Say something continuing link to previous part https://rpubs.com/nurfnick/715604
Now I can knit
model = lm(W ~ PTS, data = data)
summary(model)
##
## Call:
## lm(formula = W ~ PTS, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8066 -0.2762 0.2136 0.2136 0.2339
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.25414 0.17004 -1.495 0.146
## PTS 0.51013 0.04319 11.811 2.16e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3183 on 28 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.8328, Adjusted R-squared: 0.8269
## F-statistic: 139.5 on 1 and 28 DF, p-value: 2.163e-12
plot(model)
predict(model)
## 1 2 3 4 5 6 7 8
## 2.8066298 2.8066298 2.8066298 2.8066298 2.2965009 2.2965009 2.2965009 1.7863720
## 9 10 11 12 13 14 15 16
## 1.7863720 1.7863720 1.7863720 1.7863720 1.7863720 1.7863720 1.7863720 1.7863720
## 17 18 19 20 21 22 23 24
## 1.7863720 1.7863720 1.2762431 1.2762431 1.2762431 1.2762431 1.2762431 0.7661142
## 25 26 27 28 29 30
## 0.7661142 0.7661142 0.7661142 0.7661142 0.7661142 0.2559853
ylist = c(6,10,11,15)
point <- data.frame(PTS = ylist)
predict(model, point, interval = 'prediction')
## fit lwr upr
## 1 2.806630 2.113392 3.499867
## 2 4.847145 3.981220 5.713071
## 3 5.357274 4.431923 6.282625
## 4 7.397790 6.198372 8.597208
residuals(model)
## 1 2 3 4 5 6 7
## 0.1933702 0.1933702 0.1933702 -0.8066298 -0.2965009 -0.2965009 -0.2965009
## 8 9 10 11 12 13 14
## 0.2136280 0.2136280 0.2136280 0.2136280 0.2136280 0.2136280 0.2136280
## 15 16 17 18 19 20 21
## 0.2136280 0.2136280 0.2136280 0.2136280 -0.2762431 -0.2762431 -0.2762431
## 22 23 24 25 26 27 28
## -0.2762431 -0.2762431 0.2338858 0.2338858 0.2338858 0.2338858 -0.7661142
## 29 30
## 0.2338858 -0.2559853
3-2.806630
## [1] 0.19337
hist(residuals(model))
plot(data$PTS,data$W)
abline(model)
cor(data$PTS,data$W, use = "complete.obs")
## [1] 0.9126024
cor.test(data$PTS,data$W, use = "complete.obs")
##
## Pearson's product-moment correlation
##
## data: data$PTS and data$W
## t = 11.811, df = 28, p-value = 2.163e-12
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.8228826 0.9579232
## sample estimates:
## cor
## 0.9126024
data[which((data$PPO > data$PPOA)),"GP"]
## [1] 3 3 3 3 3 2 3 3 4 3 4 4 3 3
data[which((data$PPO > data$PPOA)),"MPPThanKills"] = TRUE
data[which(!(data$PPO > data$PPOA)),"MPPThanKills"] = FALSE
data$MPPThanKills
## [1] FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE TRUE FALSE TRUE
## [13] TRUE TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE TRUE FALSE TRUE
## [25] TRUE TRUE FALSE FALSE TRUE FALSE NA
fit <- lm(W ~ PTS + MPPThanKills, data)
fit
##
## Call:
## lm(formula = W ~ PTS + MPPThanKills, data = data)
##
## Coefficients:
## (Intercept) PTS MPPThanKillsTRUE
## -0.4629 0.5303 0.2877
summary(fit)
##
## Call:
## lm(formula = W ~ PTS + MPPThanKills, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.71867 -0.12788 0.05413 0.11466 0.40239
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.4629 0.1725 -2.684 0.0123 *
## PTS 0.5303 0.0398 13.322 2.19e-13 ***
## MPPThanKillsTRUE 0.2877 0.1073 2.681 0.0124 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.288 on 27 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.868, Adjusted R-squared: 0.8582
## F-statistic: 88.76 on 2 and 27 DF, p-value: 1.345e-12
y <- data.frame(PTS = 10, MPPThanKills = TRUE)
predict(fit, y)
## 1
## 5.127451
plot(data$PTS,data$W)
abline(fit, col = "Red")
## Warning in abline(fit, col = "Red"): only using the first two of 3 regression
## coefficients
abline(model, col = "Blue")
library(ggplot2)
ggplot(data = data, aes(x = PTS, y = W, color = MPPThanKills)) +
geom_jitter() +
geom_smooth(method="lm")
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 1 rows containing non-finite values (stat_smooth).
## Warning: Removed 1 rows containing missing values (geom_point).