ML12340A815: Difference between revisions

From kanterella
Jump to navigation Jump to search
(Created page by program invented by StriderTol)
(Created page by program invented by StriderTol)
 
(3 intermediate revisions by the same user not shown)
Line 3: Line 3:
| issue date = 10/22/2012
| issue date = 10/22/2012
| title = Official Exhibit - NYS000446-00-BD01 - Analysis by Stephen C. Sheppard Using Tolley Mls Linear Square Root
| title = Official Exhibit - NYS000446-00-BD01 - Analysis by Stephen C. Sheppard Using Tolley Mls Linear Square Root
| author name = Sheppard S C
| author name = Sheppard S
| author affiliation = - No Known Affiliation
| author affiliation = - No Known Affiliation
| addressee name =  
| addressee name =  
Line 16: Line 16:


=Text=
=Text=
{{#Wiki_filter:User: Stephen Sheppard Project: IPEC Statistics/Data Analysis name:
{{#Wiki_filter:United States Nuclear Regulatory Commission Official Hearing Exhibit                                NYS000446 Entergy Nuclear Operations, Inc.
<unnamed>log:/home/steve/Documents/IndianPoint/Contention 17/TolleyOriginalLInearSquareRoot.smcl log type: smcl1. use "/home/steve/Documents/IndianPoint/Contention 17/MLS Data STATA Format.dta"
In the Matter of:
: 2.
(Indian Point Nuclear Generating Units 2 and 3)            Submitted: October 22, 2012 ASLBP #: 07-858-03-LR-BD01 Docket #: 05000247 l 05000286 Exhibit #: NYS000446-00-BD01                  Identified: 10/22/2012 Admitted: 10/22/2012                          Withdrawn:
* Tolley MLS model from report
Rejected:                                        Stricken:
: 3. regress askprice ipdist ipdistsq med_income house_age attached rail_dist pilotpay_2011     Source       SS       df       MS             Number of obs =
Other: Originally Identified as BRD000005 User: Stephen Sheppard Statistics/Data Analysis                                                                                         Project: IPEC name:       <unnamed>
296           F( 7,   288) =
log:     /home/steve/Documents/IndianPoint/Contention 17/TolleyOriginalLInearSquareRoot.smcl log type:           smcl 1 . use "/home/steve/Documents/IndianPoint/Contention 17/MLS Data STATA Format.dta" 2 .
26.44   Model 7028465.17     7 1004066.45 Prob > F     =
* Tolley MLS model from report 3 . regress askprice ipdist ipdistsq med_income house_age attached rail_dist pilotpay_2011 Source                   SS             df             MS                       Number of obs       =       296 F( 7,         288)   =     26.44 Model         7028465.17               7   1004066.45                         Prob > F             =   0.0000 Residual             10937065.5           288         37975.922                       Rsquared            =    0.3912 Adj Rsquared        =    0.3764 Total         17965530.7           295       60900.1041                         Root MSE             =   194.87 askprice                   Coef.       Std. Err.                   t     P>ltl           [95% Conf. Interval]         Dr. Tolley's ipdist           79.32316          69.82126              1.14      0.257          216.7478            58.1015  original ipdistsq               19.90054        10.78365                1.85      0.066          1.324214          41.12529 med_income                 2.382077             .68255             3.49       0.001           1.038658         3.725496   model house_age             5.319204          .7153479              7.44      0.000          6.727177        3.911231 attached             263.2139          31.24132              8.43      0.000          324.7042        201.7236 rail_dist             38.50069          11.35376              3.39      0.001          60.84756        16.15383 pilotpa~2011                   10.38756        15.72596                0.66      0.509          20.56482          41.33994
0.0000 Residual 10937065.5   288   37975.922 0.3912 0.3764   Total 17965530.7   295 60900.1041 Root MSE     =
_cons           577.5368         121.6523               4.75       0.000           338.0965         816.9771 4 .
194.87   askprice       Coef. Std. Err.      t    P>ltl     [95% Conf. Interval]
