 31642
## [3796]    NA 28288 10250 19773 19933 33227 11601 13651 12191 11567 21418 16782 11069 28413 52242
## [3811] 12325 24175 43046  9615 37271 19173  9314 11890 33631 17377 35160  7602  8193    NA 30722
## [3826] 30545 57947 22793 36226 12070 29652 46789 21909 19721 27907 14566 17254 17709 10167 11148
## [3841]    NA    NA    NA 12181 13304 19721 20819 21420 25176 22381 15272 19366    NA 48189 20765
## [3856]    NA 35480 14292 18936 25625 22311 20900 16287 30696 16345 46274    NA 15157 19141    NA
## [3871] 12655 22160 16183 10820 10769 11745 14304 21543 11157 17553 10213  8520 20096 13499  5550
## [3886] 17174 14544 28799 23381 13779 14008  5416 19421 10143 11281 19270 23998 27563 13688 24315
## [3901] 13273 12410 18042 22107 26204  7378 16020 14213 11192 19048 13204 37990 60556 33685 20799
## [3916] 44636 14004 27188 44446 20404 19178 50770 59200 29270 47341 15884 48894    NA 33200 33229
## [3931] 40202    NA 22937 27788 15863 23908 36240 12233 33668 41180 25938 26825  8537  9586 24696
## [3946] 23790 20490 21052 31688  8714 10712    NA 31740 40866 38009 10029 38620 22332 10402 49139
## [3961] 32358 46049 11262 21980 10469 23730 31344 23707 10732 41818    NA 39432 21862 36832    NA
## [3976]  9755 25557 10190    NA 27312 18837 13571 20531 10517 10323    NA 23379 11349 19987 17521
## [3991] 45842 44330  9764 43594 13460 22508 55980    NA 48559    NA 41369 30068 12627 12328 15439
## [4006] 14898 32554 46966 11603 10521    NA 18365 10694 39429 25513 11110 25291 25255 24643 12563
## [4021] 22538 20075 26885 41010 17103 56616    NA  8261 25354  6798 17178 32304 16091 12716 11103
## [4036] 12922 25662 27251 21401 12789 33268 16214 12319 11423 13262 45406 34595 19831 13066 13067
## [4051] 18049 21433 12178 14575 46475 12513 13465 18386 25933 13012 15582 19108 27385 28214    NA
## [4066] 18189 13045 12394 11873 31957 11030 11153 12833 11124 34608 10989 17824 45299 12027 53785
## [4081] 12556 40458 12580 12324 24078 45125 50610 12969 13708 12214 11404 12334 12377 11743 11921
## [4096] 34747 26292 24606 12316 25617 22009 12200 54865 45655 12883 33057 12668 22543  6177 16673
## [4111] 38226 14940  9347  7877 32147 12377 17146 32812 14710 19910    NA 12916 21400  7021 16361
## [4126] 12162 29813 12815 15307 20493 30493 17589 27759 10490 12344 11620 28953 14846  8919 11500
## [4141]    NA 13756  6694 18406 14465 38796 27271 16281 23764 15808  9151 16898 34213  8456 15620
## [4156] 15271 30496 11611    NA 48236 12950 37563 37963 44910    NA 36660 35645 11361 12354 13272
## [4171] 14589 26613 32706 11438 50570 23879 33656 46649 17600    NA 12850 13312 40585 43747 13941
## [4186] 33166    NA 11329 13572 12935 24320 39123 40966    NA 40204 33274 15321 12299 20915 13105
## [4201] 32956 12925 12781 13010 16107 13235    NA 14907 18066 16878 17896 34192 16935 15218 22668
## [4216] 18192 16953 23718 21203 16824 16682 16427 11383  9735 13006 11177 10996 12329  9862 11588
## [4231] 32923 17652  6410  9919 13026  8394 11973 10126 15030 15218  9246  7888 13059  7695 11573
## [4246]  9409    NA  8006  8725  9395 11355 11516  9801  7547 14431 12004    NA 13054  9762  7248
## [4261]  5025 10288 14074 10979 11053 11754  9642 10167  6405  8139  4157 10830 10896 12408 11331
## [4276] 13319 10884 10578 11944 10413    NA  8982 15986  9859 11478 12604 14610 13413  9223    NA
## [4291]  8055 11056  8509 11945 11428 11686 12781 14726    NA 13018  8020 14375 13488 11643 11651
## [4306]    NA 22825 19369  9351 14214  7267  6361 16261 58408 23109 19540    NA 12952 11112 25911
## [4321] 27016 24366 29676 20052 10908 14590 21563    NA 22592 24542 14962 12247 13462 22405 15787
## [4336] 17185 11677 56453    NA    NA    NA    NA    NA 36062    NA 27266 22187  9047 13338 26410
## [4351] 11218 23939 24999 25961 24716    NA  9032 16145    NA  9161 15837    NA 11126 14990 22271
## [4366] 26467 19354 29398 29688    NA 21789 13683 64233 20303 13800    NA  9176 11033  9929  8487
## [4381] 16616 10884 12015  6887 12838 20315 18394 19804 10218 38655 23988 13076 23299 14674 27770
## [4396] 18864  9277 22655 12853 22845 27501    NA 30957 30204 28616 15660 16311 24904 27353 13027
## [4411] 28290 28979 24113 17712 15657 11049 16504 20452 33751 41957 23712 24335 18603 23776    NA
## [4426] 15039 24570 29258 25985 12647 14716 21789 27328 