Scatterplots and barcharts

aiib <- read_dta("C:/Users/Paula/Desktop/AIIB-ForResubmission.dta")

aiib %<>% 
  select(ccode, aiibmember:adbnonregionalmember, asiapacific, chinaalignment, usmilitaryalliance)

the_df <- merge(the_df, aiib, by.x = c("cow_code"), by.y = c("ccode"), all.x = TRUE)

russia_dyad <- read.csv("C:/Users/Paula/Desktop/PD_original_datasets/russia_dyad.csv")
russia_dyad$X <- NULL

the_df <- merge(the_df, russia_dyad, by = c("cow_code", "year"), all.x = TRUE)

soviet_iron_curtain_vector <- c("Albania", "Bulgaria", "Czech Republic", 
                                "Poland",  "Kosovo",   "Romania", 
                                "Hungary",  "Slovakia",  "Bosnia and Herzegovina",
                                "Croatia",  "Macedonia", "Montenegro", "Serbia")

soviet_republics_vector <- c("Russia", "Lithuania", "Georgia",
                             "Estonia", "Latvia",  "Ukraine"    ,
                             "Belarus", "Moldova", "Kyrgyzstan",    
                             "Uzbekistan", "Tajikistan", "Armenia"  ,
                             "Azerbaijan", "Turkmenistan", "Kazakhstan")

the_df %<>%
  dplyr::mutate(soviet_iron_curtain = ifelse(country %in% soviet_iron_curtain_vector, 1, 0)) 

the_df %<>%
  dplyr::mutate(soviet_republics = ifelse(country %in% soviet_republics_vector, 1, 0)) 

the_df %<>% mutate(rus_influence = ifelse(country == "Russia", 1, 
                                          ifelse(level_contig_rus == 1, 1, 
                                              ifelse(soviet_republics == 1, 1,
                                                ifelse(soviet_iron_curtain == 1, 1, 0)))))

the_df %>% 
  mutate(budget_pc = budget / pop, na.rm = TRUE) %>%
  mutate(exports_pc = exports_bop / pop, na.rm = TRUE) %>% 
  mutate(total_trade = exports_bop + imports_bop, na.rm = TRUE) %>% 
  mutate(trade_openess = total_trade / gdp_const, na.rm = TRUE) %>% 
  mutate(us_total_trade = us_exports_to_country + us_imports_from_country, na.rm = TRUE) %>% 
  mutate(us_trade_dependence = us_total_trade / balance_trade, na.rm = TRUE) %>% 
  mutate(us_exports_pc = us_exports_to_country / pop, na.rm = TRUE) %>% 
  mutate(muslim_percent = percent_muslim_jitter / pop, na.rm = TRUE) %>% 
  mutate(us_imports_pc = us_imports_from_country / pop, na.rm = TRUE) -> the_df

Cost of living ranking

The main problem

Source: “https://www.numbeo.com/cost-of-living/rankings_by_country.jsp?title=2019”

url <- "https://www.numbeo.com/cost-of-living/rankings_by_country.jsp?title=2019"

# Countries with no INDEX
col_url <- read_html(url)
col_table <- col_url %>% html_table(header = TRUE, fill = TRUE)
col_19 <- col_table[[2]]

col_19$year <- replicate(119, 2019)
col_19$rank <- NULL
col_19 %<>% 
  clean_names()

col_19$cow_code <- countrycode(col_19$country, "country.name", "cown")

col_19 %<>% dplyr::mutate(cow_code = ifelse(country == "Palestine", 6666, 
                                              ifelse(country == "Serbia", 345, 
                                                ifelse(country == "Hong Kong", 997, cow_code))))

names(col_19)

[1] “rank” “country”
[3] “cost_of_living_index” “rent_index”
[5] “cost_of_living_plus_rent_index” “groceries_index”
[7] “restaurant_price_index” “local_purchasing_power_index”
[9] “year” “cow_code”

col_19 %>% 
  arrange(desc(cost_of_living_index)) %>% 
  select(country, cost_of_living = cost_of_living_index) %>% 
  head() %>% 
  kbl() %>%
  kable_paper("striped",
              full_width = F)

country	cost_of_living
Switzerland	121.16
Iceland	101.86
Norway	100.99
Bahamas	92.40
Luxembourg	86.09
Japan	83.33

col_19 %>% 
  arrange(desc(cost_of_living_index)) %>% 
  select(country, cost_of_living = cost_of_living_index) %>% 
  tail() %>% 
  kbl() %>%
  kable_paper("striped",
              full_width = F)

country	cost_of_living
Egypt	26.46
Kosovo (Disputed Territory)	26.18
Venezuela	25.73
India	24.17
Tunisia	23.69
Pakistan	20.40

# df_19 %>% 
#   group_by(country) %>% 
#   mutate(ppp_budget = budget * ppp) %>% 
#   select(country, ppp_budget) %>% 
#   arrange(desc(ppp_budget)) -> table3_mult
# 
# df_19 %>% 
#   group_by(country) %>% 
#   mutate(ppp_budget = budget * ppp) %>% 
#   select(country, raw_budget = budget) %>% 
#   arrange(desc(raw_budget)) -> table4_mult

# kbl(list(table3_mult, table4_mult), digits = 0, 
#     caption = "Arranged By PPP Adjusted Budget LEFT and By PPP Raw Budget RIGHT") %>%
#     kable_paper("striped", full_width = T) 

Adjust to 2019 prices

country <- "United States"
countries_dataframe <- show_countries()

Generating URL to request all 299 results

inflation_dataframe <- retrieve_inflation_data(country, countries_dataframe)

Retrieving inflation data for US Generating URL to request all 61 results

# Provide a World Bank API URL and url_all_results will convert it into one with all results for that indicator
original_url <- "http://api.worldbank.org/v2/country" 

# "http://api.worldbank.org/v2/country?format=json&per_page=304"
url_all_results(original_url)

Generating URL to request all 299 results [1] “http://api.worldbank.org/v2/country?format=json&per_page=299”

the_df$budget_const <- adjust_for_inflation(the_df$budget, 
                                                the_df$year, 
                                                country, 
                                                to_date = 2019,
                                                inflation_dataframe = inflation_dataframe,
                                                countries_dataframe = countries_dataframe)

the_df$budget_pc_const <- adjust_for_inflation(the_df$budget_pc, 
                                              the_df$year, 
                                                   country, 
                                                   to_date = 2019,
                                                   inflation_dataframe = inflation_dataframe,
                                                   countries_dataframe = countries_dataframe)

Price level ratio

Source: https://data.worldbank.org/indicator/PA.NUS.PPPC.RF

Price level ratio is the ratio of a purchasing power parity (PPP) conversion factor to an exchange rate. It provides a measure of the differences in price levels between countries by indicating the number of units of the common currency needed to buy the same volume of the aggregation level in each country.

