Fall 2017 Acct 305 Individual Project #1 Due: 9/25/2017 Harlow Company is an onl

Question

Fall 2017 Acct 305 Individual Project #1 Due: 9/25/2017 Harlow Company is an online discount retailer. The CEO wants to better understand their distribution costs, and has asked his accounting team to look into it. Discussion with the workers in the distribution department have determined that distribution expense are operationally associated with 1. 2. 3. Number of orders The number of parcels in an order Number of large items shipped Data for the past 24 months as compiled by the accounting department: Month Distribution Cost 45,000 58,000 155,000 450,000 90,000 126,000 90,600 54,000 175,000 287,000 350,000 425,000 110,000 95,000 160,000 85,000 135,000 75,000 125,000 175,000 150,000 138,000 260,000 325,000 Number of Orders 11,200 14,000 40,000 110,000 20,000 33,100 21,000 12,800 43,860 50,000 92,700 85,000 28,220 21,200 38,560 19,630 35,800 18,900 33,070 43,420 35,720 35,300 68,000 87,750 Number of parcels in an order 38,000 Number of Large items 1,120 1,400 55,000 50,000 38,600 68,000 50,000 3000 85,000 75,000 85,000 4 850 4,000 5,500 1,800 6 1,500 2,500 5,000 14,000 35,000 50,000 70,000 35,000 40,000 25,000 45,000 70,000 66,800 62,500 85,000 63,000 1,340 3,000 2,000 1,900 1,430 2,200 9,000 15,250

Explanation / Answer

We shall analyse this in the open source statistical package R , The R snippet is as shown below

# read the data into R dataframe
data.df<- read.csv("C:\Users\586645\Downloads\Chegg\distcost.csv",header=TRUE)
str(data.df)

## summary of the variables

summary(data.df)

## fit the model

fit <- lm(DistributionCost~., data=data.df)
summary(fit)

## plot the model
##
par(mfrow=c(2,2))
plot(fit)

The results are

> summary(fit)

Call:
lm(formula = DistributionCost ~ ., data = data.df)

Residuals:
Min 1Q Median 3Q Max
-42834 -9600 -2911 2993 81115

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 6.110e+02 1.887e+04 0.032 0.974
orders 4.039e+00 2.934e-01 13.765 1.16e-11 ***
parcels 1.905e-02 3.878e-01 0.049 0.961
items 7.617e-01 1.812e+00 0.420 0.679
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 27900 on 20 degrees of freedom
Multiple R-squared: 0.9495,   Adjusted R-squared: 0.9419
F-statistic: 125.4 on 3 and 20 DF, p-value: 3.887e-13

based on the abvoce results, we see that only the number of orders is the statisitically signficant variable that contributes towards explaining the distribution costs. The model equation in terms of signficant variables would be thus

Distribution cost = 611.0 +4.03*number of orders

The multiple regression analysis equation is formed by using all the variablesa s

DistributionCost = 611.0 +4.03*number of orders -0.019*parcels +0.076*items

to predict the distribution cost , we use the regression equation an put the assigned values

DistributionCost = 611.0 +4.03*95000 -0.019*150000 +0.076*9500or using the r code as

####

newdata <- data.frame(orders=95000,parcels=150000 , items=9500 )

predict(fit,newdata)

394393

please note that we can answer only 4 subparts of a question at a time , as per the answering guidelines

Related Questions

Navigate

• Browse (All)
• Browse F
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.