This is my WPA

Question 0

library("yarrr")



# C
names(capture)
##  [1] "size"          "cannons"       "style"         "warnshot"     
##  [5] "date"          "heardof"       "decorations"   "daysfromshore"
##  [9] "speed"         "treasure"
# D
head(capture)
##   size cannons   style warnshot date heardof decorations daysfromshore
## 1   48      54 classic        0  172       1           8            28
## 2   51      56  modern        0   15       0           3             6
## 3   50      44  modern        0   63       0           3            23
## 4   54      54  modern        0  362       1           2            23
## 5   50      56  modern        0  183       1           2            12
## 6   51      48  modern        0  279       0           1             3
##   speed treasure
## 1    16     2175
## 2    29     2465
## 3    18     1925
## 4    19     2200
## 5    21     2290
## 6    24     2195

Question 1

# A
object <- lm(treasure ~ size, data=capture)

with(capture, plot(size, treasure))
abline(object, col="blue")

# B
object2 <- lm(treasure ~ cannons, data=capture)

with(capture, plot(cannons, treasure))
abline(object2, col="blue")

# C
object3 <- lm(treasure ~ date, data=capture)

with(capture, plot(date, treasure))
abline(object3, col="blue")

# D
object4 <- lm(treasure ~ decorations, data=capture)

with(capture, plot(decorations, treasure))
abline(object4, col="blue")

# E

object5 <- lm(treasure ~ daysfromshore, data=capture)

with(capture, plot(daysfromshore, treasure))
abline(object5, col="blue")

# F
object6 <- lm(treasure ~ speed, data=capture)

with(capture, plot(speed, treasure))
abline(object6, col="blue")

Question 2

#A
A2 <- lm(treasure ~ style, data=capture)
pirateplot(dv.name = "treasure",
           iv.name = "style",
           data = capture,
           add.hdi = F)
abline(A2, col="red")

#B
B2 <- lm(treasure ~ warnshot, data=capture)
pirateplot(dv.name = "treasure",
           iv.name = "warnshot",
           data = capture,
           add.hdi = F)
abline(B2, col="red")

#C
C2 <- lm(treasure ~ heardof, data=capture)
pirateplot(dv.name = "treasure",
           iv.name = "heardof",
           data = capture,
           add.hdi = F)
abline(C2, col="red")

Question 3

#For each of the following variables (separately), calculate the median amount of treasure earned for each level of the IV: style, warnshot, decorations (hint: use aggregate or dplyr!)

with(capture, aggregate(treasure ~ style, FUN = mean))
##     style treasure
## 1 classic 2184.301
## 2  modern 2095.645
with(capture, aggregate(treasure ~ warnshot, FUN = mean))
##   warnshot treasure
## 1        0 2085.940
## 2        1 2174.802
with(capture, aggregate(treasure ~ decorations, FUN = mean))
##    decorations treasure
## 1            1 3175.472
## 2            2 1764.758
## 3            3 1865.688
## 4            4 1847.904
## 5            5 1881.486
## 6            6 1879.208
## 7            7 1954.426
## 8            8 1998.511
## 9            9 1962.857
## 10          10 2005.526

Question 4

#The formula notation for conducting a correlation test with cor.test() is a bit different from regular formula notation. Instead of dv ~ iv, you use ~ dv + iv. For example, the following code will test the correlation between chickens’ age and weight using the ChickWeight dataset.
# A. Using the formula notation above, conduct a correlation test between the number of cannons a ship has and its size. What is the p-value?
cor.test(~ cannons + size, 
         data = capture)
## 
##  Pearson's product-moment correlation
## 
## data:  cannons and size
## t = 0.90501, df = 998, p-value = 0.3657
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.03341657  0.09046832
## sample estimates:
##        cor 
## 0.02863584
# p-value = 0.3657

# B. Now do the same with linear regression. What is the p-value?
can.ship <- lm(size ~ cannons, 
         data = capture)
summary(can.ship)
## 
## Call:
## lm(formula = size ~ cannons, data = capture)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -12.9844  -2.8873  -0.0596   2.9028  13.1409 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 49.859132   0.262458 189.970   <2e-16 ***
## cannons      0.006266   0.006923   0.905    0.366    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.14 on 998 degrees of freedom
## Multiple R-squared:  0.00082,    Adjusted R-squared:  -0.0001812 
## F-statistic: 0.819 on 1 and 998 DF,  p-value: 0.3657

Question 5

# Conduct a linear regression with treasure as the dependent variable, and with all other variables as independent variables. Save the object as treasure.model
treasure.model <- lm(treasure ~ size + cannons + style + warnshot + date + heardof + decorations + daysfromshore + speed + treasure,  
         data = capture)
## Warning in model.matrix.default(mt, mf, contrasts): the response appeared
## on the right-hand side and was dropped
## Warning in model.matrix.default(mt, mf, contrasts): problem with term 10 in
## model.matrix: no columns are assigned
#Using the summary() function, print the coefficients and main statistics of the regression
summary(treasure.model)
## 
## Call:
## lm(formula = treasure ~ size + cannons + style + warnshot + date + 
##     heardof + decorations + daysfromshore + speed + treasure, 
##     data = capture)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -880.96 -443.16 -211.02   66.08 2427.97 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    749.8957   351.0514   2.136 0.032913 *  
## size            22.5203     5.9602   3.778 0.000167 ***
## cannons         19.3817     1.2932  14.987  < 2e-16 ***
## stylemodern   -165.0932    84.6314  -1.951 0.051371 .  
## warnshot        89.0164    61.0610   1.458 0.145205    
## date             0.1508     0.2313   0.652 0.514511    
## heardof         92.1270    54.7238   1.683 0.092595 .  
## decorations    -96.3998    10.0249  -9.616  < 2e-16 ***
## daysfromshore   -8.6119     2.8180  -3.056 0.002303 ** 
## speed            9.2639     8.3892   1.104 0.269750    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 771.4 on 990 degrees of freedom
## Multiple R-squared:  0.2661, Adjusted R-squared:  0.2594 
## F-statistic: 39.88 on 9 and 990 DF,  p-value: < 2.2e-16