* Tolley model with IPEC impact modeled as linear in distance 5 . regress askprice ipdist med_income house_age attached rail_dist pilotpay_2011 Source                   SS             df             MS                       Number of obs       =       296 F( 6,         289)   =     30.03 Model         6899132.97               6     1149855.5                       Prob > F             =   0.0000 Residual             11066397.7           289       38292.0337                         Rsquared            =    0.3840 Adj Rsquared        =    0.3712 Total         17965530.7           295       60900.1041                         Root MSE             =   195.68 askprice                   Coef.       Std. Err.                   t     P>ltl           [95% Conf. Interval]         Model with ipdist             46.8946         14.10106               3.33       0.001           19.14079           74.6484   IPEC impact med_income                 2.169724         .6755748               3.21       0.001           .8400531         3.499394 house_age             5.422697          .7161083              7.57      0.000          6.832146        4.013248    proportional attached             276.5584          30.51919              9.06      0.000          336.6265        216.4904 rail_dist             34.94915          11.23594              3.11      0.002            57.0638          12.8345  to linear pilotpa~2011                   19.19545        15.04643                1.28      0.203          10.41904          48.80993
ipdist ipdistsq med_income 2.382077     .68255     3.49   0.001     1.038658   3.725496 house_age attached rail_dist pilotpa~2011
_cons           409.3269         80.90215               5.06       0.000           250.0948           568.559  distance.
_cons 577.5368   121.6523     4.75   0.000     338.0965   816.97714.
6 .
* Tolley model with IPEC impact modeled as linear in distance5. regress askprice ipdist med_income house_age attached rail_dist pilotpay_2011     Source       SS       df       MS             Number of obs =
* Tolley model with IPEC impact modeled as proportional to square root of distance 7 . generate distsquareroot=ipdist^0.5 8 . regress askprice distsquareroot med_income house_age attached rail_dist pilotpay_2011 Source                   SS             df             MS                       Number of obs       =       296 F( 6,         289)   =     29.64 Model         6843474.45               6   1140579.08                         Prob > F             =   0.0000 Residual             11122056.3           289       38484.6238                         Rsquared            =    0.3809 Adj Rsquared        =    0.3681 Total         17965530.7           295       60900.1041                         Root MSE             =   196.17
296           F( 6,   289) =
30.03   Model 6899132.97     6   1149855.5 Prob > F     =
0.0000 Residual 11066397.7   289 38292.0337 0.3840 0.3712   Total 17965530.7   295 60900.1041 Root MSE     =
195.68   askprice       Coef. Std. Err.      t    P>ltl     [95% Conf. Interval]
ipdist 46.8946   14.10106     3.33   0.001     19.14079     74.6484 med_income 2.169724   .6755748     3.21   0.001     .8400531   3.499394 house_age attached rail_dist pilotpa~2011
_cons 409.3269   80.90215     5.06   0.000     250.0948     568.5596.
* Tolley model with IPEC impact modeled as proportional to square root of distance7. generate distsquareroot=ipdist^0.5
: 8. regress askprice distsquareroot med_income house_age attached rail_dist pilotpay_2011     Source       SS       df       MS             Number of obs =
296           F( 6,   289) =
29.64   Model 6843474.45     6 1140579.08 Prob > F     =
0.0000 Residual 11122056.3   289 38484.6238 0.3809 0.3681   Total 17965530.7   295 60900.1041 Root MSE     =
196.17 United States Nuclear Regulatory Commission Official Hearing Exhibit In the Matter of
: Entergy Nuclear Operations, Inc. (Indian Point Nuclear Generating Units 2 and 3)
ASLBP #:07-858-03-LR-BD01 Docket #:05000247 l 05000286 Exhibit #:
Identified:
Admitted: Withdrawn:
Rejected: Stricken: Other: NYS000446-00-BD0110/22/2012 10/22/2012 Ori g inall y Identified as BRD000005Dr.To ll ey's original m odelModelw i thIPECimpact