Indicator source: International Comparison Program, World Bank

library(WDI)
ppp = WDI(indicator='PA.NUS.PPPC.RF', country="all", start=2013, end=2019)
ppp$ppp <- ppp$PA.NUS.PPPC.RF
ppp$PA.NUS.PPPC.RF <- NULL

ppp$cow_code <- countrycode(ppp$iso2c, "iso2c", "cown")

ppp %<>% 
dplyr::mutate(cow_code = ifelse(country == "West Bank and Gaza", 6666, 
                                ifelse(country == "Serbia", 345, 
                                       ifelse(country == "Hong Kong SAR, China", 997, cow_code))))

ppp$country <- NULL

the_df <- merge(the_df, ppp, by = c("cow_code", "year"), all.x = TRUE)

the_df %<>%  
  mutate(ppp_budget = budget / ppp, na.rm = TRUE) %>% 
  mutate(ppp_budget_pc = budget_pc * ppp, na.rm = TRUE) %>% 
  mutate(ppp_budget_const = budget_const / ppp, na.rm = TRUE) %>% 
  mutate(ppp_budget_pc_const = budget_pc_const * ppp, na.rm = TRUE) %>% 
  select(ppp_budget, ppp_budget_pc, ppp_budget_const, ppp_budget_pc_const, everything())

the_df %>%
  filter(year == 2014) %>% 
  filter(country != "Kosovo") %>% 
  filter(country != "Curacao") %>% 
  filter(country != "Vatican City") %>%
  select(country, ppp_budget) %>%
  arrange(desc(ppp_budget)) ->t1

the_df %>%
  filter(country != "Kosovo") %>% 
  filter(country != "Curacao") %>% 
  filter(country != "Vatican City") %>%
  filter(year == 2014) %>% 
  select(country, ppp_budget_pc) %>%
  arrange(desc(ppp_budget_pc)) -> t2

the_df %>%
  filter(country != "Kosovo") %>%
  filter(country != "Curacao") %>% 
  filter(country != "Vatican City") %>% 
  filter(year == 2014) %>% 
  select(country, ppp_budget_const) %>%
  arrange(desc(ppp_budget_const)) -> t3

the_df %>%
  filter(country != "Kosovo") %>% 
  filter(country != "Curacao") %>% 
  filter(country != "Vatican City") %>%
  filter(year == 2014) %>% 
  select(country, ppp_budget_pc_const) %>%
  arrange(desc(ppp_budget_pc_const)) -> t4

the_df %>%
  filter(country != "Kosovo") %>% 
  filter(country != "Curacao") %>% 
  filter(country != "Vatican City") %>%
  filter(year == 2014) %>% 
  select(country, budget) %>%
  arrange(desc(budget)) -> t0

the_df %>%
  filter(country != "Kosovo") %>% 
  filter(country != "Curacao") %>% 
  filter(country != "Vatican City") %>%
  filter(year == 2014) %>% 
  select(country, budget_pc) %>%
  arrange(desc(budget_pc)) -> tpc

kbl(list(t0, t1,  t3, tpc, t2, t4), digits = 4) %>% 
     kable_paper("striped", full_width = FALSE) 

country budget Afghanistan 56507034 Pakistan 36561172 Kenya 19795614 Mozambique 15227740 Zimbabwe 13688543 Iraq 12178606 South Africa 10905073 India 10195170 Ethiopia 9929613 Botswana 9665209 Brazil 9537682 Japan 9176177 China 7760211 Germany 7058232 Nigeria 6708386 Tanzania 6015504 Mexico 5742427 Indonesia 5517627 Russia 5455594 Zambia 4703058 South Korea 4681751 Israel 4474507 France 4355206 Palestinian Territories 4037115 Italy 4011391 Vietnam 3968612 Kazakhstan 3964445 Argentina 3938010 Turkey 3691430 Colombia 3677446 Jordan 3506201 Democratic Republic of the Congo 3411433 Uganda 3302523 Burma 3126713 United Kingdom 3110483 Spain 3085913 Cameroon 3009714 Ukraine 2987964 Egypt 2906309 Canada 2707912 Australia 2648692 Tajikistan 2644280 Peru 2616332 Chile 2597870 Poland 2578556 Philippines 2577410 Venezuela 2534132 Austria 2505317 Kyrgyzstan 2421388 Turkmenistan 2361743 Morocco 2358837 United Arab Emirates 2209363 Saudi Arabia 2143931 Thailand 2086208 Malaysia 2027167 Belgium 2018477 Bangladesh 2011284 Greece 2009268 Bolivia 2008954 Namibia 1979443 Ecuador 1904677 Malawi 1882776 Niger 1747531 Nepal 1744895 Serbia 1720045 Romania 1598707 Cote D’Ivoire 1575511 Czech Republic 1555711 Lebanon 1501240 Guinea 1497955 Bosnia and Herzegovina 1473503 Slovakia 1449542 Georgia 1387092 Hong Kong 1386503 Swaziland 1378799 Netherlands 1366532 Yemen 1365845 Uruguay 1352551 Croatia 1326867 New Zealand 1314910 Hungary 1300689 Senegal 1280760 Panama 1249559 Haiti 1213622 Sweden 1178719 El Salvador 1177991 Uzbekistan 1171380 Guatemala 1168731 Costa Rica 1146747 Singapore 1138221 Ghana 1110674 Portugal 1110465 Dominican Republic 1101621 Azerbaijan 1060545 Finland 1035227 Qatar 1025813 Bulgaria 958440 Tunisia 952028 Mali 949585 Rwanda 942289 Norway 939131 Honduras 937705 Sri Lanka 928094 Denmark 917589 Paraguay 917447 Barbados 878464 Belarus 872016 Angola 866831 Macedonia 850132 Cambodia 807945 Burkina Faso 798255 Kuwait 790326 Estonia 790305 Algeria 789224 Cyprus 788327 Slovenia 780576 Benin 764483 Liberia 760289 Albania 731251 Madagascar 726846 Switzerland 718489 Nicaragua 717722 Bahrain 717495 Lesotho 710854 Latvia 710842 Chad 690727 Armenia 681237 Jamaica 674810 Togo 673389 Lithuania 658067 Sudan 643546 Mauritania 618838 Burundi 593574 Ireland 592969 Trinidad and Tobago 579294 Mongolia 553217 Somalia 537622 Moldova 519919 Laos 519120 Mauritius 489636 Oman 487697 Fiji 484194 Cuba 472517 Papua New Guinea 414550 Montenegro 399569 Djibouti 378363 Eritrea 366500 Sierra Leone 362906 Iceland 348400 Luxembourg 344249 Libya 334681 Gambia, The 297170 Republic of Congo 289381 Equatorial Guinea 262009 Bahamas, The 253473 Brunei 250151 Gabon 246842 South Sudan 224115 Cape Verde 224077 Syria 214051 Suriname 180079 Malta 176495 East Timor 134714 Central African Republic 129296 Belize 122015 Guyana 110596 Guinea-Bissau 76785 Marshall Islands 67305 Samoa 61791 Micronesia 57651 Palau 14204

