library(fpp3)
## ── Attaching packages ────────────────────────────────────────────── fpp3 0.5 ──
## ✔ tibble 3.2.1 ✔ tsibble 1.1.4
## ✔ dplyr 1.1.4 ✔ tsibbledata 0.4.1
## ✔ tidyr 1.3.1 ✔ feasts 0.3.1
## ✔ lubridate 1.9.3 ✔ fable 0.3.3
## ✔ ggplot2 3.4.4 ✔ fabletools 0.4.0
## ── Conflicts ───────────────────────────────────────────────── fpp3_conflicts ──
## ✖ lubridate::date() masks base::date()
## ✖ dplyr::filter() masks stats::filter()
## ✖ tsibble::intersect() masks base::intersect()
## ✖ tsibble::interval() masks lubridate::interval()
## ✖ dplyr::lag() masks stats::lag()
## ✖ tsibble::setdiff() masks base::setdiff()
## ✖ tsibble::union() masks base::union()
data("us_employment")
view(us_employment)
us_employment|>ggplot(aes(x = Employed,y = Series_ID))+labs(y="Month(quarterly%change)",x = "Employed(quarterly%change)")+geom_point()+geom_smooth(method="|m",se=FALSE)+theme_bw()
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 71073 rows containing non-finite values (`stat_smooth()`).
## Warning: Computation failed in `stat_smooth()`
## Caused by error in `get()`:
## ! object '|m' of mode 'function' was not found
## Warning: Removed 71073 rows containing missing values (`geom_point()`).
{r#fitting the model} model<-lm(Month~Employed+Series_ID,data=us_employment) summary.lm(model)
{# SSR }
```{r#} Y_hat<-model\(fitted.values Y_bar<-mean(us_employment\)Month) SSR<-sum((Y_hat-Y_bar)^2) SSR
```r
#SST
SST<-sum((us_employment$Month_Y_bar)^2)
## Warning: Unknown or uninitialised column: `Month_Y_bar`.
SST
## [1] 0
#Assumptions of MLR
```{r#linearity}
```{r#}
MLR<-lm(Month~Employed+Series_ID,data = us_employment)
summary(MLR)
{r#} plot(us_employment$Month,us_employment$Employed) plot(MLR$residuals,MLR$fitted.values)
There being no pattern exhibited in residual against fitted.values hence linerity
{r#} MLR<-lm(Month~Employed,data = us_employment) summary.lm(MLR)
```{r#Homoscedacity}
```{r#}
library(performance)
check_heteroscedasticity(MLR)
{r#} library(performance) check_heteroscedasticity(MLR)
Hence reject null hypothesis
```{r#Normality of residuals}
```{r#}
check_normality(MLR)
Hence accept nullhypothesis
{r#} Shapiro.test(MLR$residuals)
```{r#multicollinearity}
```{r#}
check_collinearity(MLR)
```{r# Autocorrelation}
```{r#}
check_autocorrelation(MLR)
Hence reject null hypothesis
{r#} DurbinWatsonTest(MLR$residuals)