Workshop Experimental
Vitor
2023-02-09
Workshop
Let’s learn basic economics in R
loading Pakages
Data
#Import
dictator <- read.csv("dictator.csv")
#mydata<- read.csv("C:/Econometrics/Data/panel_wage.csv")
attach(dictator)In case you want to use XLSX file you can follow this instructions http://www.sthda.com/english/wiki/reading-data-from-excel-files-xls-xlsx-into-r
Checking the Data
str(dictator)## 'data.frame': 218 obs. of 6 variables:
## $ ID : int 522 302 111 511 406 605 314 603 8 409 ...
## $ in_group : int 1 1 1 1 1 1 1 1 1 1 ...
## $ giving : int 5 0 0 5 10 5 10 5 20 15 ...
## $ age : int 1 4 2 1 4 1 1 1 1 4 ...
## $ yearly_income: int 540 550 700 800 1100 1500 1500 2000 2000 2000 ...
## $ female : int 1 0 0 1 0 0 1 0 1 1 ...summary(dictator)## ID in_group giving age yearly_income
## Min. : 1.0 Min. :0.0 Min. : 0.000 Min. :1.000 Min. : 540
## 1st Qu.:203.0 1st Qu.:0.0 1st Qu.: 3.000 1st Qu.:1.000 1st Qu.: 4000
## Median :315.0 Median :0.5 Median :10.000 Median :3.000 Median : 7100
## Mean :352.5 Mean :0.5 Mean : 8.491 Mean :2.569 Mean : 9936
## 3rd Qu.:522.0 3rd Qu.:1.0 3rd Qu.:10.000 3rd Qu.:4.000 3rd Qu.:10000
## Max. :633.0 Max. :1.0 Max. :30.000 Max. :5.000 Max. :75000
## NA's :6
## female
## Min. :0.0000
## 1st Qu.:0.0000
## Median :0.0000
## Mean :0.4128
## 3rd Qu.:1.0000
## Max. :1.0000
## plot(dictator)
hist(dictator$giving)
out <- subset(dictator$giving, dictator$in_group ==0 )
ing <- subset(dictator$giving, dictator$in_group ==1 )
#Let's go Fancy
# histogram with added parameters
hist(dictator$giving,
main="Dictator Game",
xlab="Amount Given",
col="darkmagenta",
freq=TRUE
)
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.3.0 ✔ stringr 1.5.0
## ✔ readr 2.1.4 ✔ forcats 1.0.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::between() masks plm::between()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks plm::lag(), stats::lag()
## ✖ dplyr::lead() masks plm::lead()# create dummy data
ggplot(dictator) +
geom_bar( aes(x=in_group, y=(giving)), stat="identity", fill="skyblue", alpha=0.7) +
theme_bw()+
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank())+
labs(title = "Groups", x="In group and Out group", y = "Total")
#geom_errorbar( aes(x=name, ymin=value-sd, ymax=value+sd), width=0.4, colour="orange", alpha=0.9, size=1.3)#install.packages("plotly")
library(dbplyr)##
## Attaching package: 'dbplyr'## The following objects are masked from 'package:dplyr':
##
## ident, sqllibrary(plotly)##
## Attaching package: 'plotly'## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layoutdata <- read.csv('dictator.csv')
df_mean <- data %>% group_by(in_group)%>%summarise(mean(giving))