country ppp_budget Afghanistan 190495681.90 Pakistan 123859038.79 Kenya 45455933.79 India 33903556.16 Ethiopia 26512237.31 Mozambique 25735870.54 Iraq 25481387.90 Zimbabwe 24922160.74 South Africa 21224206.85 Botswana 20249109.36 Indonesia 16241992.12 Tanzania 13102254.37 China 12683156.30 Brazil 12377097.12 Nigeria 11921390.17 Burma 11637278.58 Vietnam 11230228.32 Ukraine 10339819.15 Russia 9970814.04 Mexico 9487656.16 Zambia 9445024.91 Japan 9433755.25 Egypt 9370153.68 Kyrgyzstan 8101423.84 Tajikistan 7910283.60 Uganda 7806212.75 Jordan 7791602.13 Kazakhstan 7653997.54 Turkey 7314318.97 Germany 6918650.56 Palestinian Territories 6636125.63 Argentina 6284244.58 Cameroon 6214755.63 Nepal 6087161.96 Philippines 6061906.91 Bangladesh 6054407.05 Colombia 6030966.33 Democratic Republic of the Congo 5955174.51 South Korea 5654116.38 Malawi 5471705.49 Thailand 5426003.33 Morocco 4915658.63 Saudi Arabia 4883579.15 Poland 4602943.57 Bolivia 4600065.21 Peru 4513002.30 Malaysia 4407066.08 Italy 4087789.12 France 4064877.29 Israel 4062913.23 Chile 4034951.97 Turkmenistan 4001668.89 Serbia 3820449.35 Namibia 3787871.07 United Arab Emirates 3717588.13 Niger 3536300.28 Spain 3511611.50 Ecuador 3498430.01 Guinea 3433679.14 Georgia 3387995.54 Romania 3288200.07 Bosnia and Herzegovina 3160983.35 Cote D’Ivoire 3155614.81 Ghana 3073400.98 Swaziland 3003367.27 Lebanon 2934866.70 Uzbekistan 2894451.13 Sri Lanka 2735461.39 United Kingdom 2706491.39 Senegal 2595800.55 Czech Republic 2542087.48 Haiti 2507754.96 Greece 2478089.21 Canada 2431453.30 Guatemala 2399060.72 El Salvador 2374069.95 Austria 2363972.86 Cambodia 2353530.85 Azerbaijan 2344352.27 Hungary 2337769.89 Tunisia 2309834.65 Slovakia 2250798.00 Dominican Republic 2246141.21 Panama 2235971.40 Rwanda 2162813.04 Croatia 2152422.04 Mali 2144040.23 Bulgaria 2136830.83 Madagascar 2130205.96 Macedonia 2078358.52 Belarus 1987116.55 Australia 1986397.28 Belgium 1901226.62 Honduras 1892616.08 Hong Kong 1884022.82 Algeria 1868265.86 Nicaragua 1833842.40 Albania 1798216.58 Sudan 1781927.47 Paraguay 1717601.34 Armenia 1715279.33 Burkina Faso 1703848.06 Costa Rica 1698614.84 Burundi 1678072.83 Benin 1677310.62 Singapore 1669354.14 Lesotho 1668677.63 Uruguay 1614646.80 Mauritania 1584835.00 Qatar 1578855.79 Laos 1525862.09 Mongolia 1470843.03 Bahrain 1467236.43 Liberia 1456876.09 Portugal 1445910.99 Togo 1395645.06 Moldova 1378680.35 Somalia 1337955.82 Angola 1310933.65 Netherlands 1273491.24 Kuwait 1257036.99 Jamaica 1192797.29 Chad 1135377.07 Estonia 1130553.19 Lithuania 1120612.09 New Zealand 1100161.96 Latvia 1076826.15 Slovenia 995105.40 Gambia, The 991677.21 Fiji 980111.69 Oman 940201.52 Eritrea 928052.58 Sweden 926643.32 Sierra Leone 907720.65 Mauritius 891517.95 Cyprus 872982.44 Finland 860090.18 Trinidad and Tobago 848712.92 Montenegro 831311.05 Barbados 808482.52 Libya 740221.84 Denmark 702710.71 Djibouti 658529.15 Norway 637831.26 Ireland 545685.70 Papua New Guinea 533877.23 Switzerland 513546.95 Brunei 487829.16 Equatorial Guinea 455227.15 Republic of Congo 454485.38 Gabon 392635.20 Cape Verde 358916.28 Suriname 328165.42 East Timor 297425.74 Iceland 293629.53 Luxembourg 293473.48 Bahamas, The 280307.80 South Sudan 253372.40 Malta 226564.37 Guyana 224004.35 Central African Republic 219425.66 Belize 185929.88 Guinea-Bissau 169783.00 Samoa 87377.65 Marshall Islands 72078.27 Micronesia 62353.75 Palau 17035.35 Cuba NA Venezuela NA Syria NA Yemen NA

country ppp_budget_const Afghanistan 205721139.31 Pakistan 133758531.00 Kenya 49089020.78 India 36613313.91 Ethiopia 28631240.41 Mozambique 27792822.15 Iraq 27517999.87 Zimbabwe 26914076.21 South Africa 22920561.61 Botswana 21867528.99 Indonesia 17540141.01 Tanzania 14149458.24 China 13696863.56 Brazil 13366342.46 Nigeria 12874212.91 Burma 12567393.57 Vietnam 12127809.63 Ukraine 11166234.09 Russia 10767736.06 Mexico 10245961.56 Zambia 10199922.99 Japan 10187752.60 Egypt 10119067.64 Kyrgyzstan 8748933.97 Tajikistan 8542516.76 Uganda 8430127.99 Jordan 8414349.61 Kazakhstan 8265746.91 Turkey 7898919.37 Germany 7471626.98 Palestinian Territories 7166521.11 Argentina 6786515.80 Cameroon 6711472.91 Nepal 6573681.25 Philippines 6546407.68 Bangladesh 6538308.40 Colombia 6512994.17 Democratic Republic of the Congo 6431144.64 South Korea 6106024.30 Malawi 5909034.14 Thailand 5859679.21 Morocco 5308544.97 Saudi Arabia 5273901.52 Poland 4970836.01 Bolivia 4967727.60 Peru 4873706.15 Malaysia 4759302.92 Italy 4414507.59 France 4389764.53 Israel 4387643.49 Chile 4357447.42 Turkmenistan 4321504.17 Serbia 4125800.57 Namibia 4090618.46 United Arab Emirates 4014718.12 Niger 3818940.75 Spain 3792278.70 Ecuador 3778043.68 Guinea 3708117.56 Georgia 3658782.68 Romania 3551011.01 Bosnia and Herzegovina 3413626.44 Cote D’Ivoire 3407828.81 Ghana 3319044.00 Swaziland 3243412.82 Lebanon 3169437.31 Uzbekistan 3125791.50 Sri Lanka 2954094.43 United Kingdom 2922808.99 Senegal 2803271.13 Czech Republic 2745265.02 Haiti 2708188.46 Greece 2676151.66 Canada 2625788.35 Guatemala 2590806.79 El Salvador 2563818.62 Austria 2552914.51 Cambodia 2541637.92 Azerbaijan 2531725.73 Hungary 2524617.25 Tunisia 2494449.28 Slovakia 2430694.10 Dominican Republic 2425665.10 Panama 2414682.47 Rwanda 2335676.89 Croatia 2324455.39 Mali 2315403.66 Bulgaria 2307618.04 Madagascar 2300463.67 Macedonia 2244472.30 Belarus 2145937.78 Australia 2145161.02 Belgium 2053183.05 Honduras 2043884.31 Hong Kong 2034604.24 Algeria 2017587.89 Nicaragua 1980413.12 Albania 1941939.89 Sudan 1924348.86 Paraguay 1854881.44 Armenia 1852373.85 Burkina Faso 1840028.92 Costa Rica 1834377.43 Burundi 1812193.60 Benin 1811370.46 Singapore 1802778.06 Lesotho 1802047.47 Uruguay 1743698.21 Mauritania 1711503.69 Qatar 1705046.58 Laos 1647817.34 Mongolia 1588400.85 Bahrain 1584505.99 Liberia 1573317.60 Portugal 1561476.11 Togo 1507192.65 Moldova 1488872.03 Somalia 1444892.58 Angola 1415710.65 Netherlands 1375275.63 Kuwait 1357506.27 Jamaica 1288132.17 Chad 1226122.62 Estonia 1220913.19 Lithuania 1210177.54 New Zealand 1188092.93 Latvia 1162891.99 Slovenia 1074639.66 Gambia, The 1070937.48 Fiji 1058447.58 Oman 1015347.58 Eritrea 1002227.62 Sweden 1000705.72 Sierra Leone 980270.65 Mauritius 962772.95 Cyprus 942755.97 Finland 928833.29 Trinidad and Tobago 916546.70 Montenegro 897753.97 Barbados 873100.86 Libya 799384.42 Denmark 758875.19 Djibouti 711162.41 Norway 688810.22 Ireland 589299.89 Papua New Guinea 576547.62 Switzerland 554592.43 Brunei 526819.13 Equatorial Guinea 491611.39 Republic of Congo 490810.33 Gabon 424016.76 Cape Verde 387602.84 Suriname 354394.19 East Timor 321197.63 Iceland 317098.01 Luxembourg 316929.48 Bahamas, The 302711.54 South Sudan 273623.31 Malta 244672.63 Guyana 241908.00 Central African Republic 236963.36 Belize 200790.42 Guinea-Bissau 183352.99 Samoa 94361.35 Marshall Islands 77839.16 Micronesia 67337.41 Palau 18396.91 Cuba NA Venezuela NA Syria NA Yemen NA

