Evaluation of the Australian Wage Subsidy Special Youth ...
Evaluation of the Australian Wage Subsidy Special Youth ... Evaluation of the Australian Wage Subsidy Special Youth ...
240 Manager/professional/paraprofessional -0.31 -0.31 (1.10) (1.09) Not employed -0.12 -0.11 (0.57) (0.55) Mother post-school qualification 0.22 0.21 when resp 14 Religion brought up in (1.26) (1.21) Catholic -0.01 0.00 (0.05) (0.03) Presbyterian 0.31 0.29 (1.29) (1.20) Methodist 0.29 0.28 (1.19) (1.18) Other Christian 0.06 0.04 (0.21) (0.15) Other religion 0.14 0.13 (0.56) (0.53) No religion 0.16 0.13 (0.84) (0.72) Constant 0.44 0.47 (0.65) (0.70) Observations 1283 1283 Log likelihood -303.41 -304.97 LR chi 2 (59) 161 131.99 118.83 Mcfadden’s Pseudo R 2 162 0.1572 0.1528 Akaike Information Criterion 0.56 0.57 Robust z-statistics in parentheses* significant at 5%; ** significant at 1% 161 This is the likelihood ratio test of the hypothesis that all coefficients except the intercept are equal to zero. It is defined as LR = 2 (log likelihood M full – 2 log likelihood M intercept ). The degrees of freedom of this chi squared distributed statistic are equal to the number of constrained parameters i.e. the number of coefficients being tested. 162 This measure of fit is also known as the likelihood ratio index. It compares the full model of parameters (Mfull) to a model with just the intercept (Mintercept). It is defined as R2 = 1 – (log likelihood Mfull / log likelihood Mintercept). The value of Mcfadden’s Pseudo R2 increases as new variables are added.
241 Table 7.4 Summary of distribution of propensity, exclude CEP referrals Distribution of estimated propensity for SYETP treatment group Percentiles Smallest 1% .0096799 .0080714 5% .0209195 .0096799 10% .0391096 .011608 Obs 104 25% .0818465 .0178796 Sum of Wgt. 104 50% .1352024 Mean .1653081 Largest Std. Dev. .1161794 75% .2308325 .4278012 90% .3124363 .456956 Variance .0134977 95% .4151957 .4614879 Skewness 1.059129 99% .4614879 .6016818 Kurtosis 4.17753 Distribution of estimated propensity for comparison group Percentiles Smallest 1% .0003765 .0000136 5% .0025803 .0000267 10% .005414 .0000539 Obs 1179 25% .0176855 .0000611 Sum of Wgt. 1179 50% .0492093 Mean .0743632 Largest Std. Dev. .0793953 75% .1044401 .4422829 90% .1755594 .4788667 Variance .0063036 95% .2357188 .4821222 Skewness 2.031504 99% .3915129 .5711446 Kurtosis 8.35458 The new matching results are shown in column 2 of Table 7.5. To better facilitate comparison, the former results with CEP referrals included are shown in the first column. The matching results are now compared, to show the effect of removing CEP referrals from the specification. The employment effect falls slightly in size, from eight percentage points to six, and statistical significance drops very low. The number of common support cases discarded from the SYETP treatment group does not change. However the number of SYETP matched falls slightly, and the number of comparison cases used to match to them also falls, with more comparison cases used with replacement than before. The mean difference in the propensity scores after matching is of the same magnitude as formerly, however the standard deviation is now slightly larger. The mean standardized bias has risen from 11.04 to 16.15. Overall, the efficiency of the match is judged to be poorer than before.
