Avocado Pricing - Hackathon
Group 5
10/10/2021
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.
Note: this analysis was performed using the open source software R and Rstudio.
Objective
The objective of this analysis is to find the elasticity between demand and price change in avocados.
Descriptive statistics
Elasticity is the used to calculate the change in demand of a product or service when price fluctuates. For example if elasticity excists whne price increases in avocados than demand would drop, and if there is no elasticity than demand would stay constant as prices in avocados fluctuate.
data <- read.csv("avocado_2020.csv")
head(data)## date average_price total_volume type year geography
## 1 12/3/17 1.39 139970 conventional 2017 Albany
## 2 12/3/17 1.44 3577 organic 2017 Albany
## 3 12/3/17 1.07 504933 conventional 2017 Atlanta
## 4 12/3/17 1.62 10609 organic 2017 Atlanta
## 5 12/3/17 1.43 658939 conventional 2017 Baltimore/Washington
## 6 12/3/17 1.58 38754 organic 2017 Baltimore/Washington
## Mileage
## 1 2832
## 2 2832
## 3 2199
## 4 2199
## 5 2679
## 6 2679#install.packages('plyr')
library(plyr)
count(data, 'geography')## geography freq
## 1 Albany 308
## 2 Atlanta 308
## 3 Baltimore/Washington 308
## 4 Boise 308
## 5 Boston 308
## 6 Buffalo/Rochester 308
## 7 Charlotte 308
## 8 Chicago 308
## 9 Cincinnati/Dayton 308
## 10 Columbus 308
## 11 Dallas/Ft. Worth 308
## 12 Denver 308
## 13 Detroit 308
## 14 Grand Rapids 308
## 15 Harrisburg/Scranton 308
## 16 Hartford/Springfield 308
## 17 Houston 308
## 18 Indianapolis 308
## 19 Jacksonville 308
## 20 Las Vegas 308
## 21 Los Angeles 308
## 22 Louisville 308
## 23 Miami/Ft. Lauderdale 308
## 24 Nashville 308
## 25 New Orleans/Mobile 308
## 26 New York 308
## 27 Orlando 308
## 28 Philadelphia 308
## 29 Phoenix/Tucson 308
## 30 Pittsburgh 308
## 31 Portland 308
## 32 Raleigh/Greensboro 308
## 33 Richmond/Norfolk 308
## 34 Sacramento 308
## 35 San Diego 308
## 36 San Francisco 308
## 37 Seattle 308
## 38 Spokane 308
## 39 St. Louis 308
## 40 Syracuse 308
## 41 Tampa 308count(data, 'average_price')## average_price freq
## 1 0.50 1
## 2 0.51 1
## 3 0.53 1
## 4 0.54 2
## 5 0.56 4
## 6 0.57 1
## 7 0.58 2
## 8 0.59 4
## 9 0.60 1
## 10 0.61 4
## 11 0.62 7
## 12 0.63 3
## 13 0.64 8
## 14 0.65 8
## 15 0.66 12
## 16 0.67 15
## 17 0.68 15
## 18 0.69 11
## 19 0.70 21
## 20 0.71 21
## 21 0.72 24
## 22 0.73 32
## 23 0.74 34
## 24 0.75 26
## 25 0.76 36
## 26 0.77 32
## 27 0.78 35
## 28 0.79 26
## 29 0.80 40
## 30 0.81 47
## 31 0.82 38
## 32 0.83 40
## 33 0.84 55
## 34 0.85 51
## 35 0.86 48
## 36 0.87 55
## 37 0.88 63
## 38 0.89 78
## 39 0.90 74
## 40 0.91 86
## 41 0.92 85
## 42 0.93 94
## 43 0.94 91
## 44 0.95 109
## 45 0.96 94
## 46 0.97 100
## 47 0.98 112
## 48 0.99 105
## 49 1.00 110
## 50 1.01 126
## 51 1.02 93
## 52 1.03 130
## 53 1.04 132
## 54 1.05 106
## 55 1.06 116
## 56 1.07 106
## 57 1.08 112
## 58 1.09 136
## 59 1.10 141
## 60 1.11 107
## 61 1.12 113
## 62 1.13 137
## 63 1.14 183
## 64 1.15 161
## 65 1.16 159
## 66 1.17 156
## 67 1.18 148
## 68 1.19 164
## 69 1.20 169
## 70 1.21 133
## 71 1.22 141
## 72 1.23 135
## 73 1.24 142
## 74 1.25 148
## 75 1.26 143
## 76 1.27 134
## 77 1.28 142
## 78 1.29 153
## 79 1.30 119
## 80 1.31 138
## 81 1.32 141
## 82 1.33 120
## 83 1.34 137
## 84 1.35 144
## 85 1.36 151
## 86 1.37 149
## 87 1.38 155
## 88 1.39 129
## 89 1.40 131
## 90 1.41 141
## 91 1.42 146
## 92 1.43 139
## 93 1.44 120
## 94 1.45 137
## 95 1.46 140
## 96 1.47 118
## 97 1.48 119
## 98 1.49 105
## 99 1.50 123
## 100 1.51 118
## 101 1.52 108
## 102 1.53 117
## 103 1.54 93
## 104 1.55 119
## 105 1.56 95
## 106 1.57 97
## 107 1.58 89
## 108 1.59 111
## 109 1.60 95
## 110 1.61 95
## 111 1.62 83
## 112 1.63 86
## 113 1.64 87
## 114 1.65 86
## 115 1.66 86
## 116 1.67 69
## 117 1.68 67
## 118 1.69 84
## 119 1.70 65
## 120 1.71 66
## 121 1.72 