QQ登录

只需要一步,快速开始

 注册地址  找回密码
查看: 12434|回复: 0
打印 上一主题 下一主题

利用spss进行异方差检验的方法,望借鉴

[复制链接]
字体大小: 正常 放大

238

主题

27

听众

4554

积分

  • TA的每日心情
    奋斗
    2014-1-11 14:06
  • 签到天数: 45 天

    [LV.5]常住居民I

    自我介绍
    本人开朗大方,善于与人沟通。

    群组英语科技论文写作实训

    跳转到指定楼层
    1#
    发表于 2013-10-13 16:12 |只看该作者 |倒序浏览
    |招呼Ta 关注Ta |邮箱已经成功绑定
    1. 用图表检验Analyze -> regression -> Linear-> Plots; h8 l( T1 ]0 w( A* B
    Scatter plot of the standardised residuals on the standardised predicted values (ZRESID as  the Y variable, and ZPRED as the X variable- [5 {% u6 \. B$ g$ y- U, ]
    6 ~9 e3 L+ n9 C: z' _+ k" y
    如果图表显示有可能存在异方差,需要用统计检验来进一步检测异方差是否确实存在。
    . y. B/ o8 I( p4 m2 R" X5 [' A* G2. 用统计检验. o' W, ]2 k0 |7 [4 r: M
    Heteroscedasticity——Testing and Correcting in SPSS.pdf Gwilym Pryce March 2002.doc (172.5 KB, 下载次数: 4)
    # I. }: g4 N; m9 \2 N2 W1 i' P  n- e. ]1 W$ ^$ I4 M9 i2 e% G
    8 L( M4 g) w0 ~, t1 a. F% h. ]  u
    Levene’s Test/ k" }, f) K8 d6 a: s0 s3 ~% U
    Goldfeld-Quandt Test
      j( j, l/ B  Q2 G+ J( H* N  I( bBreusch-Pagan Test3 F3 w  D# a/ F, F$ A
    White‘s Test (比较常用来检验异方差)+ I) c! D6 A+ e, y3 X, F: Q2 t' N
    Assume you want to run a regression of wage on age, work experience,education, gender, and a dummy for sectorofemployment (whether employed in the public sector).
    wage = function(age, workexperience, education, gender, sector)
    or, as your textbook will have it,
    wage = b1 + b2*age + b3*work experience+ b4*education + b5*gender + b6*sector
    The White’s test is usually used as a test for heteroskedasticity.  In this test, a regression of the squares ofthe residuals is run on the variables suspected of causing theheteroskedasticity, their squares, and cross products.
    (residuals)2 = b0 + b1 educ + b2 work_ex+ b3 (educ)2  + b4 (work_ex)2 + b5(educ*work_ex)

    8 Y& B  W" b, t2 d

    & i' U' ]  r# ~5 G- t1 `+ }- W

    " F& q, _7 i2 V/ r( _/ W! ~, r9 a- n1 z& w+ c  g6 c& j9 Y/ _' t/ |& l
    White’s Test
    ·        Calculate n*R2                            à              R2  = 0.037, n=2016           à    Thus, n*R2 = .037*2016 = 74.6.
    . W$ P. k6 w' g  D+ |' ^
    ·        Compare this value with c2 (n), i.e.with  c2 (2016)  ( q! ^. r9 u: r2 {+ z' y# W7 F
    (c2  is the symbol for theChi-Square distribution)
      d5 B. X/ n+ o9 M
    c2 (2016) = 124obtained from c2 table.            (For 955 confidence)              As n*R2  < c2 ,heteroskedasticity can not be confirmed.
    3 y8 F9 _' u' ?- r

    . q7 m, V' h( M0 _) U! N  g7 T请参考:regression_explained_SPSS regression_explained_SPSS.doc (368 KB, 下载次数: 0)
    , @" @5 C  U# Q6 @8 s% y
    zan
    转播转播0 分享淘帖0 分享分享0 收藏收藏0 支持支持0 反对反对0 微信微信
    您需要登录后才可以回帖 登录 | 注册地址

    qq
    收缩
    • 电话咨询

    • 04714969085
    fastpost

    关于我们| 联系我们| 诚征英才| 对外合作| 产品服务| QQ

    手机版|Archiver| |繁體中文 手机客户端  

    蒙公网安备 15010502000194号

    Powered by Discuz! X2.5   © 2001-2013 数学建模网-数学中国 ( 蒙ICP备14002410号-3 蒙BBS备-0002号 )     论坛法律顾问:王兆丰

    GMT+8, 2026-9-1 04:53 , Processed in 0.354078 second(s), 54 queries .

    回顶部