21590 21206 16085 23091 24858 25057    NA
## [4441]  6960    NA 19781 17623 17098 21115 26888 16502    NA 22617    NA 21469 16867 33195 14929
## [4456] 22340 24354 13850 17130 25105 29352 22867  9769 15637 17300    NA 14950  8330  8465 33800
## [4471] 11978 12306    NA 25678 20636 19515 13501 10157 17315    NA 13415  7625 12942 14241 14106
## [4486] 10103  7996 26057 15110 20243 31955 14581 28771 19211  6310 24405 16605 12799 12086 18019
## [4501]    NA 13440  9192 17896 15154 13287 15105 21300 20892 16588  6255 22408 27341 28929 18601
## [4516] 26443 12590    NA 10819 10765 18214 10786 11269 27758 27402 21030    NA 27016    NA    NA
## [4531] 10881 27050 27074 26516 20386 24733    NA 27830 24518 11620 12532 25151 16669 24901 17713
## [4546] 24017 37924 34950 17655 12980 28298 20001 12052 17165 11349 12342 23659 26963 24208    NA
## [4561] 17882 24448 16298 18653 23420 13727 28291 21352 17943 27607 24327  5322 39113 24044 28854
## [4576] 12007 10716    NA 29349 10855 27750 18374  8219    NA 23368    NA 15470 13059 16672 22162
## [4591]    NA    NA 27179 21198 14648  7085 16035 13868 27618  4886 22157 23574 14205 20711 21422
## [4606] 25872  3275 20837 25047 20860 11874 19605 24094 19202 22787 17625 19088 26832 23581 22568
## [4621] 27149 25592 24247 23762 18166 18836 16609 11817 18454 18395 24737 19146 24040 30766    NA
## [4636] 14649 11861 15852    NA 27162 20441 25874 19407 21450 17055 15948 12798 12798 18207 13267
## [4651] 27141 23464 14013  9100 15843  6676  3057  8248  4047  5619 13455  8432    NA 13663  6095
## [4666] 21016 11988 20620 20106    NA 11666 13527 13039  9253  9682 13911 16855 15314 14172 12974
## [4681]  8323 15825 26492 27701 16826 25465 15906 15863 15232 19271 28639 27455 10934 31639 22800
## [4696] 22185 11800 32516 26580 32655 33086 15893 18142 24989 24166 14863 19978 21842 11991 21360
## [4711]  5508 21217  8793 27522 11451 13956 11162 17511 22982 18724 24514 22295 16860 16311 17906
## [4726] 16591    NA 34689 22114 19898    NA 16581  8395 16669 17926 17220 11604 12572 26446    NA
## [4741] 16288 25962 22045 24858 21856 18886 21451 17744 19168 20691 12111 20324 24851 11783 25021
## [4756] 16254 10599 24939    NA 10774 21102    NA 13013 24821 28327 16188 11879 18826 14165    NA
## [4771]  9283 29687 18167 18583  9065 24619 26308 13544 30796 42291    NA 11959 10837 23340 19372
## [4786] 23083 18478 32946 20276 27322 19258 29649    NA 13198 21303 25797 29103 10346 22210 13348
## [4801] 27739 10063 18725 20169 10125 27839    NA    NA  9671 24013 31850 21487 13043 33979 16674
## [4816] 13649 25847  3708 21368 16008 13951 16777 25308 27214 28093 34150  8843 28736 40842 24523
## [4831]    NA 20245    NA 15153 10734 18647    NA 50053 17918    NA 12968  7073  6103  6399 18995
## [4846] 27090 18079 17850    NA 35082 23209 22820 23251 14389 22508 23256 22382 18523  8961 14894
## [4861]  9176 22423 22867 28371 18012 18338 16400 30227  6755 15971  8376 24367 23272 23147 23848
## [4876] 24988 23898    NA  9045 23851 28604 16341 29943 12872 18334 19555 16444 21068 15180 31522
## [4891] 20269 20718 27999 23051 11676 12207 18299 25434 27467 24956 16506 19037 24932 19949 15151
## [4906]    NA  8820 17630 17899 10524    NA  8670 14320 20522 15081    NA    NA 15085 19454 17039
## [4921] 17308 22403 23423 28336 17423 14382 26831 16285 25220 17270 17636 27139 31625 18141    NA
## [4936]    NA  6412  8939 13234    NA 26386 18479    NA    NA 22680 22179 27792 25758 21475 33677
## [4951] 14519 26125 30575 21377 25698 22418 22602 23166    NA 16258    NA 14075 29432 28080  6597
## [4966]  8605    NA 15141 15810 33734    NA 24182 12865 23458 11684 27523 25911 27093 27517 25735
## [4981] 17947 12868 11998 17143 17141 17340 13412 14992 14363 27549 15982 11371 26437 26800 32172
## [4996] 24120 38974 26505 18960 18080  7098 25181    NA 17701 30596 24024 25844 28435 21398 14197
## [5011]    NA 23755 18054 20173 18726 14059    NA 11894 19742    NA 22857  8664 17570  6195 22094
## [5026] 29768    NA 18071 17430 23121 20504 23440 16168 18558 16593 16584 27978 11869 11035 25284
## [5041] 25605  8326    NA 16921 17578 14539 17840 29238 10740 24435 21072 16905 16629 13871    NA
## [5056] 19864 20026 19687 17880 19441 22356 17786 27313 38650 26280  6678 13325 15475 15997 24979
## [5071]    NA 14235 