数学建模社区-数学中国

标题: 利用spss进行异方差检验的方法，望借鉴 [打印本页]
作者: 馨冉回忆    时间: 2013-10-13 16:12
标题: 利用spss进行异方差检验的方法，望借鉴
1. 用图表检验Analyze -> regression -> Linear-> Plots
, ^* D; X2 C! GScatter plot of the standardised residuals on the standardised predicted values (ZRESID as  the Y variable, and ZPRED as the X variable, v) H1 y, n6 C+ i& h- N
8 j! t+ T5 c2 {. M7 v
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。
3 Q5 F5 q, y% M4 R1 X8 q3 h9 G2. 用统计检验. z  z4 U2 P* l6 ^% I& b1 e+ T7 n7 ~
Heteroscedasticity——Testing and Correcting in SPSS.pdf Gwilym Pryce March 2002.doc (172.5 KB, 下载次数: 4) . f% I  U  w" C" o& q" }

! o3 C- g4 U+ ]. X6 y" q* e, q: n7 C+ B/ A% e; {. ?( {% V
Levene’s Test3 O( a' W" t+ D, i# H: I4 B/ T
Goldfeld-Quandt Test6 X* t& C: O9 ?. z7 Q$ |0 Y
Breusch-Pagan Test
7 C1 ?. n/ j) D9 a9 C# [  [White‘s Test （比较常用来检验异方差）8 y+ n5 T3 p/ {$ Z
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)

" B/ w" E( a" `7 N8 S

+ X1 `2 |5 z3 x6 r# q9 `1 S$ V
  j7 O* y% x1 a' d

6 c/ r: D* ?+ M, g* X# [8 t
White’s Test
·        Calculate n*R2                            à              R2  = 0.037, n=2016           à    Thus, n*R2 = .037*2016 = 74.6.

" d6 b- t8 F) h4 B9 e
·        Compare this value with c2 (n), i.e.with  c2 (2016)  
. m  t5 [) \9 a7 S5 J; s(c2  is the symbol for theChi-Square distribution)
; p6 R  i+ @  }. q1 o8 a
c2 (2016) = 124obtained from c2 table.            (For 955 confidence)              As n*R2  < c2 ,heteroskedasticity can not be confirmed.

9 O6 \1 X, R' D: z
1 ~! G0 O3 V1 a& ~1 X) Q9 x请参考：regression_explained_SPSS regression_explained_SPSS.doc (368 KB, 下载次数: 0) . e- ]- p4 v. L+ q, i




欢迎光临 数学建模社区-数学中国 (http://www.madio.net/) Powered by Discuz! X2.5