country budget_pc Botswana 4.6276 Barbados 3.0842 Afghanistan 1.6933 Swaziland 1.2592 Marshall Islands 1.1771 Iceland 1.0642 Zimbabwe 1.0075 Palestinian Territories 0.9673 Namibia 0.8707 Palau 0.8059 Cyprus 0.6841 Bahamas, The 0.6839 Montenegro 0.6426 Luxembourg 0.6188 Brunei 0.6105 Estonia 0.6012 Mozambique 0.5793 Fiji 0.5588 Israel 0.5446 Bahrain 0.5370 Micronesia 0.5366 Cape Verde 0.4324 Turkmenistan 0.4321 Trinidad and Tobago 0.4252 Kenya 0.4239 Bosnia and Herzegovina 0.4232 Djibouti 0.4210 Qatar 0.4171 Kyrgyzstan 0.4149 Macedonia 0.4092 Malta 0.4061 Uruguay 0.3978 Jordan 0.3931 Mauritius 0.3883 Slovenia 0.3786 Georgia 0.3729 Latvia 0.3565 Iraq 0.3539 Lesotho 0.3479 Belize 0.3453 Suriname 0.3255 Samoa 0.3215 Tajikistan 0.3204 Panama 0.3203 Croatia 0.3131 Zambia 0.3054 Austria 0.2931 New Zealand 0.2911 Slovakia 0.2675 Albania 0.2531 Serbia 0.2412 United Arab Emirates 0.2398 Lebanon 0.2397 Costa Rica 0.2391 Jamaica 0.2347 Armenia 0.2339 Equatorial Guinea 0.2335 Kazakhstan 0.2293 Lithuania 0.2244 Kuwait 0.2141 Singapore 0.2081 South Africa 0.1999 Hong Kong 0.1918 Finland 0.1895 Mongolia 0.1882 Bolivia 0.1876 Pakistan 0.1872 El Salvador 0.1871 Greece 0.1845 Norway 0.1828 Moldova 0.1820 Belgium 0.1801 Liberia 0.1744 Denmark 0.1626 Mauritania 0.1574 Czech Republic 0.1478 Gambia, The 0.1468 Chile 0.1463 Guyana 0.1449 Paraguay 0.1390 Guinea 0.1343 Cameroon 0.1327 Bulgaria 0.1327 Hungary 0.1318 Gabon 0.1310 Ireland 0.1273 Sweden 0.1216 Oman 0.1211 Tanzania 0.1204 Ecuador 0.1194 Nicaragua 0.1168 Malawi 0.1156 Haiti 0.1150 East Timor 0.1147 Australia 0.1128 Azerbaijan 0.1112 Dominican Republic 0.1084 Portugal 0.1068 Honduras 0.1047 Ethiopia 0.1012 Togo 0.0943 Argentina 0.0923 South Korea 0.0923 Belarus 0.0920 Niger 0.0908 Senegal 0.0904 Uganda 0.0895 Switzerland 0.0877 Germany 0.0872 Peru 0.0869 Tunisia 0.0861 Rwanda 0.0850 Venezuela 0.0843 Netherlands 0.0810 Romania 0.0803 Colombia 0.0783 Laos 0.0782 Canada 0.0764 Guatemala 0.0764 Benin 0.0743 Japan 0.0721 Cote D’Ivoire 0.0696 Saudi Arabia 0.0693 Morocco 0.0690 Malaysia 0.0679 Poland 0.0678 Spain 0.0664 Ukraine 0.0660 Italy 0.0660 France 0.0657 Nepal 0.0648 Republic of Congo 0.0611 Burundi 0.0603 Burma 0.0598 Mali 0.0561 Cambodia 0.0529 Yemen 0.0529 Libya 0.0526 Papua New Guinea 0.0522 Sierra Leone 0.0517 Chad 0.0506 United Kingdom 0.0481 Turkey 0.0478 Mexico 0.0477 Brazil 0.0470 Democratic Republic of the Congo 0.0462 Burkina Faso 0.0454 Guinea-Bissau 0.0454 Sri Lanka 0.0447 Vietnam 0.0433 Cuba 0.0418 Ghana 0.0408 Somalia 0.0401 Uzbekistan 0.0381 Nigeria 0.0380 Russia 0.0379 Angola 0.0322 Egypt 0.0321 Madagascar 0.0308 Thailand 0.0305 Central African Republic 0.0290 Philippines 0.0256 Indonesia 0.0216 South Sudan 0.0212 Algeria 0.0203 Sudan 0.0169 Bangladesh 0.0130 Syria 0.0114 India 0.0079 China 0.0057 Eritrea NA

