Discussion 6

# Import the Dodgers dataset
dodgers <- read.csv("DodgersData.csv",
                    fileEncoding = "UTF-8-BOM",
                    stringsAsFactors = FALSE)

# Remove extra spaces from text variables
text_columns <- sapply(dodgers, is.character)
dodgers[text_columns] <- lapply(dodgers[text_columns], trimws)

# Question 1a
dodgers[25, c("temp", "attend", "opponent", "bobblehead")]

##    temp attend opponent bobblehead
## 25   61  36561   Astros         NO

# Question 1b
median(dodgers$attend)

## [1] 40284

# Question 1c
sum(dodgers$day_night == "Night")

## [1] 66

# Question 2: Scatter plot
plot(dodgers$temp, dodgers$attend,
     main = "Dodgers Attendance and Temperature",
     xlab = "Temperature (°F)",
     ylab = "Attendance",
     pch = 19,
     col = ifelse(dodgers$bobblehead == "YES",
                  "red", "black"))

legend("topleft",
       legend = c("No Bobblehead", "Bobblehead"),
       col = c("black", "red"),
       pch = 19)

# Correlation for the scatter plot
cor(dodgers$temp, dodgers$attend)

## [1] 0.09895073

# Organize months chronologically
dodgers$ordered_month <- factor(
  dodgers$month,
  levels = c("APR", "MAY", "JUN", "JUL",
             "AUG", "SEP", "OCT")
)

# Organize days chronologically
dodgers$ordered_day_of_week <- factor(
  dodgers$day_of_week,
  levels = c("Monday", "Tuesday", "Wednesday",
             "Thursday", "Friday", "Saturday", "Sunday")
)

# Question 3: Regression model
model <- lm(
  attend ~ ordered_month +
    ordered_day_of_week +
    bobblehead,
  data = dodgers
)

# Display regression results
summary(model)

## 
## Call:
## lm(formula = attend ~ ordered_month + ordered_day_of_week + bobblehead, 
##     data = dodgers)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -10786.5  -3628.1   -516.1   2230.2  14351.0 
## 
## Coefficients:
##                              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                  33909.16    2521.81  13.446  < 2e-16 ***
## ordered_monthMAY             -2385.62    2291.22  -1.041  0.30152    
## ordered_monthJUN              7163.23    2732.72   2.621  0.01083 *  
## ordered_monthJUL              2849.83    2578.60   1.105  0.27303    
## ordered_monthAUG              2377.92    2402.91   0.990  0.32593    
## ordered_monthSEP                29.03    2521.25   0.012  0.99085    
## ordered_monthOCT              -662.67    4046.45  -0.164  0.87041    
## ordered_day_of_weekTuesday    7911.49    2702.21   2.928  0.00466 ** 
## ordered_day_of_weekWednesday  2460.02    2514.03   0.979  0.33134    
## ordered_day_of_weekThursday    775.36    3486.15   0.222  0.82467    
## ordered_day_of_weekFriday     4883.82    2504.65   1.950  0.05537 .  
## ordered_day_of_weekSaturday   6372.06    2552.08   2.497  0.01500 *  
## ordered_day_of_weekSunday     6724.00    2506.72   2.682  0.00920 ** 
## bobbleheadYES                10714.90    2419.52   4.429 3.59e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 6120 on 67 degrees of freedom
## Multiple R-squared:  0.5444, Adjusted R-squared:  0.456 
## F-statistic: 6.158 on 13 and 67 DF,  p-value: 2.083e-07

# Display statistical significance results
anova(model)

## Analysis of Variance Table
## 
## Response: attend
##                     Df     Sum Sq   Mean Sq F value    Pr(>F)    
## ordered_month        6  948958117 158159686  4.2225  0.001158 ** 
## ordered_day_of_week  6 1314813030 219135505  5.8504 6.002e-05 ***
## bobblehead           1  734587177 734587177 19.6118 3.590e-05 ***
## Residuals           67 2509574563  37456337                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

#Question 1b: The median attendance was 40,284 fans. #Question 1c: The Dodgers played 66 night games. #Question 2: The scatter plot shows that temperature had little effect on attendance. The points do not follow a strong pattern. However, games with bobblehead promotions usually had higher attendance than games without promotions. #Question 3: The regression results show that bobblehead promotions increased attendance by about 10,715 fans per game after considering the month and day of the week. The model explained about 54.4% of attendance differences. Overall, promotions appeared to affect attendance more than temperature, but other factors may also have influenced the results.