proportional tolinear distance.NYS000446 Submitted: October 22, 2012 askprice       Coef. Std. Err.      t    P>ltl    [95% Conf. Interval]
askprice       Coef. Std. Err.      t    P>ltl    [95% Conf. Interval]
distsquare~t 149.1657  48.24852    3.09  0.002    54.20262    244.1287 med_income 2.131092  .6773751    3.15  0.002    .7978782    3.464306 house_age attached rail_dist pilotpa~2011
distsquare~t     149.1657  48.24852    3.09  0.002    54.20262    244.1287 Model with med_income     2.131092  .6773751    3.15  0.002    .7978782    3.464306 IPEC impact house_age   5.439066  .7180836    7.57  0.000    6.852403  4.025729 attached   277.9586  30.69289    9.06  0.000    338.3686  217.5487  proportional rail_dist   32.94105  11.14021    2.96  0.003    54.86727  11.01482 pilotpa~2011     20.22589  15.26558    1.32  0.186    9.819931    50.27171  to square root
_cons 296.0152  105.2117    2.81  0.005      88.9368    503.09369.
_cons     296.0152  105.2117    2.81  0.005      88.9368    503.0936 of distance.
* Tolley model with IPEC impact modeled as proportional to square of distance10. regress askprice ipdistsq med_income house_age attached rail_dist pilotpay_2011     Source       SS      df      MS              Number of obs =
9 .
296           F( 6,   289) =
* Tolley model with IPEC impact modeled as proportional to square of distance
30.60   Model 6979449.73    6  1163241.62 Prob > F      =
: 10. regress askprice ipdistsq med_income house_age attached rail_dist pilotpay_2011 Source         SS      df      MS              Number of obs =     296 F( 6,   289) =   30.60 Model   6979449.73    6  1163241.62           Prob > F      = 0.0000 Residual     10986081  289  38014.1211           Rsquared    =  0.3885 Adj Rsquared =  0.3758 Total   17965530.7  295  60900.1041           Root MSE      = 194.97 askprice       Coef. Std. Err.      t    P>ltl    [95% Conf. Interval]
0.0000 Residual 10986081  289  38014.1211 0.3885 0.3758   Total 17965530.7  295  60900.1041 Root MSE      =
Model with ipdistsq       7.8997  2.169942    3.64  0.000    3.628806    12.17059 med_income     2.254154  .6735366    3.35  0.001    .9284944    3.579813 IPEC impact house_age   5.385319  .7133353    7.55  0.000    6.78931  3.981328 attached   272.1092  30.25947    8.99  0.000    331.6661  212.5523  proportional rail_dist   37.46601  11.32286    3.31  0.001    59.75174  15.18029  to the square pilotpa~2011     16.62003  14.74548    1.13  0.261    12.40211    45.64217
194.97   askprice       Coef. Std. Err.      t    P>ltl    [95% Conf. Interval]
_cons     467.6234  73.78841    6.34  0.000    322.3925    612.8542  of distance.
ipdistsq 7.8997  2.169942    3.64  0.000    3.628806    12.17059 med_income 2.254154  .6735366    3.35  0.001    .9284944    3.579813 house_age attached rail_dist pilotpa~2011
_cons 467.6234  73.78841    6.34  0.000    322.3925    612.8542Modelw i thIPECimpact


proportional tosquareroot ofdistance.Modelw i thIPECimpact
User: Stephen Sheppard Statistics/Data Analysis                                                       Project: IPEC name:       <unnamed>
 
