Table 4. DBDC WTP Estimates for the NRP
|
Explanatory Variables1 |
RDD Sample |
NPF Sample | ||
|
Coefficient P-Value |
Coefficient P |
-Value | ||
|
All Revenue |
0.52*** |
0.00 |
0.12*** |
"0.00 |
|
Low Visits |
-0.40*** |
0.01 |
-0.11*** |
0.00 |
|
Young |
0.12 |
0.27 |
-0.09* |
0.06 |
|
Old |
-0.01 |
0.47 |
-0.04** |
0.04 |
|
Male |
-0.09 |
0.24 |
-0.08** |
0.02 |
|
BS degree |
0.17 |
0.15 |
0.05 |
0.14 |
|
Professional degree |
0.08 |
0.33 |
0.09** |
0.04 |
|
Low Income |
-0.10 |
0.27 |
-0.19*** |
0.00 |
|
White |
0.06 |
0.43 |
-0.02 |
0.39 |
|
Hispanic |
0.77** |
0.02 |
0.07 |
0.31 |
|
Asian |
0.62 |
0.12 |
-0.16 |
0.12 |
|
African American |
-0.66* |
0.09 |
0.32 |
0.14 |
|
NE |
-0.24 |
0.22 |
0.02 |
0.38 |
|
ENC |
-0.23 |
0.17 |
-0.03 |
0.34 |
|
WNC |
-0.40** |
0.04 |
-0.04 |
0.27 |
|
GP |
-0.18 |
0.26 |
-0.12* |
0.09 |
|
SE |
-0.07 |
0.38 |
-0.02 |
0.34 |
|
WSC |
-0.40* |
0.10 |
-0.06 |
0.31 |
|
SW |
0.02 |
0.47 |
0.04 |
0.30 |
|
______RM_____ |
________0.21__________ |
0.19 |
0.05_________ |
0.21 |
|
Heteroscedasticity (Hd) Results | ||||
|
Constant |
-0.22 |
0.22 |
-0.57*** |
0.00 |
|
Initial Bid |
0.003 |
0.19 |
-0.01*** |
0.00 |
|
Hd Likelihood Ratio |
0.76 |
0.38 |
14.34*** |
0.00 |
|
Summary Statistics | ||||
|
Sample Size 462 Likelihood Ratio Statistic 45.97*** Pseudo-R2 0.056 Mean WTP $42.28 ______Median WTP_______________$34.93_________ |
1461 65.07*** 0.024 $94.52 _________$95.63 | |||
Notes. (***), (**), and (*) refer to statistical significance at the 1, 5 and 10 percent levels. The
estimation was carried out using the Constrained Maximum Likelihood (CML 2.0) package in
Gauss version 3.5. The nonlinear optimization routine was Newton-Raphson with a convergence
criterion of 1×10-5 for the gradient of the coefficients. The estimates for “don’t know” and
“missing” dummy variables are not shown. 1Although not explicitly listed as an explanatory
variable, we control for BID in creating the probabilities that enter the likelihood function. See
Cameron and James [1987] for further details. Protest households are defined as those who refused
the NRP for free and are excluded from the analysis.
29