10689 11148  5327    NA  9191  9177 15185 15900 20872 14067 14763 18563 14275
## [5086] 16631 15852 11499 12920 15411 20262 15017 19245 12870    NA  8478 10898  9112 15016 10877
## [5101] 27848 20780  8771 14243 12700 10625 19867 16289 25308    NA 10983 36084 17549 14098 25557
## [5116] 12864 13180    NA 25783 22802  6346 23317 18590 23931 14388 22324 10854 11235 11095 29195
## [5131] 27395 24021 21582 25481 16190 13086    NA  8069 20980 22243 20063 16203 26198  9110 26209
## [5146]  8764 13589 17048 30425 23497 24130 15647 11981 21256 32833    NA 13305 24365 11936 23197
## [5161] 25395 24464 13548 12119 12014  7234 10618 24240 12017 17277 23461 51591 22309  9129 22501
## [5176] 11881 21205 14969 13325 11764 34051    NA 13068 20562 18636 23107 18948 20233 20932 23570
## [5191] 32314 10316 26437 22756 16258 30355 28048 11844    NA 11852  9369  7118 11634 17424 27672
## [5206]    NA    NA 30219 19739 12035 30617 89422    NA    NA 28520 14399 26811 30628 22236 31944
## [5221] 25912 26104 24964 30831 32554 18076 17865 27938 20789 27237 17630 17616 25694 25665 28060
## [5236] 26022 28711 28324 43482 12519 11455    NA    NA  9411    NA  5804 32784 26695 17435 14015
## [5251]  8209 13412 29372 20938  8427 18727 19782 17545 20289 11841 27781  6515  8788 12324    NA
## [5266]    NA 16259 15297 12230 10883    NA 31050 13933 14918 18828 11249 17255  7597 25613  9524
## [5281] 22086 19388 18000 11282 16512 24058 24333 24184 17156 25667    NA    NA 33392 35381 33399
## [5296] 29966 30441 15263  6212 26387 14770    NA    NA 14470 25401 25081 27524 23217 18097 30119
## [5311] 11658    NA 27714 11995    NA 23570 17660  9764  9290 19967 27417 22010 12074 11714 15022
## [5326] 28846    NA 23134 15078 15949 29879 26981 27456 25121 26866 27006 17895 11920 25944    NA
## [5341] 13701 27076 23659 13606 12545 17700 23898 24315 24152 23434 23037 23434    NA 19887 12264
## [5356]    NA 16001  8653 22793 14380 24046 22104 29511    NA 22608 11895 29644 25763 12394    NA
## [5371] 10600 39561 24192 21744 17826 18803 26913 18445 13099 12946 13028 26146 27093 22650 17250
## [5386] 12970 25362 20555    NA 24488 27433 24559 11953 26169 21535 27243    NA 26275 28249 18995
## [5401] 21052 27364 14105 27456 23459 30635 25553 27614 23490 23249 22887 21146 20574 11820 23434
## [5416] 24448 29327 23461 23799 24664 23072 23434 25260 26502 12105  8488 28671 30359 29294 28996
## [5431] 12888    NA 22539 26519 27410 26677 27139 13792 14451 25521 38686 25594 19955 20115 21194
## [5446]    NA 15826 21710    NA 40651 10693 27251 25969 17807 14913 19914 16159 19050 10040 11846
## [5461] 17137 22897 19304 18583 28959 13194  8482    NA 24069    NA 17532 15999 19456 14668 18792
## [5476] 26041    NA  8756    NA 10953 21448    NA    NA 26132 19549 25363 18387 28163 25424 28458
## [5491] 15394 14601 12108 23141 26370 28017 25718 23837 29840 29359  9282    NA 23434 24294 24179
## [5506] 24282 24034 28403 26339 12367 12829    NA 23988 20843 12941 26171    NA    NA    NA 23183
## [5521] 22068 22488 22614 20882    NA 20648 18332 12970 25769 25147 29860 11862 34371    NA    NA
## [5536] 15207    NA 15380 26935 10666 44277 11205 20210    NA 17909 21318 14850 30716 23347 16935
## [5551] 12450    NA 20980 19671 15302    NA 25377 28756 27622 10705 19622 13164 17232 26750 31634
## [5566]    NA 25362 16450 26138    NA 10933  9161 24286 12600 14321 17178 30146 15509 22519 14360
## [5581] 15191 16547 16122 22381 22570 26613 26437 32068 59275 22793 22374    NA 26061 22444 24514
## [5596] 22715 24383 23234 22347 19051    NA 24365 20936 19987    NA 28459 27412 27446 28816 17627
## [5611] 22369    NA 16580 22689 28774 18094 15252 28206 28595 25067 27985 17800 25370 20444 23880
## [5626] 28668 29495 25314  7853 30277    NA 31163 27450 33668 26644    NA 21679    NA 21448 21688
## [5641] 17030 22849  6669    NA 23595 21795    NA 11073 27125 19728 15132 22717 15246 25879 18228
## [5656] 12643 20786 27776 21654  8726 19169 41318 20737 17280 24535 37848 26364 28772 23434 35405
## [5671] 13695 27093 26344 23692  9819 26334 23600 19473 20460 21603 25624 23880 18398 28900 12980
## [5686]    NA 27440 25717 32554 32554 25097 27118 21536 27697 23814 23827 23331 21563  8931 16457
## [5701] 25721 14101 13896 25036 27459    NA    NA    NA 22041 17892  8971 28619 15048 