ãWhiteã®æ¹æ³ðžãäžåäžåæ£ã®ååšããååž°ã¢ãã«ãžã®å¯Ÿå¿çïŒèšéçµæžåŠ No.15 2023/08/23
IntroductionïŒèšéçµæžåŠãžã®ææŠð¥
çµæžåŠéšã«éãç§ã
ãããã倧åŠãåŠéšãæçµå¹Žã«ãªã
åŠåã«å
šåã泚ãæéãéãããŠããŸããð
ãç¥ã¯åãªãããšããèšèãä¿¡ããŠ
æ®ãã®å€§åŠçç掻ãæºå«ããããšæããŸã
åŠéšã¬ãã«ã®ãã¯ãçµæžåŠã¯
å人çã«ããç解ã§ããã€ããã§ã
ããããªãããæ¬åœã®çµæžã®ååãç解ããã«ã¯ãåŠéšã¬ãã«ã®ç¥èã§ã¯ã話ã«ãªããŸããð¥
ãŸããæ£ããèšéçµæžåŠã®ç¥èãããŒã¿åæã®ãªãã©ã·ãŒãäŒåŸããªããã°ãªããŸããðŠ
çŸå®ã®çµæžããŒã¿ããçè«ã¢ãã«ãšåœãŠã¯ã
æ£ããèšéææ³ã«ãã£ãŠå®èšŒåæã§ããåãéžæããã
ãã£ãšå°æ¥ã©ããã§æŽ»èºã§ãã人財ã«ãªããå¯èœæ§ãé«ããããšã«ç¹ãããšæããŸã
å®éã®çµæžååãæ¿æ²»ãšçµã³ã€ããªãã
å¿çšã§ããèœåããªããã°
ç¥èãæã€æ矩ãå°ãããªã£ãŠããŸããŸãðŠ
äœäºãã¢ãŠããããåæã®ã€ã³ãããã
倧äºã§ãããšãnoteã§æ¯æ¥çºä¿¡ããŠããŸãã
ããã¯ãã©ã®ãããªå
容ã§
ãã£ãŠãåœãŠã¯ãŸããŸãð
å
è¡ç 究ã®è«æãäžæŠã«èªãã§ã
èšæ¶ã«æ®ã£ãŠããªãã£ãã
倧åãªèŠ³ç¹ãå¿ããŠããŸã£ãŠãããããã
åŠç¿ã®é²æã¯æ»ã£ãŠããŸããšæããŸã
ã ããããããã®ãnoteãããã«æŽ»çšããŠ
èªåã®ç¥èã1ïŒ
ã§ããå®çãã
誰ã«ã§ããããããã解説ãã¢ãŠããããã§ããããã«åªããŠãããããšæããŸã
ç§ãããããã¢ãŠãããããã
èšéçµæžåŠã«ãããŠæéèŠãªããŒãã§ãã
æç³»ååæã®ã¢ãã«çè«è§£èª¬ã
ã©ããæåŸãŸã§ããæèªãã ããð
æ¬æçš¿äœæã«ãããåèæç®ã¯ä»¥äžã®éãã§ã
ãªããèšéçµæžåŠãåŠã¶ã®ãïŒïŒ
èšéçµæžåŠãæç³»å解ææ³ããçè«ãªãèšæž¬ããšããŠéãããšããããã¹ã¿ãŒãããããšã§ããç¥ãããŠããã®ã§ã
1930幎ã«åµç«ãããèšéçµæžåŠäŒã®èŠçŽç¬¬1æ¡ã§ã¯ãèšéçµæžåŠã¯ãçè«çæ°éçã¢ãããŒããšçµéšæ°éçã¢ãããŒãã®çµ±äžããšå®çŸ©ãããŠããŸããð
ãŸããRã»ããªãã·ã¥ã«ããããšã³ãã¡ããªã«ãåµåã®èŸã§ã¯ããçµ±èšåŠãçµæžåŠãæ°åŠã®äžè
ã®çµ±åããšå®çŸ©ãããŠããã®ã§ãð
ãã®ãããªå®çŸ©ã«ãããŠã¯ãåœæã®ããŒããŒãæ¯æ°äºæž¬ã«ä»£è¡šãããæç³»å解ææ³ãžã®æ¹å€ã匷ãæèãããŠãããšãããŠããŸã
ããªãã¡ãããã29幎ã®å€§ææ
ã®äºæž¬ã«å€±æããã®ã¯ïŒçµæžçè«ãç¡èŠãã æç³»åããŒã¿ã®åœ¢åŒçãªè§£æã®ã¿ã«çµå§ããããã§ãã£ããšããããšã§ã