log:     /home/steve/Documents/IndianPoint/Contention 17/RepeatSalesAnalysisOfTolleyQuestions.sm log type:           smcl 1 .
proportional tothesquare ofdistance.
* Here is the model that is the basis of Dr. Sheppards analysis:
User: Stephen Sheppard Project: IPEC Statistics/Data Analysis name:
2 . regress nomreturn salepre74post76 distkm if nomreturn>1 & nomreturn<1, vce(cluster id)
<unnamed>log:/home/steve/Documents/IndianPoint/Contention 17/RepeatSalesAnalysisOfTolleyQuestions.s m log type: smcl1.
Linear regression                                                   Number of obs   =     1511 F( 2,     506) =     9.07 Prob > F       =   0.0001 Rsquared      =    0.0076 Root MSE       =   .19957 (Std. Err. adjusted for 507 clusters in id)
* Here is the model that is the basis of Dr. Sheppard's analysis:
Robust                                                 Dr. Sheppard's nomreturn               Coef. Std. Err.       t    P>ltl    [95% Conf. Interval]
2.Linear regression                                     Number of obs =
model.
1511 F( 2,   506) =
salepre74~76               .0292563  .0084169    3.48  0.001    .0457926        .01272 distkm         .0180762  .0055988    3.23  0.001    .029076    .0070764
9.07 Prob > F     =
_cons         .1585513  .0196089     8.09  0.000    .1200264     .1970762 3 .
0.0001 0.0076 Root MSE     = .19957                                   (Std. Err. adjusted for 507 clusters in id)                           Robust   nomreturn       Coef. Std. Err.     t    P>ltl    [95% Conf. Interval]
* Dr. Tolley raises a question about inclusion of data where one or more sale 4 .
salepre74~76 distkm
* involved a vacant lot. Consider the impact of excluding these observations 5 .
_cons  
* from the data used for the estimates:
  .1585513  .0196089     8.09  0.000    .1200264   .19707623.
6 . generate salewithlot=0 7 . replace salewithlot=1 if lot==1 (325 real changes made) 8 . regress nomreturn salepre74post76 distkm if (salewithlot==0 & nomreturn>1 & nomreturn<1), vce(clu Linear regression                                                   Number of obs   =     1222 F( 2,     414) =     11.33 Prob > F       =   0.0000 Rsquared      =    0.0085 Root MSE       =   .18151 (Std. Err. adjusted for 415 clusters in id)
* Dr. Tolley raises a question about inclusion of data where one or more sale 4.
Robust                                                 Model with nomreturn               Coef. Std. Err.       t    P>ltl    [95% Conf. Interval]     any vacant salepre74~76               .0423157  .0090465    4.68  0.000    .0600985    .0245328    lot data distkm         .0138921  .0058859    2.36  0.019    .025462    .0023222
* involved a vacant lot. Consider the impact of excluding these observations
_cons         .1519886  .0211621     7.18  0.000    .1103901     .1935871   excluded.
: 5.
9 .
* from the data used for the estimates:6. generate salewithlot=0
* This shows that excluding these sales strengthens the results used in Dr.
: 7. replace salewithlot=1 if lot==1 (325 real changes made)8.Linear regression                                     Number of obs =
: 10.
1222 F( 2,   414) =
* Sheppards analysis. The negative impact of the treatment group relative to the
11.33 Prob > F     =
0.0000 0.0085 Root MSE     = .18151                                   (Std. Err. adjusted for 415 clusters in id)                           Robust   nomreturn       Coef. Std. Err.     t    P>ltl    [95% Conf. Interval]
salepre74~76 distkm
_cons  
  .1519886  .0211621     7.18  0.000    .1103901    .19358719.
* This shows that excluding these sales strengthens the results used in Dr. 10.
* Sheppard's analysis. The negative impact of the treatment group relative to the  
: 11.
: 11.
* control is significantly larger. The results are estimated with greater  
* control is significantly larger. The results are estimated with greater
: 12.
: 12.
* precision.13.
* precision.
* Dr. Tolley objects to including sales that occurred during one of the times of rapid 14.
: 13.
* house price increase. Dropping these observations altogether is unwarranted.  
* Dr. Tolley objects to including sales that occurred during one of the times of rapid
: 14.
* house price increase. Dropping these observations altogether is unwarranted.
: 15.
: 15.
* If these time periods are different the preferred approach is to include an indicator Dr.S h eppar d's m odel.Modelw i thanyvacant lotdata excluded.
* If these time periods are different the preferred approach is to include an indicator
: 16.
: 16.
* or dummy variable in the model to account for any excess returns. 17.
* or dummy variable in the model to account for any excess returns.
: 17.
* We use indicator variables for the 1984Q2 to 1988Q1 time period and a separate
* We use indicator variables for the 1984Q2 to 1988Q1 time period and a separate
: 18.
: 18.
* indicator for the time from 1999 through 2009.19> , vce(cluster id)
* indicator for the time from 1999 through 2009.
Linear regression                                     Number of obs =
: 19. regress nomreturn salepre74post76 distkm dummy_80sbubble after98 if (salewithlot==0 & nomreturn>1
1222 F( 4,   414) =
  > , vce(cluster id)
11.19 Prob > F     =
Linear regression                                       Number of obs =   1222 F( 4,     414) =   11.19 Prob > F       = 0.0000 Model with Rsquared      =  0.0251 Root MSE       =  .18013 vacant lot (Std. Err. adjusted for 415 clusters in id) data excluded Robust                                             and indicator nomreturn       Coef. Std. Err.       t    P>ltl    [95% Conf. Interval] variables for salepre74~76   .0300483  .0117221    2.56  0.011    .0530906    .007006 1984-88 and distkm   .0150295  .0057691    2.61  0.010    .0263699    .003689 dummy_80sb~e     .0653683    .023289     2.81  0.005    .0195888     .1111477 1999-2009.
0.0000 0.0251 Root MSE     =  .18013                                   (Std. Err. adjusted for 415 clusters in id)                           Robust   nomreturn       Coef. Std. Err.     t    P>ltl    [95% Conf. Interval]
after98     .0538824  .0133926     4.02  0.000    .0275563     .0802085
salepre74~76 distkm dummy_80sb~e
_cons     .1123363  .0226813     4.95  0.000    .0677514     .1569212
  .0653683    .023289     2.81  0.005    .0195888   .1111477 after98  
: 20. *This shows that the result of Dr. Sheppards analysis remains essentially
  .0538824  .0133926     4.02  0.000    .0275563   .0802085
: 21.
_cons  
* unaffected by accounting for the two time periods with rapid house price appreciation.
  .1123363  .0226813     4.95  0.000    .0677514   .156921220. *This shows that the result of Dr. Sheppard's analysis remains essentially 21.
* unaffected by accounting for the two time periods with rapid house price appreciation.  
: 22.
: 22.
* The time periods DO show unusually high returns to owning housing, but the impact of  
* The time periods DO show unusually high returns to owning housing, but the impact of
: 23.
: 23.
* the IPEC treatment is not statistically different from Dr. Sheppard's original result.
* the IPEC treatment is not statistically different from Dr. Sheppards original result.
: 24.
: 24. *}}
* Modelw i thvacantlot dataexcluded andindicator variablesfor 1984-88and
 