15123 26461
## [5716] 29475  8009 18625 18877 17970  8798 22823 22435 24571  6262 17411 13927 21736 14542 16569
## [5731] 16000 13710 24165 13843 20609 22898 18237 31430 30512 30117 24786 14879 22111 16486    NA
## [5746] 26910  5150 23160  8730  9160    NA 11922 30421 20576  9009 19501 24685    NA 21644 24242
## [5761] 17123 24555 29299 11052 29827  9026 22407 11846 27181    NA 12528 22497 26698 25911 22176
## [5776] 20537 20796 24724    NA 30637 25893 26917 19171 24183 23582 30472 25744    NA 28444 22602
## [5791] 25594 23945 26399 24548 27287 27005 23434 26993 27493 28204 11597 17066 12262 22233 27069
## [5806] 28875 30463 24787 20857 17285 20021  8372 16524 37379 39499 24393 23210    NA 24083 15140
## [5821] 29543 26936 18186 22861 22603 17922 16900    NA 17196 22052 29130 28296 16468    NA 11303
## [5836] 18215    NA    NA 34729 28444 11132    NA 24696 26705 21703 22795    NA 25080 20576 12985
## [5851] 13483 13973    NA 25657 18638  9663 16448 17192    NA 12348 34758 19825 23524 16039 28116
## [5866] 27515 35260 10338 10793 35041 25293 12831 21404 25465 13360 23382 25786 15794 35931 31416
## [5881] 27787 23434 24514 24514 23434 23434 13531 20099 22472    NA 21070 20678 26812 23651 27539
## [5896] 26402 26492 27139    NA 17891 21219 26012 19353 30640 27124 27385 15803 15467 16488 16606
## [5911] 29895 28693 29665 22761 30189 12022 37574 25416 25708 20911 24252 24438 24627 22304 15181
## [5926] 26816 25498 22964 26934 15757  9764 29989 27508 24021 29846 29413 11434  7894 25439 23529
## [5941] 25489 23754 23487 28352 16501    NA 13959    NA 19022 16515 12628 28412 22722 13180    NA
## [5956] 28009 74473  5700 19995 28394 15205 22328 16784 10513 27707 26941 19987 17755 11355 21919
## [5971] 10954 26517 14532 13894 19911 17624 24220 13145 26167 15058 17037 13148 18422 15908 17409
## [5986] 10949    NA    NA 24146 22596 12916 31260 30922 22480    NA 22151 26696 16164 23206 26267
## [6001] 25989 24905 26994 26994 27523 28238 27803    NA 23206 23434 31616 22091 13014 23041 23679
## [6016] 32004 25548 25579 23827 15689 13885 24365 28620 24051 17390 17308    NA 23434 23434 18821
## [6031] 25016 22909 19566 26028 29603 32308 32554 24302 21062 21898 24929 26887 12217 12304 12339
## [6046] 24154 23824 24204 23923 24766 24627 25671 25378 25480 23106 24712    NA 22042 22105 14185
## [6061] 12805 22330 30703 25637 34428 13253 29722 24250 25339 15887 11942    NA 14842 19814 22262
## [6076] 19817    NA 14888 14591 25225 14700 23950    NA  8550 26741 22243  9642  6515 32800 28124
## [6091] 14954    NA 14925    NA 13289 25163 19082 28639 19695    NA    NA 18548 21047 18308 18881
## [6106] 18462 26693 24669 30943 22707 30890 26588 32345 33645 26062 25618 20438 29375 26272 23048
## [6121] 21900 28675 25584 27753 28306 28314 27412 27630 27932 20882    NA    NA 32554 17935 21070
## [6136] 28230 23090 23918 24391 23268 23434 23903 24461 24365 27325 24691 17430 18343 17970 17689
## [6151] 17940    NA 15312 25068 28007 27978 21219 21163 18059 19133 14682    NA 25979 26428 24256
## [6166] 22877 22999 23411 23953 24277 25207 24741 24214 13265    NA 39135 25548 18864 19990 21600
## [6181] 38341    NA 17335    NA 24572    NA 11399 25705 16319    NA 16856 15709 23731 11717 18055
## [6196] 25780 13167 15806 27188 17499    NA 16297 11462 15413 10288 23083 18609 29376 19236 12550
## [6211] 39146    NA 17829 10500 16090 28547 23552 13185    NA 15287 13157 12395 20835 18043 22113
## [6226] 18215 30337 13196 13247 28406  6971 11778 32424    NA 24621 28234 21352 11439 21006 26754
## [6241] 30508 17594 17742 31680 31937 26455 27396 24420    NA 25415 18209 27586 27490 26648 27069
## [6256] 26648 27139 27428 14781 31075 32389 23405 24129 24497 20138 21225 23274 23107  5238 15462
## [6271] 30528 27097 24509 31133 24074 32554 32554 32554 26668 24819 26668 23304 29753 16232 20794
## [6286] 23834 24794 17890 28908 44720 24552 25521 22228    NA 25811 23304 23877 25511 26187 23759
## [6301] 23522 23517 24469 23610 24732 25095 25111 24328 23851 25608 22213 15271 19773 19028 20325
## [6316]    NA 28494 18957 30978 18630 21493    NA 15958 17984 15783 18415    NA    NA 18590 25476
## [6331] 11879 26256    NA 27809 23110    NA 10303    NA 17072 18837 13990 13097 13160 22751 21664
## [6346] 12220 17479 13882 14036 19657 16987 20685 