- Page 205 and 206: 189 proportion of time spent unempl
- Page 207 and 208: 191 post-school qualification, and
- Page 209 and 210: 193 Generally, those variables foun
- Page 211 and 212: 195 longj0 Longest job by 1984 < 1
- Page 213 and 214: 197 adopted in order to maintain co
- Page 215 and 216: 199 6: Study 4 Weighting to counter
- Page 217 and 218: 201 Table 6.1, part A Employment eq
- Page 219 and 220: 203 Methodist 0.133 0.261 (0.77) (1
- Page 221 and 222: 205 CEP referrals 1984 0.143* 0.128
- Page 223 and 224: 207 6.2 Results of weighting the PS
- Page 225 and 226: 209 The distribution of the propens
- Page 227 and 228: 211 Table 6.3 Weighted probit used
- Page 229 and 230: 213 (0.76) Tradesperson mtrad 0.20
- Page 231 and 232: 215 Table 6.5 Summary statistics fo
- Page 233 and 234: 217 Table 6.7 Matching results, sin
- Page 235 and 236: 219 6.3 Discussion The comparison o
- Page 237 and 238: 221 the selection into SYETP and th
- Page 239 and 240: 223 Heteroskedasticity is a violati
- Page 241 and 242: 225 Table 7.1, Part A Employment eq
- Page 243 and 244: 227 (1.26) (1.28) (1.16) Mothers oc
- Page 245 and 246: 229 Other Post-School qualification
- Page 247 and 248: 231 7.1.2 Exclusion restriction in
- Page 249 and 250: 233 Finally, the third panel of new
- Page 251 and 252: 235 Table 7.2 summary of changes to
- Page 253 and 254: 237 schooling that was statisticall
- Page 255: 239 (0.25) (0.21) 3 years + -0.50 -
- Page 259 and 260: 243 7.2.2 Propensity score matching
- Page 261 and 262: 245 original model, but with the pe
- Page 263 and 264: 247 maintained, then the Heckman bi
- Page 265 and 266: 249 Table 7.6 Weighted Probit used
- Page 267 and 268: 251 Table 7.7 Summary of distributi
- Page 269 and 270: 253 8: Summary and Conclusions The
- Page 271 and 272: 255 over which it ran, the review m
- Page 273 and 274: 257 the Heckman and PSM methods wer
- Page 275 and 276: 259 posited that that such sensitiv
- Page 277 and 278: 261 Description Derivation and deta
- Page 279 and 280: Appendix 2 Tables 263
- Page 281 and 282: 2 years 0.28 0.07 (1.70) (1.70) 3 y
- Page 283 and 284: 267 Table A2.0b Univariate Probit o
- Page 285 and 286: 269 Religion brought up in (1.52) (
- Page 287 and 288: 271 hq9_84 Year 9 of school or less
- Page 289 and 290: 273 Table A2.1 Continued Means and
- Page 291 and 292: 275 mtrad Tradesperson 0.04 0.04 0.
- Page 293 and 294: 277 Year 9 of school or less -0.19
- Page 295 and 296: 279 Table A2.3 Probit of SYETP part
- Page 297 and 298: 281 (0.22) (0.44) (0.67) (0.89) Tra
- Page 299 and 300: 283 Table A2.5a Univariate probit f
- Page 301 and 302: 285 Manager/professional/para-profe
- Page 303 and 304: 3 years + -0.04 (2.13)* CEP referra
- Page 305 and 306: 289 Table A2.6 Part A Employment eq
240<br />
Manager/pr<strong>of</strong>essional/parapr<strong>of</strong>essional<br />
-0.31 -0.31<br />
(1.10) (1.09)<br />
Not employed -0.12 -0.11<br />
(0.57) (0.55)<br />
Mo<strong>the</strong>r post-school qualification 0.22 0.21<br />
when resp 14<br />
Religion brought up in (1.26) (1.21)<br />
Catholic -0.01 0.00<br />
(0.05) (0.03)<br />
Presbyterian 0.31 0.29<br />
(1.29) (1.20)<br />
Methodist 0.29 0.28<br />
(1.19) (1.18)<br />
O<strong>the</strong>r Christian 0.06 0.04<br />
(0.21) (0.15)<br />
O<strong>the</strong>r religion 0.14 0.13<br />
(0.56) (0.53)<br />
No religion 0.16 0.13<br />
(0.84) (0.72)<br />
Constant 0.44 0.47<br />
(0.65) (0.70)<br />
Observations 1283 1283<br />
Log likelihood -303.41 -304.97<br />
LR chi 2 (59) 161 131.99 118.83<br />
Mcfadden’s Pseudo R 2 162<br />
0.1572 0.1528<br />
Akaike Information Criterion 0.56 0.57<br />
Robust z-statistics in paren<strong>the</strong>ses* significant at 5%; ** significant at 1%<br />
161 This is <strong>the</strong> likelihood ratio test <strong>of</strong> <strong>the</strong> hypo<strong>the</strong>sis that all coefficients except <strong>the</strong> intercept are equal to<br />
zero. It is defined as LR = 2 (log likelihood M full – 2 log likelihood M intercept ). The degrees <strong>of</strong> freedom <strong>of</strong> this<br />
chi squared distributed statistic are equal to <strong>the</strong> number <strong>of</strong> constrained parameters i.e. <strong>the</strong> number <strong>of</strong><br />
coefficients being tested.<br />
162<br />
This measure <strong>of</strong> fit is also known as <strong>the</strong> likelihood ratio index. It compares <strong>the</strong> full model <strong>of</strong> parameters<br />
(Mfull) to a model with just <strong>the</strong> intercept (Mintercept). It is defined as R2 = 1 – (log likelihood Mfull / log<br />
likelihood Mintercept). The value <strong>of</strong> Mcfadden’s Pseudo R2 increases as new variables are added.