1999-2009.}}

Latest revision as of 10:10, 6 February 2020

Official Exhibit - NYS000446-00-BD01 - Analysis by Stephen C. Sheppard Using Tolley Mls Linear Square Root
ML12340A815
Person / Time
Site: Indian Point  Entergy icon.png
Issue date: 10/22/2012
From: Sheppard S
- No Known Affiliation
To:
Atomic Safety and Licensing Board Panel
SECY RAS
References
RAS 23665, 50-247-LR, 50-286-LR, ASLBP 07-858-03-LR-BD01
Download: ML12340A815 (4)
v • d • e


Text

United States Nuclear Regulatory Commission Official Hearing Exhibit NYS000446 Entergy Nuclear Operations, Inc.

In the Matter of:

(Indian Point Nuclear Generating Units 2 and 3) Submitted: October 22, 2012 ASLBP #: 07-858-03-LR-BD01 Docket #: 05000247 l 05000286 Exhibit #: NYS000446-00-BD01 Identified: 10/22/2012 Admitted: 10/22/2012 Withdrawn:

Rejected: Stricken:

Other: Originally Identified as BRD000005 User: Stephen Sheppard Statistics/Data Analysis Project: IPEC name: <unnamed>

log: /home/steve/Documents/IndianPoint/Contention 17/TolleyOriginalLInearSquareRoot.smcl log type: smcl 1 . use "/home/steve/Documents/IndianPoint/Contention 17/MLS Data STATA Format.dta" 2 .

