求问：什么是FM回归？

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

求问：什么是FM回归？

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

这是Stata命令中的解释
xtfmb is an implementation of the Fama and MacBeth (1973) two step procedure. The procedure
    is as follows: In the first step, for each single time period a cross-sectional regression is
    performed. Then, in the second step, the final coefficient estimates are obtained as the
    average of the first step coefficient estimates.

    If xtfmb is called without option lag(#), then it is possible to test for the significance of
    coefficient combinations. This works because in this case the second step of the Fama-MacBeth
    procedure is implemented by aid of Zellner's SUR estimation.

    When xtfmb is called with option lag(#), then heteroscedasticity and autocorrelation
    consistent Newey-West (1987) standard error estimates are provided.  However, in this case
    the current implementation of xtfmb does not allow for testing the significance of
    coefficient combinations.

    The "avg. R-squared" which is provided in the header of the xtfmb program is computed as the
    average value of the R-squares from the cross-sectional regressions in the first step of the
    Fama-MacBeth procedure. The coefficient estimates and R-squares of the first step regressions
    can be printed out with option verbose.