65
## 122 1.73 70
## 123 1.74 54
## 124 1.75 64
## 125 1.76 58
## 126 1.77 62
## 127 1.78 58
## 128 1.79 56
## 129 1.80 63
## 130 1.81 47
## 131 1.82 53
## 132 1.83 51
## 133 1.84 45
## 134 1.85 48
## 135 1.86 47
## 136 1.87 46
## 137 1.88 44
## 138 1.89 38
## 139 1.90 42
## 140 1.91 49
## 141 1.92 41
## 142 1.93 35
## 143 1.94 35
## 144 1.95 38
## 145 1.96 36
## 146 1.97 34
## 147 1.98 33
## 148 1.99 26
## 149 2.00 23
## 150 2.01 19
## 151 2.02 34
## 152 2.03 30
## 153 2.04 25
## 154 2.05 33
## 155 2.06 23
## 156 2.07 26
## 157 2.08 22
## 158 2.09 16
## 159 2.10 18
## 160 2.11 21
## 161 2.12 16
## 162 2.13 17
## 163 2.14 17
## 164 2.15 21
## 165 2.16 24
## 166 2.17 8
## 167 2.18 16
## 168 2.19 15
## 169 2.20 8
## 170 2.21 18
## 171 2.22 11
## 172 2.23 7
## 173 2.24 9
## 174 2.25 9
## 175 2.26 8
## 176 2.27 12
## 177 2.28 6
## 178 2.29 3
## 179 2.30 4
## 180 2.31 9
## 181 2.32 6
## 182 2.33 7
## 183 2.34 5
## 184 2.35 4
## 185 2.36 6
## 186 2.37 5
## 187 2.38 5
## 188 2.39 9
## 189 2.40 5
## 190 2.41 5
## 191 2.42 2
## 192 2.43 5
## 193 2.44 6
## 194 2.45 4
## 195 2.46 4
## 196 2.48 2
## 197 2.49 3
## 198 2.50 3
## 199 2.51 1
## 200 2.52 2
## 201 2.53 1
## 202 2.54 1
## 203 2.55 2
## 204 2.56 2
## 205 2.57 1
## 206 2.59 1
## 207 2.60 1
## 208 2.62 2
## 209 2.64 2
## 210 2.66 4
## 211 2.67 1
## 212 2.69 2
## 213 2.71 3
## 214 2.72 2
## 215 2.73 1
## 216 2.78 1mean(data$average_price)## [1] 1.358841median(data$average_price)## [1] 1.32cor(data$total_volume,data$average_price)## [1] -0.4169306Price elasticity
To calculate Price Elasticity of Demand we use the formula: PE = (ΔQ/ΔP) * (P/Q) # (Iacobacci, 2015, p.134-135).
(ΔQ/ΔP) is determined by the coefficient in our regression analysis below. Here Beta represents the change in the dependent variable y with respect to x (i.e. Δy/Δx = (ΔQ/ΔP)). To determine (P/Q) we will use the average price and average sales volume (Salem, 2014).
plot(total_volume ~ average_price, data)
regr <- lm(total_volume ~ average_price, data)
abline(regr, col='red')
summary(regr)##
## Call:
## lm(formula = total_volume ~ average_price, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -679205 -277566 -128592 118917 4901891
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1179545 17117 68.91 <2e-16 ***
## average_price -628687 12198 -51.54 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 480300 on 12626 degrees of freedom
## Multiple R-squared: 0.1738, Adjusted R-squared: 0.1738
## F-statistic: 2657 on 1 and 12626 DF, p-value: < 2.2e-16coefficients(regr)## (Intercept) average_price
## 1179544.8 -628686.6Beta <- regr$coefficients[["average_price"]]
P <- mean(data$average_price)
Q <- mean(data$total_volume)
elasticity <-Beta*P/Q
elasticity## [1] -2.626474Elasticity
According to the analysis conducted through R, there is a price elasticity of -2.63 on the sales volume of avocados. This means that for every unit of price increased will have an opposite effect on the purchased avocados by 2.63 units. The regression analysis above helps us visualize this concept. This analysis yielded a mean price of 1.35 and a median price of 1.32 with a correlation of -.42. This tells us that the average observed price was 1.35, that 50% of prices were above1.32 and the other 50% were below, and that the correlation between the two variables. The Y axis measures the units sold and the X axis measures price price. As you can see the clusters are mainly concentrated to the left corner of the table where price is lowest, and the volume is highest. As we move further right on the X axis we see the clusters thinning out and the volume decreasing causing a downward slope by 2.63 units for every .50 increase in price.
Ref: Salem, 2014. Price Elasticity with R. http://www.salemmarafi.com/code/price-elasticity-with-r/
365datascience. https://365datascience.com/trending/price-elasticity/