country ppp_budget_pc Barbados 3.3512 Botswana 2.2088 Iceland 1.2627 Marshall Islands 1.0991 Luxembourg 0.7259 Palau 0.6719 Bahamas, The 0.6184 Cyprus 0.6178 Israel 0.5998 Palestinian Territories 0.5885 Swaziland 0.5781 Zimbabwe 0.5534 Afghanistan 0.5023 Micronesia 0.4961 Namibia 0.4550 Estonia 0.4203 New Zealand 0.3480 Mozambique 0.3428 Uruguay 0.3332 Malta 0.3164 Brunei 0.3130 Austria 0.3107 Montenegro 0.3089 Slovenia 0.2969 Trinidad and Tobago 0.2902 Fiji 0.2761 Qatar 0.2710 Cape Verde 0.2699 Norway 0.2692 Bahrain 0.2626 Turkmenistan 0.2550 Djibouti 0.2419 Latvia 0.2354 Finland 0.2281 Samoa 0.2273 Belize 0.2266 Mauritius 0.2133 Denmark 0.2123 Bosnia and Herzegovina 0.1973 Croatia 0.1930 Belgium 0.1912 Kenya 0.1846 Panama 0.1790 Suriname 0.1786 Jordan 0.1769 Slovakia 0.1723 Iraq 0.1691 Macedonia 0.1674 Costa Rica 0.1614 Sweden 0.1546 Georgia 0.1527 Zambia 0.1521 Australia 0.1504 Greece 0.1496 Lesotho 0.1482 United Arab Emirates 0.1425 Singapore 0.1419 Hong Kong 0.1411 Ireland 0.1383 Kuwait 0.1346 Equatorial Guinea 0.1344 Jamaica 0.1328 Lithuania 0.1318 Kyrgyzstan 0.1240 Switzerland 0.1228 Lebanon 0.1226 Kazakhstan 0.1188 Serbia 0.1086 Tajikistan 0.1071 Albania 0.1029 South Africa 0.1027 Chile 0.0942 Armenia 0.0929 El Salvador 0.0929 Liberia 0.0910 Czech Republic 0.0905 Germany 0.0889 Netherlands 0.0869 Canada 0.0851 Gabon 0.0824 Portugal 0.0820 Bolivia 0.0819 South Korea 0.0764 Paraguay 0.0743 Hungary 0.0733 Guyana 0.0715 Mongolia 0.0708 France 0.0704 Japan 0.0701 Moldova 0.0686 Ecuador 0.0650 Italy 0.0648 Cameroon 0.0643 Oman 0.0628 Mauritania 0.0615 Bulgaria 0.0595 Guinea 0.0586 Spain 0.0583 Argentina 0.0578 Haiti 0.0557 United Kingdom 0.0553 Tanzania 0.0553 Pakistan 0.0553 Dominican Republic 0.0532 East Timor 0.0520 Honduras 0.0519 Peru 0.0504 Azerbaijan 0.0503 Colombia 0.0477 Nicaragua 0.0457 Togo 0.0455 Niger 0.0449 Senegal 0.0446 Gambia, The 0.0440 Papua New Guinea 0.0405 Belarus 0.0404 Malawi 0.0398 Romania 0.0390 Republic of Congo 0.0389 Poland 0.0380 Ethiopia 0.0379 Uganda 0.0379 Guatemala 0.0372 Rwanda 0.0370 Brazil 0.0362 Tunisia 0.0355 Cote D’Ivoire 0.0347 Benin 0.0339 Morocco 0.0331 Malaysia 0.0312 Chad 0.0308 Saudi Arabia 0.0304 Mexico 0.0289 Laos 0.0266 Democratic Republic of the Congo 0.0265 Mali 0.0248 Turkey 0.0241 Libya 0.0238 Nigeria 0.0214 Burundi 0.0213 Angola 0.0213 Burkina Faso 0.0213 Russia 0.0208 Sierra Leone 0.0207 Guinea-Bissau 0.0205 Ukraine 0.0191 South Sudan 0.0188 Nepal 0.0186 Cambodia 0.0182 Central African Republic 0.0171 Somalia 0.0161 Burma 0.0161 Uzbekistan 0.0154 Vietnam 0.0153 Sri Lanka 0.0152 Ghana 0.0147 Thailand 0.0117 Philippines 0.0109 Madagascar 0.0105 Egypt 0.0100 Algeria 0.0086 Indonesia 0.0073 Sudan 0.0061 Bangladesh 0.0043 China 0.0035 India 0.0024 Cuba NA Venezuela NA Eritrea NA Syria NA Yemen NA

country ppp_budget_pc_const Barbados 3.6190 Botswana 2.3854 Iceland 1.3636 Marshall Islands 1.1870 Luxembourg 0.7839 Palau 0.7256 Bahamas, The 0.6678 Cyprus 0.6672 Israel 0.6477 Palestinian Territories 0.6355 Swaziland 0.6243 Zimbabwe 0.5976 Afghanistan 0.5424 Micronesia 0.5357 Namibia 0.4914 Estonia 0.4539 New Zealand 0.3758 Mozambique 0.3702 Uruguay 0.3598 Malta 0.3417 Brunei 0.3381 Austria 0.3355 Montenegro 0.3335 Slovenia 0.3207 Trinidad and Tobago 0.3134 Fiji 0.2981 Qatar 0.2927 Cape Verde 0.2915 Norway 0.2907 Bahrain 0.2836 Turkmenistan 0.2754 Djibouti 0.2612 Latvia 0.2542 Finland 0.2464 Samoa 0.2455 Belize 0.2447 Mauritius 0.2303 Denmark 0.2293 Bosnia and Herzegovina 0.2130 Croatia 0.2084 Belgium 0.2065 Kenya 0.1994 Panama 0.1933 Suriname 0.1929 Jordan 0.1910 Slovakia 0.1860 Iraq 0.1827 Macedonia 0.1807 Costa Rica 0.1743 Sweden 0.1670 Georgia 0.1649 Zambia 0.1642 Australia 0.1625 Greece 0.1615 Lesotho 0.1600 United Arab Emirates 0.1539 Singapore 0.1532 Hong Kong 0.1524 Ireland 0.1494 Kuwait 0.1454 Equatorial Guinea 0.1451 Jamaica 0.1434 Lithuania 0.1423 Kyrgyzstan 0.1339 Switzerland 0.1326 Lebanon 0.1324 Kazakhstan 0.1283 Serbia 0.1173 Tajikistan 0.1157 Albania 0.1112 South Africa 0.1109 Chile 0.1017 Armenia 0.1003 El Salvador 0.1003 Liberia 0.0983 Czech Republic 0.0977 Germany 0.0960 Netherlands 0.0939 Canada 0.0919 Gabon 0.0890 Portugal 0.0885 Bolivia 0.0885 South Korea 0.0825 Paraguay 0.0802 Hungary 0.0792 Guyana 0.0772 Mongolia 0.0764 France 0.0760 Japan 0.0757 Moldova 0.0741 Ecuador 0.0702 Italy 0.0699 Cameroon 0.0694 Oman 0.0678 Mauritania 0.0664 Bulgaria 0.0643 Guinea 0.0633 Spain 0.0630 Argentina 0.0625 Haiti 0.0601 United Kingdom 0.0598 Tanzania 0.0597 Pakistan 0.0597 Dominican Republic 0.0574 East Timor 0.0561 Honduras 0.0560 Peru 0.0544 Azerbaijan 0.0543 Colombia 0.0516 Nicaragua 0.0494 Togo 0.0492 Niger 0.0485 Senegal 0.0481 Gambia, The 0.0475 Papua New Guinea 0.0437 Belarus 0.0436 Malawi 0.0429 Romania 0.0422 Republic of Congo 0.0420 Poland 0.0410 Ethiopia 0.0409 Uganda 0.0409 Guatemala 0.0402 Rwanda 0.0400 Brazil 0.0391 Tunisia 0.0383 Cote D’Ivoire 0.0375 Benin 0.0366 Morocco 0.0358 Malaysia 0.0337 Chad 0.0332 Saudi Arabia 0.0329 Mexico 0.0312 Laos 0.0287 Democratic Republic of the Congo 0.0286 Mali 0.0268 Turkey 0.0261 Libya 0.0257 Nigeria 0.0231 Burundi 0.0230 Angola 0.0230 Burkina Faso 0.0230 Russia 0.0224 Sierra Leone 0.0223 Guinea-Bissau 0.0222 Ukraine 0.0206 South Sudan 0.0203 Nepal 0.0201 Cambodia 0.0196 Central African Republic 0.0184 Somalia 0.0174 Burma 0.0174 Uzbekistan 0.0166 Vietnam 0.0165 Sri Lanka 0.0164 Ghana 0.0159 Thailand 0.0127 Philippines 0.0118 Madagascar 0.0114 Egypt 0.0108 Algeria 0.0092 Indonesia 0.0079 Sudan 0.0066 Bangladesh 0.0047 China 0.0038 India 0.0026 Cuba NA Venezuela NA Eritrea NA Syria NA Yemen NA

library(troopdata)

troops_us <- get_troopdata(startyear = 2013, endyear = 2020)

the_df <- merge(the_df, troops_us, by.x = c("cow_code", "year"), by.y = c("ccode", "year"), all.x = TRUE)

us_base_df <-read.csv("C:/Users/Paula/Desktop/PD_original_datasets/Bases.csv") 
  
us_base_df %>% 
  filter(base == 1) %>%
  group_by(Country.Name) %>% 
  count() %>% 
  arrange(desc(n)) %>% 
  filter(n > 2) %>% 
  kbl() %>%
  kable_paper("striped",
              full_width = F)

