R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

# Load libraries
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ggplot2)

# Load data 
movies <- read.csv("C:/Users/Prasad/Downloads/imdb.csv")

# Fit linear model
fit <- lm(revenue ~ budget_x + score, data = movies)

# Model diagnostics
par(mfrow = c(2, 2)) 
plot(fit)

summary(fit)
## 
## Call:
## lm(formula = revenue ~ budget_x + score, data = movies)
## 
## Residuals:
##        Min         1Q     Median         3Q        Max 
## -849646874 -148107537  -35799539  123828672 1942070819 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -5.133e+08  8.114e+07  -6.326 6.24e-10 ***
## budget_x     3.706e+00  1.907e-01  19.428  < 2e-16 ***
## score        8.114e+06  1.111e+06   7.306 1.32e-12 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 283300000 on 436 degrees of freedom
## Multiple R-squared:  0.4814, Adjusted R-squared:  0.479 
## F-statistic: 202.3 on 2 and 436 DF,  p-value: < 2.2e-16
# Check assumptions
ggplot(fit, aes(x = .fitted, y = .resid)) + 
  geom_point() +
  geom_smooth()
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

 # Create a ggplot object and specify the data
p <- ggplot(data = movies, aes(x = budget_x))

# Add a density plot
p + geom_density()

# Interpretation
summary(fit)$coefficients
##                  Estimate   Std. Error   t value     Pr(>|t|)
## (Intercept) -5.132965e+08 8.114066e+07 -6.326008 6.244670e-10
## budget_x     3.705702e+00 1.907364e-01 19.428398 5.034949e-61
## score        8.114215e+06 1.110626e+06  7.305980 1.321389e-12