df_mean$str <- c("0","1")
fig <- plot_ly(x = df_mean$str,y = df_mean$`mean(giving)`,type = 'bar',color = ~ df_mean$str)%>%
layout(#title = "........",list(size= 20),
xaxis = list(title = "In Group",titlefont = list(size=10 )),
yaxis = list(title = "Giving", titlefont = list(size=10)))
print(fig)## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levels
## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levelsData Manipulation
#missing data
is.na(dictator)## ID in_group giving age yearly_income female
## [1,] FALSE FALSE FALSE FALSE FALSE FALSE
## [2,] FALSE FALSE FALSE FALSE FALSE FALSE
## [3,] FALSE FALSE FALSE FALSE FALSE FALSE
## [4,] FALSE FALSE FALSE FALSE FALSE FALSE
## [5,] FALSE FALSE FALSE FALSE FALSE FALSE
## [6,] FALSE FALSE FALSE FALSE FALSE FALSE
## [7,] FALSE FALSE FALSE FALSE FALSE FALSE
## [8,] FALSE FALSE FALSE FALSE FALSE FALSE
## [9,] FALSE FALSE FALSE FALSE FALSE FALSE
## [10,] FALSE FALSE FALSE FALSE FALSE FALSE
## [11,] FALSE FALSE FALSE FALSE FALSE FALSE
## [12,] FALSE FALSE FALSE FALSE FALSE FALSE
## [13,] FALSE FALSE FALSE FALSE FALSE FALSE
## [14,] FALSE FALSE FALSE FALSE FALSE FALSE
## [15,] FALSE FALSE FALSE FALSE FALSE FALSE
## [16,] FALSE FALSE FALSE FALSE FALSE FALSE
## [17,] FALSE FALSE FALSE FALSE FALSE FALSE
## [18,] FALSE FALSE FALSE FALSE FALSE FALSE
## [19,] FALSE FALSE FALSE FALSE FALSE FALSE
## [20,] FALSE FALSE FALSE FALSE FALSE FALSE
## [21,] FALSE FALSE FALSE FALSE FALSE FALSE
## [22,] FALSE FALSE FALSE FALSE FALSE FALSE
## [23,] FALSE FALSE FALSE FALSE FALSE FALSE
## [24,] FALSE FALSE FALSE FALSE FALSE FALSE
## [25,] FALSE FALSE FALSE FALSE FALSE FALSE
## [26,] FALSE FALSE FALSE FALSE FALSE FALSE
## [27,] FALSE FALSE FALSE FALSE FALSE FALSE
## [28,] FALSE FALSE FALSE FALSE FALSE FALSE
## [29,] FALSE FALSE FALSE FALSE FALSE FALSE
## [30,] FALSE FALSE FALSE FALSE FALSE FALSE
## [31,] FALSE FALSE FALSE FALSE FALSE FALSE
## [32,] FALSE FALSE FALSE FALSE FALSE FALSE
## [33,] FALSE FALSE FALSE FALSE FALSE FALSE
## [34,] FALSE FALSE FALSE FALSE FALSE FALSE
## [35,] FALSE FALSE FALSE FALSE FALSE FALSE
## [36,] FALSE FALSE FALSE FALSE FALSE FALSE
## [37,] FALSE FALSE FALSE FALSE FALSE FALSE
## [38,] FALSE FALSE FALSE FALSE FALSE FALSE
## [39,] FALSE FALSE FALSE FALSE FALSE FALSE
## [40,] FALSE FALSE FALSE FALSE FALSE FALSE
## [41,] FALSE FALSE FALSE FALSE FALSE FALSE
## [42,] FALSE FALSE FALSE FALSE FALSE FALSE
## [43,] FALSE FALSE FALSE FALSE FALSE FALSE
## [44,] FALSE FALSE FALSE FALSE FALSE FALSE
## [45,] FALSE FALSE FALSE FALSE FALSE FALSE
## [46,] FALSE FALSE FALSE FALSE