rm(list =ls())
library(readxl)
# read data
RD <- read_excel("/home/hossein/Downloads/organiseddata.xlsx")

# summary stats
summary(RD)
##       Year          Month      Frynumber     Quntityoffeed   Quantityharvested
##  Min.   :2016   Min.   : 1   Min.   :10245   Min.   : 5405   Min.   : 5357    
##  1st Qu.:2016   1st Qu.: 9   1st Qu.:19337   1st Qu.: 7890   1st Qu.: 6616    
##  Median :2017   Median :17   Median :24086   Median : 8612   Median : 7512    
##  Mean   :2017   Mean   :17   Mean   :26961   Mean   :10694   Mean   : 9235    
##  3rd Qu.:2018   3rd Qu.:25   3rd Qu.:36307   3rd Qu.: 9946   3rd Qu.: 9352    
##  Max.   :2019   Max.   :33   Max.   :53171   Max.   :35260   Max.   :25799    
##    No.workers      Revenue        Costoffry        Costoffeed   
##  Min.   :11.0   Min.   :11361   Min.   : 409.8   Min.   : 5567  
##  1st Qu.:11.0   1st Qu.:14010   1st Qu.: 773.5   1st Qu.: 8127  
##  Median :13.0   Median :16477   Median : 963.4   Median : 8870  
##  Mean   :12.7   Mean   :20056   Mean   :1078.5   Mean   :11014  
##  3rd Qu.:13.0   3rd Qu.:19150   3rd Qu.:1452.3   3rd Qu.:10244  
##  Max.   :15.0   Max.   :56241   Max.   :2126.8   Max.   :36318  
##   Costoflabor     Equipmentcosts     Operationcosts    Totalcost    
##  Min.   : 910.8   Min.   :   2.101   Min.   :111.9   Min.   : 7397  
##  1st Qu.: 996.3   1st Qu.:  31.620   1st Qu.:211.2   1st Qu.:10457  
##  Median :1088.6   Median :  77.046   Median :268.2   Median :11631  
##  Mean   :1095.5   Mean   : 109.737   Mean   :281.2   Mean   :13579  
##  3rd Qu.:1169.6   3rd Qu.: 109.471   3rd Qu.:351.4   3rd Qu.:12935  
##  Max.   :1361.6   Max.   :1180.772   Max.   :552.1   Max.   :40089  
##     CashFlow           PV       
##  Min.   : 1303   Min.   : 1218  
##  1st Qu.: 3964   1st Qu.: 3544  
##  Median : 5158   Median : 4479  
##  Mean   : 6477   Mean   : 5590  
##  3rd Qu.: 6400   3rd Qu.: 5626  
##  Max.   :19293   Max.   :15749
# Histograms
hist(RD$Frynumber)

hist(RD$Quntityoffeed)

hist(RD$No.workers)

table1::table1 (~ Frynumber + Quntityoffeed+No.workers + Quantityharvested|Year, data=RD,overall="Total",
                topclass="Rtable1-grid Rtable1-shade Rtable1-times")
## Warning in table1.formula(~Frynumber + Quntityoffeed + No.workers +
## Quantityharvested | : Terms to the right of '|' in formula 'x' define table
## columns and are expected to be factors with meaningful labels.
2016
(N=9)		 2017
(N=12)		 2018
(N=7)		 2019
(N=5)		 Total
(N=33)
Frynumber
Mean (SD) 25200 (10400) 25700 (11200) 35100 (13500) 21900 (8460) 27000 (11500)
Median [Min, Max] 24100 [13600, 42000] 21900 [10200, 46000] 30000 [19300, 53200] 19500 [14900, 36300] 24100 [10200, 53200]
Quntityoffeed
Mean (SD) 9200 (3200) 10200 (4590) 15600 (10000) 7680 (1540) 10700 (6030)
Median [Min, Max] 8890 [5510, 16600] 7890 [5410, 20800] 12900 [6890, 35300] 7890 [5510, 9490] 8610 [5410, 35300]
No.workers
Mean (SD) 11.0 (0) 13.0 (0) 12.7 (0.488) 15.0 (0) 12.7 (1.31)
Median [Min, Max] 11.0 [11.0, 11.0] 13.0 [13.0, 13.0] 13.0 [12.0, 13.0] 15.0 [15.0, 15.0] 13.0 [11.0, 15.0]
Quantityharvested
Mean (SD) 8230 (3120) 8950 (4050) 12600 (7480) 7050 (1360) 9240 (4720)
Median [Min, Max] 7770 [5360, 15600] 7030 [5360, 18000] 8290 [6620, 25800] 6640 [5850, 9350] 7510 [5360, 25800] 
# Modeling

