. pwcorr lny lnK lnH lnh,obs sig star(5)

| lny lnK lnH lnh
-------------+------------------------------------
lny | 1.0000
|
| 580
|
lnK | 0.9852* 1.0000
| 0.0000
| 580 580
|
lnH | 0.7700* 0.6904* 1.0000
| 0.0000 0.0000
| 580 580 580
|
lnh | 0.6611* 0.7085* 0.2130* 1.0000
| 0.0000 0.0000 0.0000
| 580 580 580 580

直接作，这是一个时间=20，单元=29的例题。选项obs给出观察值个数,sig给出显著水平,star(5)凡显著者打上5号大小的星。

Thank you very much.

面板数据也是这么做吗??

2# minixi

对于star选项的解释有误，括号内标明显著水平的阀值。

Options for pwcorr

        +------+
    ----+ Main +--------------------------------------------------------------------------------------------------------------------------------

    obs adds a line to each row of the matrix reporting the number of observations used to calculate the correlation coefficient.

    sig adds a line to each row of the matrix reporting the significance level of each correlation coefficient.

    print(#) specifies the significance level of correlation coefficients to be printed.  Correlation coefficients with larger significance
        levels are left blank in the matrix.  Typing pwcorr, print(.10) would list only correlation coefficients significant at the 10% level or
        better.

    star(#) specifies the significance level of correlation coefficients to be starred.  Typing pwcorr, star(.05) would star all correlation
        coefficients significant at the 5% level or better.