Country.Name	n
Japan	42
Germany	40
Korea, South	30
Puerto Rico	19
United Kingdom	16
Italy	14
Afghanistan	9
Kuwait	9
Marshall Islands	6
Oman	6
Turkey	6
Belgium	5
Qatar	5
Bahrain	4
Australia	3
Guam	3
Northern Mariana Islands	3
Romania	3
United Arab Emirates	3

  us_base_df %>% 
  filter(lilypad == 1) %>%
  group_by(Country.Name) %>% 
  count() %>% 
  arrange(desc(n)) %>% 
  filter(n > 2) %>% 
  kbl() %>%
  kable_paper("striped",
              full_width = F)

Country.Name	n
Saudi Arabia	9
Syria	8
Israel	6
Pakistan	6
Philippines	6
Colombia	4
Germany	4
Netherlands	4
Bulgaria	3
Cameroon	3
Peru	3

us_base_df %>% 
  group_by(Country.Name) %>% 
  count() %>% 
  arrange(desc(n)) %>% 
  filter(n > 5) %>% 
  kbl() %>%
  kable_paper("striped",
              full_width = F)

Country.Name	n
Germany	44
Japan	42
Korea, South	32
Puerto Rico	19
United Kingdom	16
Italy	15
Syria	10
Afghanistan	9
Honduras	9
Kuwait	9
Saudi Arabia	9
Belize	8
Guatemala	7
Belgium	6
Israel	6
Marshall Islands	6
Netherlands	6
Oman	6
Pakistan	6
Panama	6
Philippines	6
Turkey	6

war_on_terror <- c("Afghanistan", "Yemen", "Syria", "Iraq", "Pakistan")

 the_df %<>%
   dplyr::mutate(war_on_terror = ifelse(country %in% war_on_terror, 1, 0)) 

Drone attacks

# drone_wars <- read.csv("C:/Users/Paula/Desktop/drone_war.csv")

# substrRight <- function(x, n){
#   substr(x, nchar(x)-n+1, nchar(x)) }
 
# drone_wars$year <- as.numeric(substrRight(drone_wars$Date..MM.DD.YYYY., 4))
 
# drone_wars %<>% 
#   mutate(Country = ifelse(grepl('Afghanistan', Country), 'Afghanistan', as.character(Country)))

# drone_wars %>%
#   clean_names() %>% 
#   group_by(country) %>%
#   summarise(sum_drone = n()) %>% 
#   arrange(desc(sum_drone)) %>% 
#   ggplot(aes(x = reorder(country, sum_drone),  
#              y = sum_drone, 
#              fill = as.factor(country))) + 
#   geom_bar(stat = "identity") + 
#   coord_flip() + 
#   scale_fill_manual(values = c("#9b2226","#0a9396","#94d2bd","#ee9b00"), 
#                     name = NULL) +
#   theme(axis.text.y = element_text(size = 10),
#         axis.title.y = element_blank(), 
#         legend.position = "bottom") + 
#   xlab("country") +
#   ylab("Total drone strikes") +
#   ggthemes::theme_pander() 

# drone_wars %>%
#   clean_names() %>%
#   group_by(country, year) %>%
#   summarise(sum_drone = n()) -> drone_sum

# drone_sum$cow_code <- countrycode(drone_sum$country, "country.name", "cown")
# 
# the_df <- merge(the_df, drone_sum, by = c("cow_code", "year"), all.x = TRUE)
# the_df$sum_drone[is.na(the_df$sum_drone)] <- 0

# the_df %>% 
#   select(country, 
#          year,
#          sum_drone.x) %>% 
#   arrange(desc(sum_drone))

# the_df %>%
#   mutate(drones_binary = ifelse(sum_drone > 0, 1, 0)) %>% 
#   mutate(drones_binary = as.factor(drones_binary)) %>% 
#   group_by(country.x) %>% 
#   # filter(country.x == "Afghanistan" | country.x  == "Somalia" | country.x  == "Yemen" | country.x  == "Pakistan" ) %>% 
#   ggplot(aes(budget)) +
#   # geom_smooth(method = "lm", aes(color = as.factor(region_6)), se = FALSE) + 
#   geom_histogram() +
#   # scale_shape_manual(values = c(15,16,17,18,19,10),
#   #                    name = NULL) +
#   facet_wrap(~drones_binary) +
#   ggtitle("Drone attacks and PD spending") +
#   ylab("Logged PD budget per capita") +
#   theme(legend.position = "left") + 
#   ggthemes::theme_pander()

the_df %>% 
  group_by(president, cow_code) %>% 
  
  mutate(pres_pd_budget_pc = sum(budget_pc_const, na.rm = TRUE)) %>% 
  mutate(pres_pd_budget = sum(budget_const, na.rm = TRUE)) %>% 
  
  mutate(pres_avg_pd_budget_pc = mean(budget_pc_const, na.rm = TRUE)) %>% 
  mutate(pres_avg_pd_budget = mean(budget_const, na.rm = TRUE)) %>% 
  
  mutate(pres_ppp_budget = sum(ppp_budget, na.rm = TRUE)) %>% 
  mutate(pres_ppp_budget_pc = sum(ppp_budget_pc, na.rm = TRUE)) %>% 
  
  mutate(pres_ppp_budget_const = sum(ppp_budget_const, na.rm = TRUE)) %>% 
  mutate(pres_ppp_budget_pc_const = sum(ppp_budget_pc_const, na.rm = TRUE)) %>% 

  mutate(pres_avg_polity = mean(polity_index, na.rm = TRUE)) %>%
  mutate(pres_avg_elect = mean(electoral_demo, na.rm = TRUE)) %>%

  mutate(pres_avg_gdp = mean(gdp_const, na.rm = TRUE)) %>% 
  mutate(pres_avg_gdp_pc = mean(gdp_pc_const, na.rm = TRUE)) %>% 

  mutate(pres_avg_pop = mean(pop, na.rm = TRUE)) %>%  
  mutate(pres_avg_un_dist = mean(ideal_point_distance, na.rm = TRUE)) %>% 
  
  mutate(pres_avg_pol_rights = mean(pol_right_fh, na.rm = TRUE)) %>% 
  mutate(pres_avg_civ_lib = mean(civ_lib_fh, na.rm = TRUE)) %>%  

  mutate(pres_avg_mil_exp = mean(mil_exp_gdp, na.rm = TRUE)) %>% 
  mutate(pres_avg_trade_dep_us = mean(us_trade_dependence, na.rm = TRUE)) %>%  
  