ä»åŸã¯ãããããçè«ãªãèšæž¬ãã®ç«å Žãéãããçè«ã«åºã¥ãèšæž¬ããéèŠããŠãããªããã°ãªããªãããšããèŠè§£ã®éèŠæ§ãå¢ããŠããŸã
ãã®ãããªæŽå²ãçµãŠãèšéçµæžåŠã¯ã¹ã¿ãŒãããã£ãã®ã§ãã
ãããŠãäœãããã¯ãçµæžå€æ°ã¯
ãã®å€ããäºãã«åœ±é¿ãåãŒãåãçžäºäŸåã®é¢ä¿ã«ããããŸãéå»ã®å€åã®åœ±é¿ãæç¶ãããšããåŸåãæã¡ãŸã
ãããã®ååãåæããããå°æ¥ãäºæž¬ãããã§ããããã«ãªãããã«ã¯ãèšéçµæžåŠãã²ããŠã¯ãæç³»ååæãã«å¯Ÿããçè«ãæ£ããå®èšŒææ³ãžã®ç解ãå¿
èŠäžå¯æ¬ ãšãªããŸã
ãèšéçµæžåŠãã·ãªãŒãºã®æçš¿ã§ã¯ããããããã¯ãæç³»åå€æ°ã®å®èšŒåæã«å¿
èŠãªèšéçè«ãšææ³ãç¿åŸããããšãç®çãšããŸã
ããããç§ãã¢ãŠãããããã
æç³»åãã¯ãçµæžåæã«é¢ããå
容ã«ã€ããŠ
ã©ããæåŸãŸã§ãæèªãã ãããð
ååã®ã埩ç¿ãâš
ãvs.èªå·±çžé¢ð¥ãDurbin-Watsonæ€å®ãæ£ããå®æœããããã«å€§åãªããšðïŒèšéçµæžåŠ No.12
ãäžåäžåæ£ãšã®éãð¥ãå éæå°èªä¹æ³(WLS)ã«ããé©åãªååž°åæææ³ã«ã€ããŠïŒèšéçµæžåŠ No.13
ãWhiteæ€å®ðãäžåäžåæ£ã®ããååž°ã¢ãã«ã«å¯Ÿããæ€å®ã«ã€ããŠïŒèšéçµæžåŠ No.14
äžåäžåæ£ãžã®å¯Ÿå¿çïŒWhiteã®æ¹æ³ð
äžåäžåæ£ã®åœ¢æ
ãæ¢ç¥ã§ãªãå Žåã«
éåžžéãã®æå°èªä¹æ³ãé©çšããŠæ€å®ãããŠããŸããšã倧åé¡ãçºçããŸã
ããªãã¡ãæšæºèª€å·®ãé©åã§ã¯ãªã
誀ã£ãçµ±èšçæšè«ãå®æœããŠããŸãããšã«ãªããšããããšã§ãð¥²
Whiteã¯ããã§ããã®ãããªå Žåã«å¯Ÿããã¢ãããŒããææ¡ããã®ã§ãð
以äžã§ã¯ã次ã®ååž°åŒ(1)ãèããŸã
$$
y_i =\beta_0+\beta_1x_i +u_i \cdot\cdot\cdot (1)
\\i=1,2,\cdot\cdot\cdot,n
$$
ããã§åæ£ãåäžã®å Žåãæ³å®ãããš
β1ã®OLSæšå®éã®åæ£ã¯ä»¥äž(2)ã®ããã«è¡šèšã§ããŸã
$$
\\
if,V(u_i)=\sigma^2:Homoscedasticity\\ \\ \\The Varianve of OLS Estimator : \hat{\beta_1}\\ \\V(\hat{\beta_1}) =\frac{\large{\sigma^2}}{\textstyle\sum_{i=1}^n(x_i-\bar{x_i})^2} \cdot\cdot\cdot (2)
$$
ããã«å¯ŸããŠãäžåäžåæ£ãååšããå Žåã«
ãããŠãβ1ã®OLSæšå®éã®åæ£ã¯(3)ã®ããã«ãªããŸã
$$
\\
