podatki <- read.table("./Interakcije.csv", header=TRUE, sep=";", dec=",")
print(podatki)
## Y X Spol
## 1 1 2 0
## 2 2 3 0
## 3 3 1 0
## 4 4 4 0
## 5 5 5 0
## 6 6 4 0
## 7 7 6 0
## 8 8 7 0
## 9 9 8 0
## 10 10 9 0
## 11 1 8 1
## 12 2 5 1
## 13 3 4 1
## 14 4 5 1
## 15 5 3 1
Opis kategorialne spremenljivke:
library(car)
scatterplot(y = podatki$Y, x = podatki$X,
main = "Y ~ X",
smooth = FALSE)
fit <- lm(Y ~ X,
data = podatki)
summary(fit)
##
## Call:
## lm(formula = Y ~ X, data = podatki)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.9448 -1.1019 0.2838 1.7838 2.3123
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.0018 1.4722 0.680 0.5082
## X 0.7429 0.2718 2.733 0.0171 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.353 on 13 degrees of freedom
## Multiple R-squared: 0.3649, Adjusted R-squared: 0.316
## F-statistic: 7.469 on 1 and 13 DF, p-value: 0.01709
podatki$SpolF <- factor(podatki$Spol,
levels = c(0, 1),
labels = c("Z", "M"))
library(car)
scatterplot(Y ~ X | SpolF,
main = "Y ~ X",
smooth = FALSE,
data = podatki)
fit_z <- lm(Y ~ X,
data = podatki[podatki$SpolF == "Z", ])
summary(fit_z)
##
## Call:
## lm(formula = Y ~ X, data = podatki[podatki$SpolF == "Z", ])
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.42529 -0.58621 0.06897 0.27586 1.75862
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.1494 0.7815 0.191 0.853
## X 1.0920 0.1424 7.666 5.93e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.112 on 8 degrees of freedom
## Multiple R-squared: 0.8802, Adjusted R-squared: 0.8652
## F-statistic: 58.77 on 1 and 8 DF, p-value: 5.928e-05
fit_m <- lm(Y ~ X,
data = podatki[podatki$SpolF == "M", ])
summary(fit_m)
##
## Call:
## lm(formula = Y ~ X, data = podatki[podatki$SpolF == "M", ])
##
## Residuals:
## 11 12 13 14 15
## 0.1429 -1.0000 -0.7143 1.0000 0.5714
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.5714 1.3752 4.779 0.0174 *
## X -0.7143 0.2608 -2.739 0.0714 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9759 on 3 degrees of freedom
## Multiple R-squared: 0.7143, Adjusted R-squared: 0.619
## F-statistic: 7.5 on 1 and 3 DF, p-value: 0.07142
fit <- lm(Y ~ X + SpolF,
data = podatki)
summary(fit)
##
## Call:
## lm(formula = Y ~ X + SpolF, data = podatki)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.2630 -0.9105 0.6702 1.0808 3.5087
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.8037 1.3222 1.364 0.1975
## X 0.7543 0.2356 3.202 0.0076 **
## SpolFM -2.5754 1.1169 -2.306 0.0398 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.039 on 12 degrees of freedom
## Multiple R-squared: 0.5599, Adjusted R-squared: 0.4865
## F-statistic: 7.633 on 2 and 12 DF, p-value: 0.007268
fit <- lm(Y ~ X + SpolF + X:SpolF,
data = podatki)
summary(fit)
##
## Call:
## lm(formula = Y ~ X + SpolF + X:SpolF, data = podatki)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4253 -0.6617 0.1149 0.4351 1.7586
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.1494 0.7567 0.197 0.847054
## X 1.0920 0.1379 7.917 7.21e-06 ***
## SpolFM 6.4220 1.6949 3.789 0.003000 **
## X:SpolFM -1.8062 0.3190 -5.662 0.000146 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.076 on 11 degrees of freedom
## Multiple R-squared: 0.8876, Adjusted R-squared: 0.8569
## F-statistic: 28.95 on 3 and 11 DF, p-value: 1.617e-05