  mutate(pres_avg_us_exp = mean(us_exports_pc, na.rm = TRUE)) %>%  
  mutate(pres_sum_us_exp = sum(us_exports_pc, na.rm = TRUE)) %>%  

  mutate(pres_avg_us_imp = mean(us_imports_pc, na.rm = TRUE)) %>% 
  mutate(pres_sum_us_imp = sum(us_imports_pc, na.rm = TRUE)) %>% 

  mutate(pres_avg_trade_open = mean(trade_openess, na.rm = TRUE)) %>% 
  mutate(pres_avg_ethno_frac = mean(ethno_frac, na.rm = TRUE)) %>%  
 
  mutate(pres_avg_mus_perc = mean(muslim_percent, na.rm = TRUE)) %>%
  
  mutate(pres_avg_us_troops = mean(troops, na.rm = TRUE)) %>%  
  mutate(pres_sum_us_troops = sum(troops, na.rm = TRUE)) %>%  

  mutate(pres_avg_suicide = mean(sum_suicides, na.rm = TRUE)) %>%  
  mutate(pres_sum_suicide = sum(sum_suicides, na.rm = TRUE)) %>%  

  mutate(pres_avg_cso_repress = mean(cso_repress, na.rm = TRUE)) %>% 
  mutate(pres_avg_mountain = mean(mountainous, na.rm = TRUE))  %>% 
  
  distinct(pres_pd_budget_pc, .keep_all = TRUE) %>% 
  filter(!is.na(president)) %>% 
  select(president, 
         year, 
         country, 
         region_6,
         pres_ppp_budget,
         pres_ppp_budget_pc,
         pres_ppp_budget_const,
         pres_ppp_budget_pc_const,
         pres_avg_pd_budget_pc,
         pres_avg_pd_budget,
         pres_pd_budget_pc,
         pres_pd_budget,
         pres_avg_polity,
         pres_avg_elect,
         pres_avg_us_troops,
         pres_sum_us_troops,
         pres_avg_pol_rights,
         pres_avg_civ_lib,
         pres_avg_gdp,
         pres_avg_gdp_pc,
         pres_avg_pop,
         pres_avg_mil_exp,
         pres_avg_un_dist,
         pres_avg_trade_dep_us,
         pres_avg_us_exp,
         pres_sum_us_exp,
         pres_avg_us_imp,
         pres_sum_us_imp,
         pres_avg_trade_open,
         pres_avg_ethno_frac,
         pres_avg_mus_perc,
         pres_avg_cso_repress,
         pres_avg_mountain,
         defense_pact_us,
         pres_avg_suicide,
         pres_sum_suicide,
         dist_moscow = dist_soto_moscow,
         dist_dc = dist_to_wash_dc,
         dist_beijing = dist_to_beijing)  %>% 
    ungroup() -> pd_pres

pooling_model1 <-lm(log(pres_ppp_budget + 1) ~ 
               log(pres_avg_gdp_pc) +
               log(pres_avg_pop) +
               pres_avg_mus_perc +
               log(pres_avg_us_exp + 1) +
               # pres_avg_un_dist +
               log(pres_sum_suicide + 1) +
               pres_avg_elect +
               # I(pres_avg_elect^2) +
               log(pres_sum_us_troops + 1) +
               # as.factor(region_6) +
               as.factor(president),
               data = pd_pres)


pooling_model2 <-lm(log(pres_ppp_budget_pc + 1) ~ 
               log(pres_avg_gdp_pc) +
               log(pres_avg_pop) +
               pres_avg_mus_perc +
               log(pres_avg_us_exp + 1) +
               # pres_avg_un_dist +
               log(pres_sum_suicide + 1) +
               pres_avg_elect +
               # I(pres_avg_elect^2) +
               log(pres_sum_us_troops + 1) +
               # as.factor(region_6) +
               as.factor(president),
               data = pd_pres)


stargazer(pooling_model1, pooling_model2,
          type = "html")

	Dependent variable:
	log(pres_ppp_budget + 1)	log(pres_ppp_budget_pc + 1)
	(1)	(2)
log(pres_avg_gdp_pc)	-0.210	0.057***
	(0.149)	(0.018)
log(pres_avg_pop)	0.460***	-0.150***
	(0.095)	(0.012)
pres_avg_mus_perc	0.910**	-0.020
	(0.435)	(0.053)
log(pres_avg_us_exp + 1)	0.067	0.007
	(0.107)	(0.013)
log(pres_sum_suicide + 1)	0.068	0.052***
	(0.115)	(0.014)
pres_avg_elect	1.491**	0.123*
	(0.588)	(0.072)
log(pres_sum_us_troops + 1)	0.025	0.004
	(0.061)	(0.007)
as.factor(president)Trump	-0.599**	-0.180***
	(0.238)	(0.029)
Constant	9.198***	2.235***
	(1.864)	(0.229)
Observations	299	299
R2	0.173	0.557
Adjusted R2	0.150	0.545
Residual Std. Error (df = 290)	2.035	0.250
F Statistic (df = 8; 290)	7.588***	45.545***
Note:	p<0.1; p<0.05; p<0.01

pd_pres %>% 
   filter(pres_avg_un_dist < 2.8) -> high_un
 
pd_pres %>% 
   filter(pres_avg_un_dist >= 2.8) -> low_un



high_pc <-lm(log(pres_ppp_budget_pc + 1) ~ 
               log(pres_avg_gdp_pc) +
               log(pres_avg_pop) +
               pres_avg_mus_perc +
               log(pres_avg_us_exp + 1) +
               # pres_avg_un_dist +
               log(pres_sum_suicide + 1) +
               pres_avg_elect +
                # I(pres_avg_elect^2) +
               log(pres_sum_us_troops + 1) +
               # (region_6) +
               as.factor(president),
               data = high_un)


low_pc <-lm(log(pres_ppp_budget_pc + 1) ~ 
               log(pres_avg_gdp_pc) +
               log(pres_avg_pop) +
               pres_avg_mus_perc +
               log(pres_avg_us_exp + 1) +
               log(pres_sum_suicide + 1) +
               pres_avg_elect +
                # I(pres_avg_elect^2) +
               log(pres_sum_us_troops + 1) +
               # as.factor(region_6) +
               as.factor(president),
               data = low_un)



high_total <-lm(log(pres_ppp_budget + 1) ~ 
               log(pres_avg_gdp_pc) +
               log(pres_avg_pop) +
               pres_avg_mus_perc +
               log(pres_avg_us_exp + 1) +
               # pres_avg_un_dist +
               log(pres_sum_suicide + 1) +
               pres_avg_elect +
                # I(pres_avg_elect^2) +
               log(pres_sum_us_troops + 1) +
               # (region_6) +
               as.factor(president),
               data = high_un)


low_total <-lm(log(pres_ppp_budget + 1) ~ 
               log(pres_avg_gdp_pc) +
               log(pres_avg_pop) +
               pres_avg_mus_perc +
               log(pres_avg_us_exp + 1) +
               log(pres_sum_suicide + 1) +
               pres_avg_elect +
                # I(pres_avg_elect^2) +
               log(pres_sum_us_troops + 1) +
               # as.factor(region_6) +
               as.factor(president),
               data = low_un)


stargazer(high_total, low_total, high_pc, low_pc, 
          # column.labels = c("High_total", "Low_total", "High PC", "Low PC"),
          type = "html")