19719 16133    NA    NA 20148 24357    NA 19673
## [6361]    NA 15742 10979 18830    NA    NA 15455 19893 20692 13829 10818 21710 15645 26176 19659
## [6376] 12633 19763 19726 21106 17657 16462 22442 41287    NA 11626 23310    NA 14893 15014 28764
## [6391] 18908 10507 25802 30106 21858 30362 24127 23865 50374 29943 26468    NA 15626    NA    NA
## [6406]  7350 15564 24415 21090 25063 21768 35917 14298    NA    NA 17112 21457 17608 18147 20890
## [6421] 18769 19721 20605 13046 14536  7354 17262  8650 18751  8700  9809    NA 25420 28629 15684
## [6436] 20454 20008 15984 18267 17034 21189 18527 16875 18309 17676 24528 26098 22814 18934 25840
## [6451] 17856 22291 24124 22829 20956 20660 37108 26419 26430 20814 26194 28368 26525 26353 27656
## [6466] 26686 23402 26577 22784 20892 22963    NA 17322 18754 15399 14389 23438    NA 32554 32554
## [6481] 24087 25021 25125 22956 24794 23824 25764 27810 23203 28338 29699 13137 29869 24118 22006
## [6496] 31298 31911 24744 22141 17166 23214 25666 24317 17606 19003 17729 22235 29665    NA 25025
## [6511]    NA 14054 27225    NA 30229 13779    NA 13671 19831 20062 16233 12144 18259    NA 15270
## [6526]  5918 16300 12565 27163 22579 19457 20926 10613 14164 20502 18314 31366 12894 32995 18332
## [6541] 21049 14345 19467 16510 16965    NA 13164    NA 24730 14959  8729 21870 12419 21340    NA
## [6556] 19955 11222 10900 14070 20055 27250 16171 16334 12218 18931 45588 20484 18036 23537 22219
## [6571] 23700    NA  8666 10280 19650  9050 19628 18679 12327 17582  9517 28400 25455 18085 19666
## [6586]    NA 10437 22490 17038 17706 18021 30998 20246 24525    NA 15514 23783 26261 13575 43784
## [6601] 41496 23956 21509 29510 21696 27260 24744 24004 24397 25194 25296 24577 25776 22600 26851
## [6616] 28588 17970 25952 25468    NA 23678 26044 13853 21300 18867 31586 20711 26771 18947    NA
## [6631]    NA    NA    NA    NA 22863 22272 26213 25009 26714 27040 30686 26927 28450 30146 30285
## [6646] 25975 16537 15578 16855 17978 15980 17920 18201    NA 32554    NA    NA 32554 32554 31351
## [6661] 29929 16353 17309 18167 17420 16849 16558 18343 16585 28230 20755 20432 13405 16540 18433
## [6676] 23303 16861 11644 11196 17473 32958 24672    NA 16873 28471 28881 14184 16838 17965 15551
## [6691] 11223  8330 16500 16035    NA 18415 12180 12628 15852 29928 18790 15100 22147 18286 37105
## [6706] 21400 12672 19050 18632  9083 14991 12383 16272 18025 15907 25911 28894 28613 27428 27139
## [6721] 26613 25173 25344 26608 26832 26525 26800 27139 27586 20498    NA    NA 16260    NA 26560
## [6736] 23712 23928 24722 25571 17652 26372 32554 25802 18026 19267 23926 22330 15330 20253 25820
## [6751] 22365 22409 22271 22055 20272 19451 25318 24830 23976 21721    NA 26049 27339 12250 20476
## [6766] 22527 12678    NA 31242 18592 24745 19009 22634 21448 14543 34106 28715 30471 23867 22726
## [6781] 20942 23899 27245 11115 22430 14863 18197 19997 19605 39183 17835 11269 20769 23519 12521
## [6796] 26996 26442 24482 16069 20407 14012 26120 28213 13687 17666  7201 18939    NA 27298 21690
## [6811] 20243 15406 16586 22840 22863 18603 17692 21023  8732    NA    NA 58218    NA    NA 18117
## [6826] 15412 15063 25010 10836 11689 21667 17872    NA 28175  8801 12201    NA    NA 18180    NA
## [6841] 23961    NA 15609 19248 14445    NA 18601    NA  7815 18672 23098    NA 13507 15551 12558
## [6856] 11758 11799 15220 12432 16438 15457 20980 16706 16882  6368 27398    NA 18779    NA  9853
## [6871] 22817 16776 16563 15719 25821 15263  9586    NA 14984 26873 10608 19909 15760 10568 17779
## [6886] 18445 25242 23641 15147 22204    NA 14021 14616 18090 13481 11714 15262 23319 26585 15658
## [6901] 17196 10348 16215 19701 13072 16640    NA 21211 17836 15252    NA 24722 33267 19438 18677
## [6916] 18844 15656 40896 27753 26226 22994 22662    NA 24096 23880 23202 28514 29571 25501    NA
## [6931] 26788 19075 27478 24228 21576 25134 25392 25465 23915 26835 25187 25469 25296 26464 23099
## [6946] 23855 25257 24732 24602 23664 25067 25081 25174 28135 28372 17310 18182 16992 26092 18326
## [6961]    NA 30693 29650 15653 15084 24497 15808 14330 21018 16591 16022  9057 14075 12199 19760
## [6976] 21350 21512 21995 22540 21999    NA 14243 11677 12063 11551    NA 20331 18615 23510 24523
## [6991] 35793 