全部版块 我的主页
论坛 计量经济学与统计论坛 五区 计量经济学与统计软件 Stata专版
2369 2
2009-02-22
<p>如下数据:变量 X ,频数 f ,如何进行带频数的 ttest, 数据示意如下(注意:总频数=170>50):</p><p>x  f</p><p>1 10</p><p>2 15</p><p>3 20</p><p>4 25</p><p>5 30</p><p>6 25</p><p>7 20</p><p>8 15</p><p>90</p><p></p><p></p>
二维码

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

全部回复
2009-2-27 01:29:00

使用stata,ttest

estpost ttest varlist [if] [in], by(groupvar) [ unequal welch listwise
               casewise quietly esample ]

    posts two-group mean-comparison tests computed by ttest.

    Options are:

        by(), unequal, and welch as described in help ttest.

        listwise to handle missing values through listwise deletion, meaning
            that an observation is omitted from the estimation sample if any
            of the variables in varlist is missing for that observation. The
            default is to determine the used observations for each variable
            separately without regard to whether other variables are missing.
            casewise is a synonym for listwise.

        quietly to suppress the output.

        esample to mark the estimation sample in e(sample).

    The following results vectors are saved in e():

        e(b)         mean difference
        e(count)     number of observations
        e(se)        standard error of difference
        e(t)         t statistic
        e(df_t)      degrees of freedom
        e(p_l)       lower one-sided p-value
        e(p)         two-sided p-value
        e(p_u)       upper one-sided p-value
        e(N_1)       number of observations in group 1
        e(mu_1)      mean in group 1
        e(N_2)       number of observations in group 2
        e(mu_2)      mean in group 2

二维码

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

2009-3-1 10:05:00
谢谢,偶是一个十足的菜鸟,谢谢 楼上的!
二维码

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

相关推荐
栏目导航
热门文章
推荐文章

说点什么

分享

扫码加好友,拉您进群
各岗位、行业、专业交流群