	Dependent variable:
	log(pres_ppp_budget + 1)		log(pres_ppp_budget_pc + 1)
	(1)	(2)	(3)	(4)
log(pres_avg_gdp_pc)	0.023	-0.212	0.088***	0.066**
	(0.100)	(0.286)	(0.033)	(0.029)
log(pres_avg_pop)	0.484***	0.496***	-0.182***	-0.130***
	(0.065)	(0.141)	(0.022)	(0.014)
pres_avg_mus_perc	0.590	1.115*	0.257**	-0.099
	(0.384)	(0.597)	(0.128)	(0.061)
log(pres_avg_us_exp + 1)	-0.135**	0.121	0.023	-0.006
	(0.055)	(0.193)	(0.018)	(0.020)
log(pres_sum_suicide + 1)	-0.142	0.031	0.018	0.044***
	(0.103)	(0.161)	(0.034)	(0.016)
pres_avg_elect	-1.177*	2.052**	-0.084	0.193**
	(0.688)	(0.948)	(0.229)	(0.097)
log(pres_sum_us_troops + 1)	0.018	0.046	-0.005	0.028**
	(0.034)	(0.107)	(0.011)	(0.011)
as.factor(president)Trump	-0.437***	-0.719*	-0.177***	-0.179***
	(0.123)	(0.376)	(0.041)	(0.038)
Constant	9.745***	8.030**	2.559***	1.798***
	(1.180)	(3.137)	(0.394)	(0.320)
Observations	113	185	113	185
R2	0.645	0.156	0.689	0.512
Adjusted R2	0.618	0.118	0.665	0.490
Residual Std. Error	0.644 (df = 104)	2.526 (df = 176)	0.215 (df = 104)	0.257 (df = 176)
F Statistic	23.650*** (df = 8; 104)	4.064*** (df = 8; 176)	28.834*** (df = 8; 104)	23.080*** (df = 8; 176)
Note:	p<0.1; p<0.05; p<0.01

dv <- "log(budget + 1)"

ivs <- c("electoral_demo",
         "log(gdp_pc_const)",
         "log(pop)",
         "muslim_percent"
         )

form_1 <- as.formula(paste(dv, paste(ivs, collapse = " + "), sep = " ~ "))

the_df %>% 
   filter(ideal_point_distance < 2.7) -> high_df
 
the_df %>% 
   filter(ideal_point_distance >= 2.7) -> low_df

pooled <- plm(form_1, data = high_df, model = "pooling")

fixed_ind <- plm(form_1, data = high_df, model = "within", effect = "individual")

fixed_time <- plm(form_1, data = high_df, model = "within", effect = "time")

fixed_two <- plm(form_1, data = high_df, model = "within", effect = "twoways")

rand_ind <- plm(form_1, data = high_df, model = "random", effect = "individual")

rand_time <- plm(form_1, data = high_df, model = "random", effect = "time")

rand_two <- plm(form_1, data = high_df, model = "random", effect = "twoways")

Hausman Test

When we run the Hausman test with phtest() command, we see the p-value is is 0.8.

It is not less that 0.05 so we can look at random effects model.

phtest(fixed_time, rand_time)

Hausman Test

data: form_1 chisq = 0.1681, df = 4, p-value = 0.9967 alternative hypothesis: one model is inconsistent

Regression output

stargazer(rand_ind, 
          rand_time, 
          rand_two, 
          column.labels = c(
            # "Fixed Ind", "Fixed Time", "Fixed Two",
                            "Rand Ind", "Rand Time", "Rand Two"), 
          type = "html")

	Dependent variable:
	log(budget + 1)
	Rand Ind	Rand Time	Rand Two
	(1)	(2)	(3)
electoral_demo	0.909*	-0.221	0.163
	(0.480)	(0.294)	(1.460)
log(gdp_pc_const)	-0.002	0.052	0.113
	(0.072)	(0.042)	(0.239)
log(pop)	0.479***	0.479***	0.468***
	(0.049)	(0.021)	(0.172)
muslim_percent	0.984**	0.558***	0.909
	(0.399)	(0.172)	(1.408)
Constant	5.881***	6.260***	5.501*
	(0.913)	(0.422)	(3.297)
Observations	353	353	353
R2	0.785	0.639	0.559
Adjusted R2	0.783	0.635	0.554
F Statistic	102.985***	610.171***	8.258*
Note:	p<0.1; p<0.05; p<0.01

Correct for heteroskedasticity with robust standard errors

stargazer(
# coeftest(fixed_ind, vcov = vcovHC, type = "HC1"),
# coeftest(fixed_time, vcov = vcovHC, type = "HC1"),
# coeftest(fixed_two, vcov = vcovHC, type = "HC1"),
coeftest(rand_ind, vcov = vcovHC, type = "HC1"),
coeftest(rand_time, vcov = vcovHC, type = "HC1"),
coeftest(rand_two, vcov = vcovHC, type = "HC1"),
          column.labels = c(
            # "Fixed Ind", "Fixed Time", "Fixed Two",
                            "Rand Ind", "Rand Time", "Rand Two"), 
          type = "html")

	Dependent variable:
	Rand Ind	Rand Time	Rand Two
	(1)	(2)	(3)
electoral_demo	0.909	-0.221	0.163
	(0.782)	(0.670)	(0.812)
log(gdp_pc_const)	-0.002	0.052	0.113
	(0.112)	(0.105)	(0.115)
log(pop)	0.479***	0.479***	0.468***
	(0.044)	(0.041)	(0.044)
muslim_percent	0.984***	0.558	0.909*
	(0.375)	(0.455)	(0.470)
Constant	5.881***	6.260***	5.501***
	(1.054)	(1.108)	(1.049)
Note:	p<0.1; p<0.05; p<0.01

Lagrange Multiplier Test

Time effects (Breusch-Pagan)

We look at the Lagrange Multiplier test to see if there are time-effects in the model.

If the p-value < 0.05 then use time-fixed effects.

In our model, the , p-value is far below 0.05 so we can support the alternative hypothesis that there are time effects in the model

plmtest(pooled, c("time"), type=("bp"))

Lagrange Multiplier Test - time effects (Breusch-Pagan) for unbalanced
panels

data: form_1 chisq = 330.26, df = 1, p-value < 2.2e-16 alternative hypothesis: significant effects

Test of individual and/or time effects

We can use the pFtest() to also look at whether we use individual or time effects, based on the comparison of the within and the pooling model.

pFtest(fixed_time, pooled)

F test for time effects

data: form_1 F = 16.092, df1 = 6, df2 = 342, p-value = 2.566e-16 alternative hypothesis: significant effects

stargazer(rand_time, coeftest(rand_time, vcov = vcovHC, type = "HC1"),
          column.labels = c("Random Model (Time Effects) ||", " Rand Time Robust Std. Error"), 
          type = "html")

	Dependent variable:
	log(budget + 1)
	panel	coefficient
	linear	test
	Random Model (Time Effects) ||	Rand Time Robust Std. Error
	(1)	(2)
electoral_demo	-0.221	-0.221
	(0.294)	(0.670)
log(gdp_pc_const)	0.052	0.052
	(0.042)	(0.105)
log(pop)	0.479***	0.479***
	(0.021)	(0.041)
muslim_percent	0.558***	0.558
	(0.172)	(0.455)
Constant	6.260***	6.260***
	(0.422)	(1.108)
Observations	353
R2	0.639
Adjusted R2	0.635
F Statistic	610.171***
Note:	p<0.1; p<0.05; p<0.01