FALSE FALSE
## [47,] FALSE FALSE FALSE FALSE FALSE FALSE
## [48,] FALSE FALSE FALSE FALSE FALSE FALSE
## [49,] FALSE FALSE FALSE FALSE FALSE FALSE
## [50,] FALSE FALSE FALSE FALSE FALSE FALSE
## [51,] FALSE FALSE FALSE FALSE FALSE FALSE
## [52,] FALSE FALSE FALSE FALSE FALSE FALSE
## [53,] FALSE FALSE FALSE FALSE FALSE FALSE
## [54,] FALSE FALSE FALSE FALSE FALSE FALSE
## [55,] FALSE FALSE FALSE FALSE FALSE FALSE
## [56,] FALSE FALSE FALSE FALSE FALSE FALSE
## [57,] FALSE FALSE FALSE FALSE FALSE FALSE
## [58,] FALSE FALSE FALSE FALSE FALSE FALSE
## [59,] FALSE FALSE FALSE FALSE FALSE FALSE
## [60,] FALSE FALSE FALSE FALSE FALSE FALSE
## [61,] FALSE FALSE FALSE FALSE FALSE FALSE
## [62,] FALSE FALSE FALSE FALSE FALSE FALSE
## [63,] FALSE FALSE FALSE FALSE FALSE FALSE
## [64,] FALSE FALSE FALSE FALSE FALSE FALSE
## [65,] FALSE FALSE FALSE FALSE FALSE FALSE
## [66,] FALSE FALSE FALSE FALSE FALSE FALSE
## [67,] FALSE FALSE FALSE FALSE FALSE FALSE
## [68,] FALSE FALSE FALSE FALSE FALSE FALSE
## [69,] FALSE FALSE FALSE FALSE FALSE FALSE
## [70,] FALSE FALSE FALSE FALSE FALSE FALSE
## [71,] FALSE FALSE FALSE FALSE FALSE FALSE
## [72,] FALSE FALSE FALSE FALSE FALSE FALSE
## [73,] FALSE FALSE FALSE FALSE FALSE FALSE
## [74,] FALSE FALSE FALSE FALSE FALSE FALSE
## [75,] FALSE FALSE FALSE FALSE FALSE FALSE
## [76,] FALSE FALSE FALSE FALSE FALSE FALSE
## [77,] FALSE FALSE FALSE FALSE FALSE FALSE
## [78,] FALSE FALSE FALSE FALSE FALSE FALSE
## [79,] FALSE FALSE FALSE FALSE FALSE FALSE
## [80,] FALSE FALSE FALSE FALSE FALSE FALSE
## [81,] FALSE FALSE FALSE FALSE FALSE FALSE
## [82,] FALSE FALSE FALSE FALSE FALSE FALSE
## [83,] FALSE FALSE FALSE FALSE FALSE FALSE
## [84,] FALSE FALSE FALSE FALSE FALSE FALSE
## [85,] FALSE FALSE FALSE FALSE FALSE FALSE
## [86,] FALSE FALSE FALSE FALSE FALSE FALSE
## [87,] FALSE FALSE FALSE FALSE FALSE FALSE
## [88,] FALSE FALSE FALSE FALSE FALSE FALSE
## [89,] FALSE FALSE FALSE FALSE FALSE FALSE
## [90,] FALSE FALSE FALSE FALSE FALSE FALSE
## [91,] FALSE FALSE FALSE FALSE FALSE FALSE
## [92,] FALSE FALSE FALSE FALSE FALSE FALSE
## [93,] FALSE FALSE FALSE FALSE FALSE FALSE
## [94,] FALSE FALSE FALSE FALSE FALSE FALSE
## [95,] FALSE FALSE FALSE FALSE FALSE FALSE
## [96,] FALSE FALSE FALSE FALSE FALSE FALSE
## [97,] FALSE FALSE FALSE FALSE FALSE FALSE
## [98,] FALSE FALSE FALSE FALSE FALSE FALSE
## [99,] FALSE FALSE FALSE FALSE FALSE FALSE
## [100,] FALSE FALSE FALSE FALSE FALSE FALSE
## [101,] FALSE FALSE FALSE FALSE FALSE FALSE
## [102,] FALSE FALSE FALSE FALSE FALSE FALSE
## [103,] FALSE FALSE FALSE FALSE FALSE FALSE
## [104,] FALSE FALSE