ãWhiteæ€å®ðãäžåäžåæ£ãååšããååž°ã¢ãã«ã«å¯Ÿããæ€å®ã«ã€ããŠïŒèšéçµæžåŠ No.14
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
äžåäžåæ£ã®æ€å®â ïŒWhite Test
åæ£ã®åäžæ§ãæ€å®ããæ¹æ³ãšããŠãWhiteæ€å®ããããŸãð
Whiteæ€å®ã¯ãäžåäžåæ£ã®åå ãç¹å®ãã
ããšãå°é£ãªå Žåã§ãå¿çšãå¹ããšããéåžžã«äŸ¿å©ãªææ³ã§ããã®ã§ããã£ãããã¹ã¿ãŒãããæ€å®æ¹æ³ã§ããããã«æããŸãð¥
以äžã§ã¯ãWhiteæ€å®ã®ããã»ã¹ã«ã€ããŠ
解説ããŠãããããšæããŸãïŒ
ãŸãã¯ã¹ãããïŒãšããŠã以äžã®ååž°åŒã
èããŠãããŸã
$$
\\
\\y_i =\beta_0+\beta_1x_i+u_i\cdot\cdot\cdot(1)\\i=1,\cdot\cdot\cdot,n \\ \\ \\applying OLS\\\to Resudals :e_i(i=1,\cdot\cdot\cdot,n)
$$
ãã®ååž°åŒ(1)ããæå°èªä¹æ³(OLS)ã§æšå®ãããã®çµæãšããŠåŸãããæ®å·®ãeiãšããŸã
次ã«ãã¹ãããïŒãšããŠããã®æ®å·®ã«å¯ŸããŠè£å©ååž°(2)ãèããŸã
$$
\\ \\
e_i^2 = \gamma_0+\gamma_1x_i+\gamma_2x_i^2+v_i\cdot\cdot\cdot(2)\\ \\applying OLS \to we get R^2
$$
ãã®(2)åŒã«å¯ŸããŠãã©ãããã«OLSãé©çšãããã®ã¢ãã«ã®æ±ºå®ä¿æ°R^2ãæ±ããŸã
ããã§è£å©ååž°ã®èª¬æå€æ°ãšããŠã¯(1)åŒã®èª¬æå€æ°ã説æåãã®èªä¹é
ã説æå€æ°ã®äº€å·®é
ãçšããããšããã€ã³ãã§ãð
ãããŠãã¹ãããïŒãšããŠä»¥äžã®åž°ç¡ä»®èª¬ãšå¯Ÿç«ä»®èª¬ãèããããšã«ãªããŸã
$$
\\
Null hypothesis\\ H_0 :\gamma_1=\gamma_2=0 \to homoscedasticity \\ \\Alternative hypothesis\\H_1:\gamma_1\not=0 or \gamma_2\not=0 \to heteroscedasticity
$$
åž°ç¡ä»®èª¬ã¯ãåäžåæ£ã§ãããšããããš
ãããŠã察ç«ä»®èª¬ã¯ãäžåäžåæ£ããããšããããšã«å¯ŸããŠãæ€å®ããããšã«ãªããŸã
æåŸã«ãã¹ãããïŒãšããŠä»¥äžã®èå¯ãããŸã
åž°ç¡ä»®èª¬ã®ããšã§ãæšæ¬æ°ã倧ãããšãã«ã¯ã次ã®é¢ä¿ãæç«ããŠããŸã
$$
\\ \\
nR^2\backsim\chi^2(2) \cdot\cdot\cdot(3)
$$
ããã§èªç±åºŠ(DF)ã¯(2)åŒã§ç€ºãããè£å©ååž°ã®å®æ°é
以å€ã®èª¬æå€æ°ã®æ°ã«å¯Ÿå¿ããŠããŸã
ãŸãR^2ã¯ãååž°åŒ(2)ã®æ±ºå®ä¿æ°ã§ããããšã«ãçæãå¿
èŠã§ãð
ãããŠããããŸã§ã®è°è«ãèžãŸããŠ
次ã®ããã«äžåäžåæ£ã®æ€å®ã§ããWhiteæ€å®ã®å€æãè¡ããŸã
ãŸãæææ°Žæº100α%ã«å¯ŸããŠ
èªç±åºŠ2ã®ã«ã€èªä¹ååžã®èšçå€ãªã©ãã
èããŠè¡ãããšã«ãªããŸã
$$
White Test \\at the Significance level :\alpha \%\\ \\ \\nR^2 \ge \chi^2_{\alpha}(2)\to Reject H_0 \\nR^2 < \chi^2_{\alpha}(2)\to Accept H_0
$$
ãã ããèªç±åºŠ2ã®ã«ã€èªä¹ååžã®äžåŽ100α%ç¹ãåºæºã«ä»®èª¬æ€å®ãè¡ã£ãŠããç¹ãããã§ç¢ºèªããŠãããŸã
Whiteæ€å®ã§ã¯ãè£å©ååž°ã®èª¬æå€æ°ã¯ããšã®ååž°åŒã®èª¬æå€æ°ã®1次ã®é
ã2次ã®é
ããã³äº€å·®é
ãçšãããšããã®ãéåžžã§ã
ãããã£ãŠãå
ã
ã®ååž°åŒã®èª¬æå€æ°ã®æ°ã
å¢ãããšãè£å©ååž°ã®èª¬æå€æ°ã®æ°ã
é£èºçã«å¢å ããŠããŸãããšã«æ³šæããå¿
èŠãããããã«æããŸã
ããã察象ãšãªãå
ã®ååž°åŒã以äžã§ãã£ããšããŸã
ããªãã¡ãå®æ°é
ãšèª¬æå€æ°ã3ã€ã§ããã±ãŒã¹ãèããŸã
$$
y_i = \beta_0 +\beta_1 x_1 +\beta_2x_2 +\beta_3 x_3+u_i\\ \\ \\
Auxiliary Regression \\e_i^2 =\gamma_0+\gamma_1x_1+\gamma_2x_2+\gamma_3x_3\\ \\ +\gamma_4x_1^2+\gamma_5x_2^2+\gamma_6 x_3^2\\ \\ +\gamma_7x_1x_2 +\gamma_8 x_2x_3+\gamma_9x_2x_3
$$
äžèšã®å®åŒåã®ããã«ãããå
ã®ååž°åŒã
å®æ°é
ïŒèª¬æå€æ°ã®æ°ã3ã€ã§ããã°
Whiteæ€å®ã®å¯Ÿè±¡ãšãªãè£å©ååž°ã«ããã説æå€æ°ã®æ°ã¯ãªããš10åã«ãªã£ãŠããŸãã®ã§ã
ããã¯éåžžã«è€éãªéååž°åæã«ãªããŸããã
ãã®ããã«å¯Ÿè±¡ãšãªãååž°åŒã®èª¬æå€æ°ãå¢ãããšãè£å©ååž°ãæ§æãã説æå€æ°ã®æ°ãçå¢ããŠããŸãããšã«å
å泚æããå¿
èŠãããç¹ãä»äžåºŠç¢ºèªããŠãããŸã
æ¬æ¥ã®è§£èª¬ã¯ããããŸã§ãšããŸã
次åã¯ãäžåäžåæ£ã®æ€å®â¡ïŒWhiteã®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¥
æ¬æ¥ã®è§£èª¬ã¯ã以äžãšããŸãð
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