if,V(u_i) =\sigma_i^2:Heteroscedasticity \\ \\ \\The Varianve of OLS Estimator : \hat{\beta_1}\\ \\V(\hat{\beta_1}) =\frac{\textstyle\sum_{i=1}^n(x_i-\bar{x_i})^2 \sigma_i^2}{\textstyle\sum_{i=1}^n(x_i-\bar{x_i})^2} \cdot\cdot\cdot (3)
$$
(3)åŒã«ã¯ã(2)åŒãšã¯ç°ãªããæªç¥ã®
ãã©ã¡ãŒã¿(Ïi^2,i=1,2,âŠ,n)ãååšããŠããŸã
ããããäžåäžåæ£ãååšãããšãã«
ãã€ãã®ããã«éåžžæå°èªä¹æ³ãå®æœããŠããŸããšãåæ£ãæšæºèª€å·®ãæ£ããèšæž¬ãããªããšããæ以ã«ãªããŸãð
ããã§Whiteã¯ãæªç¥ã®ãã©ã¡ãŒã¿(Ïi^2)ã®
代æ¿ãšããŠãOLSæ®å·®(ei)ãçšããŠ
(3)åŒã(4)åŒã®ããã«ããŠããæšå®ããããšãææ¡ããã®ã§ãð
$$
\\
White's Approach\\ \\Use OLS Residual :e_i =y_i -\hat{\beta_0}-\hat{\beta_1}x_i\\ \\
\\V(\hat{\beta_1}) =\frac{\textstyle\sum_{i=1}^n(x_i-\bar{x_i})^2 e_i^2}{\textstyle\sum_{i=1}^n(x_i-\bar{x_i})^2} \cdot\cdot\cdot (4)
$$
ããã§éåžžã«éèŠãªãã€ã³ãã¯ä»¥äžã®éãã§ã
äžèšã§è¿°ã¹ããäžåäžåæ£ã«å¯ŸããWhiteã®
ä¿®æ£æ¹æ³ã¯ãããšãäžåäžåæ£ã®åããã¿ãŒã³ãããããªããšãããã®æšå®éã¯
äžèŽæ§ãæºãããšããããšã§ãð
(4)åŒã«åºã¥ããŠãèšç®ãããæšæºèª€å·®ã¯
(5)åŒã®ããã«HCSEãšåŒã°ããŸã
ãã㯠Heteroscedasticity Consistent Standard Errorã®ç¥ã«ãªããŸãð
$$
\\
HCSE(\hat{\beta_1}) =\sqrt{\frac{\textstyle\sum_{i=1}^n(x_i-\bar{x_i})^2 e_i^2}{\textstyle\sum_{i=1}^n(x_i-\bar{x_i})^2}} \cdot\cdot\cdot (5)
$$
ç·ããŠãäžåäžåæ£ã®çãããããšãã«ã¯
(5)åŒã«åºã¥ããŠïœæ€å®ãè¡ãã°ããã®ã§ã
HCSEãçšããŠãååž°ä¿æ°ã®æšå®å€
ããèªäœã¯åœ±é¿ãåããŸãã
ããããæšæºèª€å·®ã®å€ãããã³ãã®çµæãšããŠïœæ€å®ãªã©ã®çµ±èšçæšè«ã¯åœ±é¿ãåããããšã«ãªãã®ã§ãð
æ¬æ¥ã®è§£èª¬ã¯ããããŸã§ãšããŸãð
次åã¯ãNewey-Westã®æ¹æ³ããšããããŒãã培åºçã«èå¯ããŠãããããšæããŸã
ãã¯ãçµæžåŠãããç解ããææ³ãšããŠã®
èšéçµæžåŠãªãã³ã«æç³»ååæã®ç¥èã
äžç·ã«ç²åŸããŠãããŸãããð¥
ä»é²ïŒç§ã®åè«ç 究ããŒãã«ã€ããŠð
ç§ã¯ãçºæ¿ä»å
¥ã®å®èšŒåæããããŒãã«
åæ¥è«æãå·çããããšèããŠããŸãð