27343 26825 20563    NA 10997 18158 29785 24121 15192 12352 15668 18623 29596 26994
## [7006] 27753 28462 27563 27563 23434 24993 29536 27752 28440 13747 15263 20319 19871 23154 23434
## [7021] 23434 55632 19729 20187    NA 24075 23289 25865 27031 43608 30660 24465 23769 25945    NA
## [7036] 13413    NA 26526 21702 23623 19702  6172 13947 15740 14571 15180 35950 26092 14593 24582
## [7051] 16062    NA 30511    NA 20322 20360 19577 17482 10818 11221 22839 19685 23168 16331 21731
## [7066] 38389  9332 16004 15112 21499 21865 25825    NA 28916 28814 21487    NA 22975    NA    NA
## [7081] 19457 24154 23907 25082 25893 24978 24908 24312 23461 18361    NA 23624 15699 34422 26928
## [7096] 25409 20215    NA 18597 28957 30004 31001 11825 18000 29427 10027 15589  9174 15177 13849
## [7111] 16741 14129 19312 24746 20200 16736 17115 28675 10257 27718 17400 19915 17099 20408 26720
## [7126] 13710 18114 12557 20441  7570    NA  9977    NA 15944 12272 18748 14495 17341  9825 29413
## [7141] 23126 14517 34424    NA 26482 14135 24820    NA 16860 18105 12302 32554 32554 40829 27446
## [7156] 24420 24420    NA 18043 19559 18437 27068 28222 18937 16398 16185 20633 22188 21414 26076
## [7171]  8200    NA 27037 26437 27753 27895 27753 26832 27362 28122 26743 26437 27039 26880 22065
## [7186] 25441    NA 19971 16758    NA 13924 16025 22543 30687 29061 29650 17894 21752 25202    NA
## [7201] 23765 20367    NA 19651 23276 34187 33931    NA 15763 28554 19298 23983 23997 21456 24380
## [7216] 22417 23516    NA    NA 10492 22479 14904    NA 21442    NA 20622 25863 25947 24348 10367
## [7231] 23138    NA 11829 32858 18582    NA 15041    NA 14674    NA    NA    NA 15205 16458 14985
## [7246]    NA    NA 17416 34756    NA 14292 22416    NA 14575 29969 17734    NA    NA 14795 20925
## [7261]    NA 24716  4955 14480 14501 10125 17669 11617 13737  8928 14676 14801    NA 16329 22457
## [7276] 12151    NA 15300    NA 18500 13251 19401 11275    NA 20626 18050 13733 15397 15628    NA
## [7291] 14373 18486    NA 31554 30517    NA 26964 17061 19832 18311    NA 17692 18339    NA 23724
## [7306]    NA 23935 18608 23111 22578    NA 23380    NA 20132 26343    NA 27095    NA    NA    NA
## [7321] 23731    NA  7715 13472    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7336]    NA 24420    NA 19773    NA 13880 19413    NA    NA 25150 25099 24050 26908 25426 25718
## [7351] 25625 26345 27517    NA 25272 27417 25342 24265 23738 24250 24985 27517    NA 25403 20983
## [7366] 24919 28093 25202 21999 27417 16525 12337    NA 20964 24330 18393    NA 11905  8532    NA
## [7381]    NA 19666 21375    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7396]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7411]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7426]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7441]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7456]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7471]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7486]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7501]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7516]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7531]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7546]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7561]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7576]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7591]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7606]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7621]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7636]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7651]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7666]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7681]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7696]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7711]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7726]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7741]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7756]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7771]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7786]    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA    NA
## [7801]    NA    NA    NA    NA