FALSE FALSE FALSE FALSE
## [105,] FALSE FALSE FALSE FALSE FALSE FALSE
## [106,] FALSE FALSE FALSE FALSE FALSE FALSE
## [107,] FALSE FALSE FALSE FALSE TRUE FALSE
## [108,] FALSE FALSE FALSE FALSE TRUE FALSE
## [109,] FALSE FALSE FALSE FALSE TRUE FALSE
## [110,] FALSE FALSE FALSE FALSE FALSE FALSE
## [111,] FALSE FALSE FALSE FALSE FALSE FALSE
## [112,] FALSE FALSE FALSE FALSE FALSE FALSE
## [113,] FALSE FALSE FALSE FALSE FALSE FALSE
## [114,] FALSE FALSE FALSE FALSE FALSE FALSE
## [115,] FALSE FALSE FALSE FALSE FALSE FALSE
## [116,] FALSE FALSE FALSE FALSE FALSE FALSE
## [117,] FALSE FALSE FALSE FALSE FALSE FALSE
## [118,] FALSE FALSE FALSE FALSE FALSE FALSE
## [119,] FALSE FALSE FALSE FALSE FALSE FALSE
## [120,] FALSE FALSE FALSE FALSE FALSE FALSE
## [121,] FALSE FALSE FALSE FALSE FALSE FALSE
## [122,] FALSE FALSE FALSE FALSE FALSE FALSE
## [123,] FALSE FALSE FALSE FALSE FALSE FALSE
## [124,] FALSE FALSE FALSE FALSE FALSE FALSE
## [125,] FALSE FALSE FALSE FALSE FALSE FALSE
## [126,] FALSE FALSE FALSE FALSE FALSE FALSE
## [127,] FALSE FALSE FALSE FALSE FALSE FALSE
## [128,] FALSE FALSE FALSE FALSE FALSE FALSE
## [129,] FALSE FALSE FALSE FALSE FALSE FALSE
## [130,] FALSE FALSE FALSE FALSE FALSE FALSE
## [131,] FALSE FALSE FALSE FALSE FALSE FALSE
## [132,] FALSE FALSE FALSE FALSE FALSE FALSE
## [133,] FALSE FALSE FALSE FALSE FALSE FALSE
## [134,] FALSE FALSE FALSE FALSE FALSE FALSE
## [135,] FALSE FALSE FALSE FALSE FALSE FALSE
## [136,] FALSE FALSE FALSE FALSE FALSE FALSE
## [137,] FALSE FALSE FALSE FALSE FALSE FALSE
## [138,] FALSE FALSE FALSE FALSE FALSE FALSE
## [139,] FALSE FALSE FALSE FALSE FALSE FALSE
## [140,] FALSE FALSE FALSE FALSE FALSE FALSE
## [141,] FALSE FALSE FALSE FALSE FALSE FALSE
## [142,] FALSE FALSE FALSE FALSE FALSE FALSE
## [143,] FALSE FALSE FALSE FALSE FALSE FALSE
## [144,] FALSE FALSE FALSE FALSE FALSE FALSE
## [145,] FALSE FALSE FALSE FALSE FALSE FALSE
## [146,] FALSE FALSE FALSE FALSE FALSE FALSE
## [147,] FALSE FALSE FALSE FALSE FALSE FALSE
## [148,] FALSE FALSE FALSE FALSE FALSE FALSE
## [149,] FALSE FALSE FALSE FALSE FALSE FALSE
## [150,] FALSE FALSE FALSE FALSE FALSE FALSE
## [151,] FALSE FALSE FALSE FALSE FALSE FALSE
## [152,] FALSE FALSE FALSE FALSE FALSE FALSE
## [153,] FALSE FALSE FALSE FALSE FALSE FALSE
## [154,] FALSE FALSE FALSE FALSE FALSE FALSE
## [155,] FALSE FALSE FALSE FALSE FALSE FALSE
## [156,] FALSE FALSE FALSE FALSE FALSE FALSE
## [157,] FALSE FALSE FALSE FALSE FALSE FALSE
## [158,] FALSE FALSE FALSE FALSE FALSE FALSE
## [159,] FALSE FALSE FALSE FALSE FALSE FALSE
## [160,] FALSE FALSE FALSE FALSE FALSE FALSE
## [161,] FALSE