  • Tolley MLS model from report 3 . regress askprice ipdist ipdistsq med_income house_age attached rail_dist pilotpay_2011 Source SS df MS Number of obs = 296 F( 7, 288) = 26.44 Model 7028465.17 7 1004066.45 Prob > F = 0.0000 Residual 10937065.5 288 37975.922 Rsquared = 0.3912 Adj Rsquared = 0.3764 Total 17965530.7 295 60900.1041 Root MSE = 194.87 askprice Coef. Std. Err. t P>ltl [95% Conf. Interval] Dr. Tolley's ipdist 79.32316 69.82126 1.14 0.257 216.7478 58.1015 original ipdistsq 19.90054 10.78365 1.85 0.066 1.324214 41.12529 med_income 2.382077 .68255 3.49 0.001 1.038658 3.725496 model house_age 5.319204 .7153479 7.44 0.000 6.727177 3.911231 attached 263.2139 31.24132 8.43 0.000 324.7042 201.7236 rail_dist 38.50069 11.35376 3.39 0.001 60.84756 16.15383 pilotpa~2011 10.38756 15.72596 0.66 0.509 20.56482 41.33994

_cons 577.5368 121.6523 4.75 0.000 338.0965 816.9771 4 .

  • Tolley model with IPEC impact modeled as linear in distance 5 . regress askprice ipdist med_income house_age attached rail_dist pilotpay_2011 Source SS df MS Number of obs = 296 F( 6, 289) = 30.03 Model 6899132.97 6 1149855.5 Prob > F = 0.0000 Residual 11066397.7 289 38292.0337 Rsquared = 0.3840 Adj Rsquared = 0.3712 Total 17965530.7 295 60900.1041 Root MSE = 195.68 askprice Coef. Std. Err. t P>ltl [95% Conf. Interval] Model with ipdist 46.8946 14.10106 3.33 0.001 19.14079 74.6484 IPEC impact med_income 2.169724 .6755748 3.21 0.001 .8400531 3.499394 house_age 5.422697 .7161083 7.57 0.000 6.832146 4.013248 proportional attached 276.5584 30.51919 9.06 0.000 336.6265 216.4904 rail_dist 34.94915 11.23594 3.11 0.002 57.0638 12.8345 to linear pilotpa~2011 19.19545 15.04643 1.28 0.203 10.41904 48.80993

_cons 409.3269 80.90215 5.06 0.000 250.0948 568.559 distance.

6 .

  • Tolley model with IPEC impact modeled as proportional to square root of distance 7 . generate distsquareroot=ipdist^0.5 8 . regress askprice distsquareroot med_income house_age attached rail_dist pilotpay_2011 Source SS df MS Number of obs = 296 F( 6, 289) = 29.64 Model 6843474.45 6 1140579.08 Prob > F = 0.0000 Residual 11122056.3 289 38484.6238 Rsquared = 0.3809 Adj Rsquared = 0.3681 Total 17965530.7 295 60900.1041 Root MSE = 196.17

askprice Coef. Std. Err. t P>ltl [95% Conf. Interval]

distsquare~t 149.1657 48.24852 3.09 0.002 54.20262 244.1287 Model with med_income 2.131092 .6773751 3.15 0.002 .7978782 3.464306 IPEC impact house_age 5.439066 .7180836 7.57 0.000 6.852403 4.025729 attached 277.9586 30.69289 9.06 0.000 338.3686 217.5487 proportional rail_dist 32.94105 11.14021 2.96 0.003 54.86727 11.01482 pilotpa~2011 20.22589 15.26558 1.32 0.186 9.819931 50.27171 to square root

_cons 296.0152 105.2117 2.81 0.005 88.9368 503.0936 of distance.

9 .

  • Tolley model with IPEC impact modeled as proportional to square of distance
10. regress askprice ipdistsq med_income house_age attached rail_dist pilotpay_2011 Source SS df MS Number of obs = 296 F( 6, 289) = 30.60 Model 6979449.73 6 1163241.62 Prob > F = 0.0000 Residual 10986081 289 38014.1211 Rsquared = 0.3885 Adj Rsquared = 0.3758 Total 17965530.7 295 60900.1041 Root MSE = 194.97 askprice Coef. Std. Err. t P>ltl [95% Conf. Interval]

Model with ipdistsq 7.8997 2.169942 3.64 0.000 3.628806 12.17059 med_income 2.254154 .6735366 3.35 0.001 .9284944 3.579813 IPEC impact house_age 5.385319 .7133353 7.55 0.000 6.78931 3.981328 attached 272.1092 30.25947 8.99 0.000 331.6661 212.5523 proportional rail_dist 37.46601 11.32286 3.31 0.001 59.75174 15.18029 to the square pilotpa~2011 16.62003 14.74548 1.13 0.261 12.40211 45.64217

_cons 467.6234 73.78841 6.34 0.000 322.3925 612.8542 of distance.

