Skip to menu

이런 경우는 어떻게 해석해야 하는지요?

orthojang 2015.04.17 09:26 Views : 908

어떤 반응값에 2가지의 설명변수만 넣었을때는 유의하지 않았던 인자가 ( PerfRatioMed,ADCepi)
같은 반응값에 4가지의 설명 변수를 넣었더니 유의하게 바뀌었습니다.

confounder effect로 생각해서 다중공선성을 살펴보았는데,  특별한 사항이 없었습니다.

어떻게 이해해야 할지 모르겠습니다.



> fit<-lm(DI0.3~PDR.in.central.ephysis+PerfRatioMed,data=LCP)
> summary(fit)

Call:
lm(formula = DI0.3 ~ PDR.in.central.ephysis + PerfRatioMed, data = LCP)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.5291 -0.4136 -0.1998  0.3801  0.8964 

Coefficients:
                         Estimate Std. Error t value Pr(>|t|)  
(Intercept)             0.2260148  0.1346602   1.678   0.1005  
PDR.in.central.ephysis  0.0072108  0.0031079   2.320   0.0251 *
PerfRatioMed           -0.0015097  0.0007537  -2.003   0.0515 .
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.453 on 43 degrees of freedom
Multiple R-squared:  0.1945, Adjusted R-squared:  0.1571 
F-statistic: 5.192 on 2 and 43 DF,  p-value: 0.009555

> fit<-lm(DI0.3~ADR.in.metaphysis+ADCepi,data=LCP)
> summary(fit)

Call:
lm(formula = DI0.3 ~ ADR.in.metaphysis + ADCepi, data = LCP)

Residuals:
    Min      1Q  Median      3Q     Max 
-1.1044 -0.2712 -0.1426  0.3596  0.7451 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)       0.002722   0.120065   0.023 0.982018    
ADR.in.metaphysis 0.007409   0.001860   3.983 0.000258 ***
ADCepi            0.000441   0.000871   0.506 0.615216    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4209 on 43 degrees of freedom
Multiple R-squared:  0.3048, Adjusted R-squared:  0.2725 
F-statistic: 9.429 on 2 and 43 DF,  p-value: 0.0004024

> fit<-lm(DI0.3~PDR.in.central.ephysis+PerfRatioMed+ADR.in.metaphysis+ADCepi,data=LCP)
> summary(fit)

Call:
lm(formula = DI0.3 ~ PDR.in.central.ephysis + PerfRatioMed + 
    ADR.in.metaphysis + ADCepi, data = LCP)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.83068 -0.20354 -0.08403  0.27185  0.64545 

Coefficients:
                         Estimate Std. Error t value Pr(>|t|)    
(Intercept)            -0.2357246  0.1359272  -1.734  0.09040 .  
PDR.in.central.ephysis  0.0076449  0.0024446   3.127  0.00324 ** 
PerfRatioMed           -0.0020127  0.0006146  -3.275  0.00215 ** 
ADR.in.metaphysis       0.0064848  0.0015599   4.157  0.00016 ***
ADCepi                  0.0017448  0.0007808   2.235  0.03094 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.35 on 41 degrees of freedom
Multiple R-squared:  0.5416, Adjusted R-squared:  0.4969 
F-statistic: 12.11 on 4 and 41 DF,  p-value: 1.373e-06

> vif(fit)
PDR.in.central.ephysis           PerfRatioMed      ADR.in.metaphysis                 ADCepi 
              1.046292               1.124601               1.109561               1.267423 
> sqrt(vif(fit))>2
PDR.in.central.ephysis           PerfRatioMed      ADR.in.metaphysis                 ADCepi 
                 FALSE                  FALSE                  FALSE                  FALSE 



I want to
List
Write Tag