drop1(p.lm4,test=Chi)

⇐ ПредыдущаяСтр 4 из 4

AIC()

AIC(p. lm3, p. lm4)

df AIC

p. lm3 11 578. 3099

p. lm4 19 567. 4625

drop1()

drop1(p. lm4, test=" Chi" )

Single term deletions

Model:

abundance ~ NAP * fBeach

Df Sum of Sq RSS AIC Pr(> Chi)

< none> 339293 437. 76

NAP: fBeach 8 276845 616138 448. 61 0. 0007512 ***

---

Signif. codes: 0 ‘***’ 0. 001 ‘**’ 0. 01 ‘*’ 0. 05 ‘. ’ 0. 1 ‘ ’ 1

drop1(p. lm4, test=" F" )

Single term deletions

Model:

abundance ~ NAP * fBeach

Df Sum of Sq RSS AIC F value Pr(> F)

< none> 339293 437. 76

NAP: fBeach 8 276845 616138 448. 61 2. 7538 0. 0231 *

---

Signif. codes: 0 ‘***’ 0. 001 ‘**’ 0. 01 ‘*’ 0. 05 ‘. ’ 0. 1 ‘ ’ 1

drop1(p. lm3, test=" F" )

Single term deletions

Model:

abundance ~ NAP + fBeach

Df Sum of Sq RSS AIC F value Pr(> F)

< none> 616138 448. 61

NAP 1 6559 622697 447. 08 0. 3726 0. 54555

fBeach 8 390683 1006821 454. 70 2. 7741 0. 01734 *

---

Signif. codes: 0 ‘***’ 0. 001 ‘**’ 0. 01 ‘*’ 0. 05 ‘. ’ 0. 1 ‘ ’ 1

anova(m)

anova(m1, m2)

- вывод значимости факторов в целом

- использование факторов для дисперсионного анализа

- сравнение моделей

anova(p. lm3)

Analysis of Variance Table

Response: abundance

Df Sum Sq Mean Sq F value Pr(> F)

NAP 1 1213 1213 0. 0689 0. 79444

fBeach 8 390683 48835 2. 7741 0. 01734 *

Residuals 35 616138 17604

---

Signif. codes: 0 ‘***’ 0. 001 ‘**’ 0. 01 ‘*’ 0. 05 ‘. ’ 0. 1 ‘ ’ 1

anova(p. lm3, p. lm4)

Analysis of Variance Table

Model 1: abundance ~ NAP + fBeach

Model 2: abundance ~ NAP * fBeach

Res. Df RSS Df Sum of Sq F Pr(> F)

1 35 616138

2 27 339293 8 276845 2. 7538 0. 0231 *

---

Signif. codes: 0 ‘***’ 0. 001 ‘**’ 0. 01 ‘*’ 0. 05 ‘. ’ 0. 1 ‘ ’ 1

оценка качества модели:

plot()

boxplot(residuals(p. lm4)~p1$fBeach)

⇐ Предыдущая 1 2 34