User: Stephen Sheppard Statistics/Data Analysis Project: IPEC name: <unnamed>

log: /home/steve/Documents/IndianPoint/Contention 17/RepeatSalesAnalysisOfTolleyQuestions.sm log type: smcl 1 .

  • Here is the model that is the basis of Dr. Sheppards analysis:

2 . regress nomreturn salepre74post76 distkm if nomreturn>1 & nomreturn<1, vce(cluster id)

Linear regression Number of obs = 1511 F( 2, 506) = 9.07 Prob > F = 0.0001 Rsquared = 0.0076 Root MSE = .19957 (Std. Err. adjusted for 507 clusters in id)

Robust Dr. Sheppard's nomreturn Coef. Std. Err. t P>ltl [95% Conf. Interval]

model.

salepre74~76 .0292563 .0084169 3.48 0.001 .0457926 .01272 distkm .0180762 .0055988 3.23 0.001 .029076 .0070764

_cons .1585513 .0196089 8.09 0.000 .1200264 .1970762 3 .

  • Dr. Tolley raises a question about inclusion of data where one or more sale 4 .
  • involved a vacant lot. Consider the impact of excluding these observations 5 .
  • from the data used for the estimates:

6 . generate salewithlot=0 7 . replace salewithlot=1 if lot==1 (325 real changes made) 8 . regress nomreturn salepre74post76 distkm if (salewithlot==0 & nomreturn>1 & nomreturn<1), vce(clu Linear regression Number of obs = 1222 F( 2, 414) = 11.33 Prob > F = 0.0000 Rsquared = 0.0085 Root MSE = .18151 (Std. Err. adjusted for 415 clusters in id)

Robust Model with nomreturn Coef. Std. Err. t P>ltl [95% Conf. Interval] any vacant salepre74~76 .0423157 .0090465 4.68 0.000 .0600985 .0245328 lot data distkm .0138921 .0058859 2.36 0.019 .025462 .0023222

_cons .1519886 .0211621 7.18 0.000 .1103901 .1935871 excluded.

9 .

  • This shows that excluding these sales strengthens the results used in Dr.
10.
  • Sheppards analysis. The negative impact of the treatment group relative to the
11.
  • control is significantly larger. The results are estimated with greater
12.
  • precision.
13.
  • Dr. Tolley objects to including sales that occurred during one of the times of rapid
14.
  • house price increase. Dropping these observations altogether is unwarranted.
15.
  • If these time periods are different the preferred approach is to include an indicator
16.
  • or dummy variable in the model to account for any excess returns.
17.
  • We use indicator variables for the 1984Q2 to 1988Q1 time period and a separate
18.
  • indicator for the time from 1999 through 2009.
19. regress nomreturn salepre74post76 distkm dummy_80sbubble after98 if (salewithlot==0 & nomreturn>1

> , vce(cluster id)

Linear regression Number of obs = 1222 F( 4, 414) = 11.19 Prob > F = 0.0000 Model with Rsquared = 0.0251 Root MSE = .18013 vacant lot (Std. Err. adjusted for 415 clusters in id) data excluded Robust and indicator nomreturn Coef. Std. Err. t P>ltl [95% Conf. Interval] variables for salepre74~76 .0300483 .0117221 2.56 0.011 .0530906 .007006 1984-88 and distkm .0150295 .0057691 2.61 0.010 .0263699 .003689 dummy_80sb~e .0653683 .023289 2.81 0.005 .0195888 .1111477 1999-2009.

after98 .0538824 .0133926 4.02 0.000 .0275563 .0802085

_cons .1123363 .0226813 4.95 0.000 .0677514 .1569212

20. *This shows that the result of Dr. Sheppards analysis remains essentially
21.
  • unaffected by accounting for the two time periods with rapid house price appreciation.
22.
  • The time periods DO show unusually high returns to owning housing, but the impact of
23.
  • the IPEC treatment is not statistically different from Dr. Sheppards original result.
24. *
Retrieved from "https://kanterella.com/w/index.php?title=ML12340A815&oldid=2459127"