|
|
|
Çѱ¹¼öÀÚ¿øÇÐȸ / v.42, no.4, 2009³â, pp.331-341
|
Information Matrix¿¡ µû¸¥ Generalized Logistic ºÐÆ÷ÀÇ ÃÖ¿ìµµ ÃßÁ¤·® Á¤È®µµ¿¡ °üÇÑ ¿¬±¸
( A Study on the Accuracy of the Maximum Likelihood Estimator of the Generalized Logistic Distribution According to Information Matrix ) |
| ½ÅÈ«ÁØ;Á¤¿µÈÆ;ÇãÁØÇà; ¿¬¼¼´ëÇб³ »çȸȯ°æ½Ã½ºÅÛ°øÇкÎ;¿¬¼¼´ëÇб³ »çȸȯ°æ½Ã½ºÅÛ°øÇкÎ;¿¬¼¼´ëÇб³ »çȸȯ°æ½Ã½ºÅÛ°øÇкÎ;
|
|
|
 |
|
| |
| ÃÊ ·Ï |
| º» ¿¬±¸¿¡¼´Â generalized logistic(GL) ºÐÆ÷ÀÇ ÃÖ¿ìµµ ÃßÁ¤·®(maximum likelihood estimate)¿¡ ´ëÇÑ ºÒÈ®½Ç¼º ÃßÁ¤À» À§ÇÏ¿© »ç¿ëµÇ´Â °üÃøÁ¤º¸Çà·Ä(observed information matrix)°ú Fisher Á¤º¸Çà·Ä(Fisher information matrix)ÀÇ Á¤È®µµ¸¦ ºñ±³ÇØ º¸°íÀÚ ÇÏ¿´´Ù. Ÿ ºÐÆ÷Çü¿¡ ´ëÇÑ ±âÁ¸ÀÇ ¿¬±¸°á°ú¿¡¼ Ç¥º»ÀÇ Å©±â°¡ Ŭ °æ¿ì ¸Å°³º¯¼ö ÃßÁ¤½Ã °üÃøÁ¤º¸Çà·ÄÀÌ µ¿½Ã¿¡ ÃßÁ¤µÇ¾î °è»ê½Ã°£µµ ´ÜÃàµÇ°í Fisher Á¤º¸Çà·ÄÀÇ Á¤È®µµ¿Íµµ Â÷À̵µ °ÅÀÇ ¾ø¾î °üÃøÁ¤º¸Çà·ÄÀÇ »ç¿ëÀÌ ÃßõµÈ ¹Ù ÀÖÀ¸³ª, ÃÖ±Ù »ç¿ëÀÌ Áõ°¡µÇ°í ÀÖ´Â GL ºÐÆ÷¿¡ ´ëÇÑ ¿¬±¸°á°ú´Â ¾ÆÁ÷ Àü¹«ÇÑ ½ÇÁ¤ÀÌ¸ç ±âÁ¸ ¿¬±¸¹®ÇåÀÇ °á°ú¸¦ Åä´ë·Î ±¸Ã¼ÀûÀÎ ¿¬±¸ ¾øÀÌ °üÃøÁ¤º¸Çà·ÄÀ» »ç¿ëÇϰí ÀÖ´Â »óȲÀÌ´Ù. µû¶ó¼ º» ¿¬±¸¿¡¼´Â À̸¦ À§ÇØ ¸ðÀǽÇÇèÀ» ¼öÇàÇÏ¿´À¸¸ç, ¸ðÀÇ °á°ú ÃÖ¿ìµµ¹ý¿¡ ÀÇÇÑ ¸Å°³º¯¼öÀÇ ºÐ»ê ¹× °øºÐ»êÀº ±âÁ¸ÀÇ ¿¬±¸ °á°ú¿Í ºñ½ÁÇÑ °á°ú¸¦ º¸À̳ª, quantile¿¡ ´ëÇÑ ºÒÈ®½Ç¼º ÃßÁ¤¿¡´Â °üÃøÁ¤º¸Çà·Äº¸´Ù Fisher Á¤º¸Çà·ÄÀÇ »ç¿ëÀÌ ´õ ÀûÀýÇÒ °ÍÀ¸·Î ÆÇ´ÜµÇ¾ú´Ù. |
|
| In this study, we compared the observed information matrix with the Fisher information matrix to estimate the uncertainty of maximum likelihood estimators of the generalized logistic (GL) distribution. The previous literatures recommended the use of the observed information matrix because this is convenient since this matrix is determined as the part of the parameter estimation procedure and there is little difference in accuracy between the observed information matrix and the Fisher information matrix for large sample size. The observed information matrix has been applied for the generalized logistic distribution based on the previous study without verification. For this purpose, a simulation experiment was performed to verify which matrix gave the better accuracy for the GL model. The simulation results showed that the variance-covariance of the ML parameters for the GL distribution came up with similar results to those of previous literature, but it is preferable to use of the Fisher information matrix to estimate the uncertainty of quantile of ML estimators. |
| |
| Ű¿öµå |
| generalized logistic ºÐÆ÷;ÃÖ¿ìµµ ÃßÁ¤·®;°üÃøÁ¤º¸Çà·Ä;Fisher Á¤º¸Çà·Ä;generalized logistic distribution;maximum likelihood estimator;observed information matrix;Fisher information matrix; |
| |
|
|
 |
|
Çѱ¹¼öÀÚ¿øÇÐȸ³í¹®Áý / v.42, no.4, 2009³â, pp.331-341
Çѱ¹¼öÀÚ¿øÇÐȸ
ISSN : 1226-6280
UCI : G100:I100-KOI(KISTI1.1003/JNL.JAKO200912840746080)
¾ð¾î : Çѱ¹¾î |
|
| ³í¹® Á¦°ø : KISTI Çѱ¹°úÇбâ¼úÁ¤º¸¿¬±¸¿ø |
|
|
|
|
|
|