How are NA variables for this new cost estimator distributed?

colleges %>% 
    group_by(PREDDEG) %>% 
    summarize(`fraction NA` = mean(is.na(cost)))
## # A tibble: 5 × 2
##   PREDDEG `fraction NA`
##     <int>         <dbl>
## 1       0    0.88053950
## 2       1    0.05832832
## 3       2    0.02607562
## 4       3    0.06797937
## 5       4    0.99315068

The fraction of NA variables is pretty low (<10%) for certificate, associates, and bachelors degree awarding institutions. We may want to just remove the “type 0” and entirely graduate degree granting institutions for our clustering algorithm.

For the rest of the 2-7% of NA values in this new cost estimator, we could start with substituting the mean/median for the whole variable, then maybe try something more complicated (random forest, etc.)

Understanding the Aid Data

Let’s look in more detail at all the cost variables.

aid_names <- dictionary %>% 
    filter(`dev-category` == "aid") %>% 
    select(`VARIABLE NAME`, `NAME OF DATA ELEMENT`)

aid_names
## # A tibble: 40 × 2
##    `VARIABLE NAME`                                                         `NAME OF DATA ELEMENT`
##              <chr>                                                                          <chr>
## 1          PCTPELL                          Percentage of undergraduates who receive a Pell Grant
## 2         PCTFLOAN Percent of all federal undergraduate students receiving a federal student loan
## 3         DEBT_MDN              The original amount of the loan principal upon entering repayment
## 4    GRAD_DEBT_MDN                                The median debt for students who have completed
## 5   WDRAW_DEBT_MDN                            The median debt for students who have not completed
## 6  LO_INC_DEBT_MDN             The median debt for students with family income between $0-$30,000
## 7  MD_INC_DEBT_MDN        The median debt for students with family income between $30,001-$75,000
## 8  HI_INC_DEBT_MDN                       The median debt for students with family income $75,001+
## 9     DEP_DEBT_MDN                                         The median debt for dependent students
## 10    IND_DEBT_MDN                                       The median debt for independent students
## # ... with 30 more rows