æ¥æ¬çµæžãèãããšãã«ãçºæ¿ã¬ãŒãã«ãã£ãŠ
貿æååŒãçµåžžåæ¯ãå€åããã
æ ªã蚌åžãåµæš©ãšãã£ãéèè³ç£ã®åççã
å€åããããšæ¥æ¬çµæžãšçºæ¿ã¬ãŒããšã¯
åã£ãŠãåããªãçžãããã®ã§ãð
ïŒåðŽã ãã«ïœ¥ïœ¥ïœ¥ïŒ
çµæžã·ã§ãã¯ã«ãã£ãŠ
çºæ¿ã¬ãŒããå€åãããš
ãã®åœ±é¿ã¯ç§ãã¡ã®ç掻ã«å€§ãã圱é¿ããŸã
ã ãããããçºæ¿ã¬ãŒãã®å®å®æ§ã
æ
ä¿ãããããªçºæ¿ä»å
¥ã¯ãã¯ãçµæžæ¿çã«
ãããŠãéåžžã«éèŠãªæ矩ãæã£ãŠãããš
æšæž¬ããŠããŸã
決ããŠåŠéšçã楜ããŠå·çã§ããç°¡åãªããŒããéžæããŠããããã§ã¯ç¡ããšä¿¡ããŠããŸã
ãã ããã®åæ¥è«æãããåãããšã
ç§ã®åŠçç掻ã®é倧æãšãªãããšã¯äºå®ãªã®ã§
æåŸãŸã§ã³ãã³ããšåãçµãã§åããŸãð¥
ä»åŸãçµæžåŠçè«éãªãã³ã«
瀟äŒèª²é¡ã«å¯ŸããçµæžåŠçèŠç¹ã«ãã説æãªã©
ææ矩ãªå
容ãçºä¿¡ã§ããããã«åªããŠãŸãããŸãã®ã§ãä»åŸãšãå®ãããé¡ãããŸãð¥º
ãããããã¬ãžã³ã®ã玹ä»ð
ãã¡ãã«ïŒïŒåãšããŠã®ç§ã®å°±è·æŽ»åäœéšèšããŸãšãããã¬ãžã³ãã玹ä»ãããŠããã ããŸãð
æ§ã
ãªèŠ³ç¹ããå°±è·æŽ»åã«ã€ããŠèå¯ããŠããŸãã®ã§ããäžèªããã ããŸããšå¹žãã§ã
æ¹ããŠãå°±è·æŽ»åã¯
æ¬åœã«ããçžãã ãšæããŸããð
ã ããããããçžã倧åã«
ãããŠãéžãã éãæ£è§£ã«ã§ãããã
ãããããåªåããŠãããããªãšæããŸãð¥
åæ¥è«æå·çãžã®è»è·¡ð
ãšãã»ã³ã·ã£ã«ã»çµæžåŠçè«éð
ãåœéçµæžåŠðãåºç€ççè«ïŒã¢ãã«ã®èª¬æ
ãã¡ãã®ãã¬ãžã³ã«ãŠ
åæ¥è«æå·çãžã®è»è·¡
ãšãã»ã³ã·ã£ã«çµæžåŠçè«éããªãã³ã«
åœéçµæžåŠðã®åºç€çè«ããŸãšããŠããŸã
ä»åŸãããã«ã³ã³ãã³ããæ¡å
ã§ããããã«åªããŠåããŸãã®ã§ãä»åŸãšãäœåãããããé¡ãç³ãäžããŸãð
æåŸãŸã§ãæèªããã ãèª ã«æé£ãããããŸããïŒ
ãããŸã§ãç§ã®èŠè§£ãæã£ãããšã
ãŸãšããããŠããã ããŠãŸãã
ãã®ç¹ã«é¢ããŸããŠããäºæ¿ãã ããð
ãã®æçš¿ãã¿ãŠãã ãã£ãæ¹ã
ã»ãã®å°ããªäºã§ãåŠã³ããã£ãïŒ
èãæ¹ã®åŒãåºããå¢ããïŒ
èªæžããåŠã¹ãããšãå€ãïŒ
ãªã©ãªã©ããã©ã¹ã®åç©«ããã£ãã®ã§ããã°
倧å€å¬ããæããŸãããæçš¿äœæã®å¥å©ã«å°œããŸãïŒïŒ
ãæ°è»œã«ã³ã¡ã³ããããããã¹ããð
ãããŠããå·®ãæ¯ããªããã°
ãã©ããŒïŒã·ã§ã¢ããé¡ããããã§ãð
ä»åŸãšãäœåãããããé¡ãããããŸãïŒ
ãã®èšäºãæ°ã«å ¥ã£ãããµããŒããããŠã¿ãŸãããïŒ