FALSE FALSE FALSE FALSE FALSE
## [162,] FALSE FALSE FALSE FALSE FALSE FALSE
## [163,] FALSE FALSE FALSE FALSE FALSE FALSE
## [164,] FALSE FALSE FALSE FALSE FALSE FALSE
## [165,] FALSE FALSE FALSE FALSE FALSE FALSE
## [166,] FALSE FALSE FALSE FALSE FALSE FALSE
## [167,] FALSE FALSE FALSE FALSE FALSE FALSE
## [168,] FALSE FALSE FALSE FALSE FALSE FALSE
## [169,] FALSE FALSE FALSE FALSE FALSE FALSE
## [170,] FALSE FALSE FALSE FALSE FALSE FALSE
## [171,] FALSE FALSE FALSE FALSE FALSE FALSE
## [172,] FALSE FALSE FALSE FALSE FALSE FALSE
## [173,] FALSE FALSE FALSE FALSE FALSE FALSE
## [174,] FALSE FALSE FALSE FALSE FALSE FALSE
## [175,] FALSE FALSE FALSE FALSE FALSE FALSE
## [176,] FALSE FALSE FALSE FALSE FALSE FALSE
## [177,] FALSE FALSE FALSE FALSE FALSE FALSE
## [178,] FALSE FALSE FALSE FALSE FALSE FALSE
## [179,] FALSE FALSE FALSE FALSE FALSE FALSE
## [180,] FALSE FALSE FALSE FALSE FALSE FALSE
## [181,] FALSE FALSE FALSE FALSE FALSE FALSE
## [182,] FALSE FALSE FALSE FALSE FALSE FALSE
## [183,] FALSE FALSE FALSE FALSE FALSE FALSE
## [184,] FALSE FALSE FALSE FALSE FALSE FALSE
## [185,] FALSE FALSE FALSE FALSE FALSE FALSE
## [186,] FALSE FALSE FALSE FALSE FALSE FALSE
## [187,] FALSE FALSE FALSE FALSE FALSE FALSE
## [188,] FALSE FALSE FALSE FALSE FALSE FALSE
## [189,] FALSE FALSE FALSE FALSE FALSE FALSE
## [190,] FALSE FALSE FALSE FALSE FALSE FALSE
## [191,] FALSE FALSE FALSE FALSE FALSE FALSE
## [192,] FALSE FALSE FALSE FALSE FALSE FALSE
## [193,] FALSE FALSE FALSE FALSE FALSE FALSE
## [194,] FALSE FALSE FALSE FALSE FALSE FALSE
## [195,] FALSE FALSE FALSE FALSE FALSE FALSE
## [196,] FALSE FALSE FALSE FALSE FALSE FALSE
## [197,] FALSE FALSE FALSE FALSE FALSE FALSE
## [198,] FALSE FALSE FALSE FALSE FALSE FALSE
## [199,] FALSE FALSE FALSE FALSE FALSE FALSE
## [200,] FALSE FALSE FALSE FALSE FALSE FALSE
## [201,] FALSE FALSE FALSE FALSE FALSE FALSE
## [202,] FALSE FALSE FALSE FALSE FALSE FALSE
## [203,] FALSE FALSE FALSE FALSE FALSE FALSE
## [204,] FALSE FALSE FALSE FALSE FALSE FALSE
## [205,] FALSE FALSE FALSE FALSE FALSE FALSE
## [206,] FALSE FALSE FALSE FALSE FALSE FALSE
## [207,] FALSE FALSE FALSE FALSE FALSE FALSE
## [208,] FALSE FALSE FALSE FALSE FALSE FALSE
## [209,] FALSE FALSE FALSE FALSE FALSE FALSE
## [210,] FALSE FALSE FALSE FALSE FALSE FALSE
## [211,] FALSE FALSE FALSE FALSE FALSE FALSE
## [212,] FALSE FALSE FALSE FALSE FALSE FALSE
## [213,] FALSE FALSE FALSE FALSE FALSE FALSE
## [214,] FALSE FALSE FALSE FALSE FALSE FALSE
## [215,] FALSE FALSE FALSE FALSE FALSE FALSE
## [216,] FALSE FALSE FALSE FALSE TRUE FALSE
## [217,] FALSE FALSE FALSE FALSE TRUE FALSE
## [218,] FALSE FALSE FALSE FALSE TRUE FALSEnewdata <- na.omit(dictator)
mean(newdata$yearly_income)## [1] 9935.755mean(dictator$yearly_income) #not going to work## [1] NAmean(dictator$yearly_income, na.rm=TRUE) # returns ## [1] 9935.755Creating subsets