What are these 40 aid variables?

aid_names$`NAME OF DATA ELEMENT`
##  [1] "Percentage of undergraduates who receive a Pell Grant"                                                                         
##  [2] "Percent of all federal undergraduate students receiving a federal student loan"                                                
##  [3] "The original amount of the loan principal upon entering repayment"                                                             
##  [4] "The median debt for students who have completed"                                                                               
##  [5] "The median debt for students who have not completed"                                                                           
##  [6] "The median debt for students with family income between $0-$30,000"                                                            
##  [7] "The median debt for students with family income between $30,001-$75,000"                                                       
##  [8] "The median debt for students with family income $75,001+"                                                                      
##  [9] "The median debt for dependent students"                                                                                        
## [10] "The median debt for independent students"                                                                                      
## [11] "The median debt for Pell students"                                                                                             
## [12] "The median debt for no-Pell students"                                                                                          
## [13] "The median debt for female students"                                                                                           
## [14] "The median debt for male students"                                                                                             
## [15] "The median debt for first-generation students"                                                                                 
## [16] "The median debt for not-first-generation students"                                                                             
## [17] "The number of students in the median debt cohort"                                                                              
## [18] "The number of students in the median debt completers cohort"                                                                   
## [19] "The number of students in the median debt withdrawn cohort"                                                                    
## [20] "The number of students in the median debt low-income (less than $30,000 in nominal family income) students cohort"             
## [21] "The number of students in the median debt middle-income (between $30,000 and $75,000 in nominal family income) students cohort"
## [22] "The number of students in the median debt high-income (above $75,000 in nominal family income) students cohort"                
## [23] "The number of students in the median debt dependent students cohort"                                                           
## [24] "The number of students in the median debt independent students cohort"                                                         
## [25] "The number of students in the median debt Pell students cohort"                                                                
## [26] "The number of students in the median debt no-Pell students cohort"                                                             
## [27] "The number of students in the median debt female students cohort"                                                              
## [28] "The number of students in the median debt male students cohort"                                                                
## [29] "The number of students in the median debt first-generation students cohort"                                                    
## [30] "The number of students in the median debt not-first-generation students cohort"                                                
## [31] "Median loan debt of completers in monthly payments (10-year amortization plan)"                                                
## [32] "Number of students in the cumulative loan debt cohort"                                                                         
## [33] "Cumulative loan debt at the 90th percentile"                                                                                   
## [34] "Cumulative loan debt at the 75th percentile"                                                                                   
## [35] "Cumulative loan debt at the 25th percentile"                                                                                   
## [36] "Cumulative loan debt at the 10th percentile"                                                                                   
## [37] "Share of students who received a federal loan while in school"                                                                 
## [38] "Median debt, suppressed for n=30"                                                                                              
## [39] "Median debt of completers, suppressed for n=30"                                                                                
## [40] "Median debt of completers expressed in 10-year monthly payments, suppressed for n=30"

Here, I suggest the most important variables are two up near the top (not broken out by income level or whether they were Pell or not Pell grants, etc.).

aid_names[2:3,]
## # A tibble: 2 × 2
##   `VARIABLE NAME`                                                         `NAME OF DATA ELEMENT`
##             <chr>                                                                          <chr>
## 1        PCTFLOAN Percent of all federal undergraduate students receiving a federal student loan
## 2        DEBT_MDN              The original amount of the loan principal upon entering repayment

These would be used separately. How are NA values distributed for these two values?

colleges %>% 
    group_by(PREDDEG) %>% 
    summarize(`fraction NA` = mean(is.na(PCTFLOAN)))
## # A tibble: 5 × 2
##   PREDDEG `fraction NA`
##     <int>         <dbl>
## 1       0  0.8554913295
## 2       1  0.0003006615
## 3       2  0.0006518905
## 4       3  0.0014064698
## 5       4  1.0000000000

Here again we see quite low values of missing data for certificate, associate, and bachelor degree granting institutions.

colleges %>% 
    group_by(PREDDEG) %>% 
    summarize(`fraction NA` = mean(is.na(DEBT_MDN)))
## # A tibble: 5 × 2
##   PREDDEG `fraction NA`
##     <int>         <dbl>
## 1       0    0.10789981
## 2       1    0.20535177
## 3       2    0.07301173
## 4       3    0.06329114
## 5       4    0.87328767

The fraction of missing data is getting high for certificate granting institutions, but it still low for associate and bachelor granting institutions.

Summary