m1  <- lm(Quantityharvested ~ Frynumber+No.workers+Quntityoffeed, data=RD)
summary(m1)
## 
## Call:
## lm(formula = Quantityharvested ~ Frynumber + No.workers + Quntityoffeed, 
##     data = RD)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2899.43  -377.88    23.03   447.18  2291.57 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    -71.33503 1845.76563  -0.039 0.969436    
## Frynumber        0.12680    0.03150   4.026 0.000373 ***
## No.workers       3.35089  139.09865   0.024 0.980946    
## Quntityoffeed    0.54664    0.06026   9.071 5.74e-10 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1029 on 29 degrees of freedom
## Multiple R-squared:  0.957,  Adjusted R-squared:  0.9526 
## F-statistic: 215.2 on 3 and 29 DF,  p-value: < 2.2e-16
anova(m1)
## Analysis of Variance Table
## 
## Response: Quantityharvested
##               Df    Sum Sq   Mean Sq  F value    Pr(>F)    
## Frynumber      1 596130622 596130622 563.0967 < 2.2e-16 ***
## No.workers     1    345431    345431   0.3263    0.5723    
## Quntityoffeed  1  87119721  87119721  82.2921 5.738e-10 ***
## Residuals     29  30701279   1058665                       
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot(m1)

m3 <- lm(Revenue ~ Costoffry+Costoffeed+Costoflabor+Equipmentcosts+Operationcosts, data = RD)
summary(m3)
## 
## Call:
## lm(formula = Revenue ~ Costoffry + Costoffeed + Costoflabor + 
##     Equipmentcosts + Operationcosts, data = RD)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -6251.0 -1127.4   123.7  1448.5  4972.2 
## 
## Coefficients:
##                  Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    -1.510e+03  3.963e+03  -0.381  0.70617    
## Costoffry       6.928e+00  1.893e+00   3.660  0.00108 ** 
## Costoffeed      1.193e+00  1.402e-01   8.512 3.99e-09 ***
## Costoflabor    -6.083e-01  3.813e+00  -0.160  0.87443    
## Equipmentcosts  1.189e-02  2.203e+00   0.005  0.99573    
## Operationcosts  5.740e+00  4.600e+00   1.248  0.22277    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2428 on 27 degrees of freedom
## Multiple R-squared:  0.9548, Adjusted R-squared:  0.9464 
## F-statistic: 114.1 on 5 and 27 DF,  p-value: < 2.2e-16
anova(m3)
## Analysis of Variance Table
## 
## Response: Revenue
##                Df     Sum Sq    Mean Sq  F value    Pr(>F)    
## Costoffry       1 2908951033 2908951033 493.3563 < 2.2e-16 ***
## Costoffeed      1  444199946  444199946  75.3360 2.701e-09 ***
## Costoflabor     1    1059009    1059009   0.1796    0.6751    
## Equipmentcosts  1       4303       4303   0.0007    0.9786    
## Operationcosts  1    9182432    9182432   1.5573    0.2228    
## Residuals      27  159198680    5896247                       
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
plot(m3)

m4 <- lm(PV ~ Totalcost+Equipmentcosts+Operationcosts+Quantityharvested+Year,data = RD)
summary(m4)
## 
## Call:
## lm(formula = PV ~ Totalcost + Equipmentcosts + Operationcosts + 
##     Quantityharvested + Year, data = RD)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -934.9 -521.4  149.8  388.9 1089.3 
## 
## Coefficients:
##                     Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        1.082e+06  2.234e+05   4.846 4.61e-05 ***
## Totalcost         -8.292e-01  7.264e-02 -11.416 7.70e-12 ***
## Equipmentcosts     1.306e-01  5.773e-01   0.226    0.823    
## Operationcosts     1.382e+00  1.086e+00   1.272    0.214    
## Quantityharvested  1.855e+00  1.009e-01  18.378  < 2e-16 ***
## Year              -5.369e+02  1.108e+02  -4.847 4.59e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 630.2 on 27 degrees of freedom
## Multiple R-squared:  0.9764, Adjusted R-squared:  0.9721 
## F-statistic: 223.7 on 5 and 27 DF,  p-value: < 2.2e-16