fem <- subset(dictator, female==1)OLS
OLS is simple regression model
pooling <- lm(giving ~ age+yearly_income+female+in_group, data= dictator)
summary(pooling)##
## Call:
## lm(formula = giving ~ age + yearly_income + female + in_group,
## data = dictator)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11.308 -5.848 -1.036 3.901 20.493
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.868e+00 1.335e+00 4.397 1.76e-05 ***
## age 5.009e-01 3.635e-01 1.378 0.169755
## yearly_income -3.376e-05 3.993e-05 -0.845 0.398832
## female 1.782e-01 1.026e+00 0.174 0.862191
## in_group 3.274e+00 9.788e-01 3.345 0.000978 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.125 on 207 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.06133, Adjusted R-squared: 0.04319
## F-statistic: 3.381 on 4 and 207 DF, p-value: 0.0105Automated Version
#Assign variables
Y <- cbind(dictator$giving)
X <- cbind(dictator$in_group,dictator$age,dictator$yearly_income,dictator$female)
# Pooled OLS estimator
pooling <- lm(Y ~ X, data=dictator)
summary(pooling)##
## Call:
## lm(formula = Y ~ X, data = dictator)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11.308 -5.848 -1.036 3.901 20.493
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.868e+00 1.335e+00 4.397 1.76e-05 ***
## X1 3.274e+00 9.788e-01 3.345 0.000978 ***
## X2 5.009e-01 3.635e-01 1.378 0.169755
## X3 -3.376e-05 3.993e-05 -0.845 0.398832
## X4 1.782e-01 1.026e+00 0.174 0.862191
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.125 on 207 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.06133, Adjusted R-squared: 0.04319
## F-statistic: 3.381 on 4 and 207 DF, p-value: 0.0105Statistics
# Descriptive statistics
summary(Y)## V1
## Min. : 0.000
## 1st Qu.: 3.000
## Median :10.000
## Mean : 8.491
## 3rd Qu.:10.000
## Max. :30.000summary(X)## V1 V2 V3 V4
## Min. :0.0 Min. :1.000 Min. : 540 Min. :0.0000
## 1st Qu.:0.0 1st Qu.:1.000 1st Qu.: 4000 1st Qu.:0.0000
## Median :0.5 Median :3.000 Median : 7100 Median :0.0000
## Mean :0.5 Mean :2.569 Mean : 9936 Mean :0.4128
## 3rd Qu.:1.0 3rd Qu.:4.000 3rd Qu.:10000 3rd Qu.:1.0000
## Max. :1.0 Max. :5.000 Max. :75000 Max. :1.0000
## NA's :6Resources and References
https://sites.google.com/site/econometricsacademy/econometrics-models/panel-data-models
https://www.datamentor.io/r-programming/histogram/ (histogram)