data project update
Jingshu Zhao
11/7/2020
##Data ##For Suraj: Please add in data collection background and introduction.
#check countries selected in the data
length(unique(main$Country))## [1] 20#combine year month column,modify column names
main$Covid_share_pop_num = with(main,round(main$`Mid Month Covid Cummulative`/main$`Population (2019)`,4))
main$Date = as.yearmon(paste(main$Year,main$Month, sep = "-"))
colnames(main) <- c("Country","Year","Month","PMI","Money_supply","CPI","Share_Price_Index","unemployment_rate","Population","covid_cummulative","Covid_share_pop_PCT","Period","StringencyIndex","GovernmentResponseIndex","EconomicSupportIndex","PMI_PCT","Money_Supply_PCT","CPI_PCT","Share_Price_Index_PCT","unemployment_rate_pct","Covid_share_pop_num","Date")
main <- transform(main, Date = as.Date(Date, frac = 1))
main## Country Year Month PMI Money_supply CPI Share_Price_Index
## 1: Belgium 2019 9 NA 565.7 108.44 94.96
## 2: Belgium 2019 10 NA 567.4 108.83 94.71
## 3: Belgium 2019 11 NA 570.3 108.90 95.44
## 4: Belgium 2019 12 NA 567.7 109.04 95.74
## 5: Belgium 2020 1 NA 570.6 109.69 96.22
## ---
## 174: USA 2020 5 37.0 17779.1 256.39 105.66
## 175: USA 2020 6 47.9 18118.9 257.80 113.17
## 176: USA 2020 7 50.3 18278.8 259.10 115.12
## 177: USA 2020 8 54.4 18369.1 259.92 120.64
## 178: USA 2020 9 54.3 18612.9 260.28 119.70
## unemployment_rate Population covid_cummulative Covid_share_pop_PCT
## 1: 5.3 11480000 NA 0.00%
## 2: 5.2 11480000 NA 0.00%
## 3: 5.1 11480000 NA 0.00%
## 4: 5.2 11480000 NA 0.00%
## 5: 5.2 11480000 NA 0.00%
## ---
## 174: 13.3 328240000 1382362 0.42%
## 175: 11.1 328240000 2057838 0.63%
## 176: 10.2 328240000 3344783 1.02%
## 177: 8.4 328240000 5203206 1.59%
## 178: 7.9 328240000 6462135 1.97%
## Period StringencyIndex GovernmentResponseIndex EconomicSupportIndex
## 1: Pre COVID 0 0 0
## 2: Pre COVID 0 0 0
## 3: Pre COVID 0 0 0
## 4: Pre COVID 0 0 0
## 5: Pre COVID 0 0 0
## ---
## 174: Post COVID 73 71 63
## 175: Post COVID 69 68 63
## 176: Post COVID 69 70 63
## 177: Post COVID 67 69 63
## 178: Post COVID 63 66 63
## PMI_PCT Money_Supply_PCT CPI_PCT Share_Price_Index_PCT
## 1: 0.46% -0.46% 4.10%
## 2: 0.30% 0.36% -0.26%
## 3: 0.51% 0.06% 0.77%
## 4: -0.46% 0.13% 0.31%
## 5: 0.51% 0.60% 0.50%
## ---
## 174: 37.04% 3.89% 0.00% 3.79%
## 175: 29.46% 1.91% 0.55% 7.11%
## 176: 5.01% 0.88% 0.50% 1.72%
## 177: 8.15% 0.49% 0.32% 4.79%
## 178: -0.18% 1.33% 0.14% -0.78%
## unemployment_rate_pct Covid_share_pop_num Date
## 1: -0.10% NA 2019-09-30
## 2: -0.10% NA 2019-10-31
## 3: -0.10% NA 2019-11-30
## 4: 0.10% NA 2019-12-31
## 5: 0.00% NA 2020-01-31
## ---
## 174: -1.40% 0.0042 2020-05-31
## 175: -2.20% 0.0063 2020-06-30
## 176: -0.90% 0.0102 2020-07-31
## 177: -1.80% 0.0159 2020-08-31
## 178: -0.50% 0.0197 2020-09-30Rank by max cumulative case and then by max Covid_share_pop_num
main[is.na(main)] <- 0
rankbycase = main %>% group_by(Country) %>%
summarise_at(vars(covid_cummulative),max) %>%
arrange(desc(covid_cummulative))
rankbycase## # A tibble: 20 x 2
## Country covid_cummulative
## <chr> <dbl>
## 1 USA 6462135
## 2 India 4930236
## 3 Brazil 4330455
## 4 Russia 1073849
## 5 Colombia 716319
## 6 Spain 615384
## 7 South Africa 579140
## 8 Mexico 505751
## 9 Chile 436433
## 10 United Kingdom 371129
## 11 France 366980
## 12 Turkey 292878
## 13 Italy 288761
## 14 Philippines 265888
## 15 Germany 261762
## 16 Belgium 96934
## 17 Israel 90314
## 18 Netherlands 83321
## 19 Poland 74529
## 20 Czech Republic 37222rankbyshare = main %>% group_by(Country) %>%
summarise_at(vars(Covid_share_pop_num),max) %>%
arrange(desc(Covid_share_pop_num))
rankbyshare## # A tibble: 20 x 2
## Country Covid_share_pop_num
## <chr> <dbl>
## 1 Chile 0.023
## 2 Brazil 0.0205
## 3 USA 0.0197
## 4 Colombia 0.0142
## 5 Spain 0.0131
## 6 Israel 0.01
## 7 South Africa 0.0099
## 8 Belgium 0.0084
## 9 Russia 0.0074
## 10 United Kingdom 0.0056
## 11 France 0.0055
## 12 Italy 0.00480
## 13 Netherlands 0.00480
## 14 Mexico 0.004
## 15 India 0.0036
## 16 Czech Republic 0.0035
## 17 Turkey 0.0035
## 18 Germany 0.0031
## 19 Philippines 0.0025
## 20 Poland 0.002##Check the general trend for pre_covid/post_covid start time cross all 20 countries.
## Scale for 'colour' is already present. Adding another scale for 'colour',
## which will replace the existing scale.## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Blues is 9
## Returning the palette you asked for with that many colors## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.##Check CPI pre_covid/post_covid across countries
## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.##Check Share_Price_Index pre_covid/post_covid across countries
##Check unemployment rate pre_covid/post_covid across countries
##Check striengency index applied pre_covid/post_covid across countries
##Check GovernmentResponseIndex index applied pre_covid/post_covid across countries ##Check EconomicSupportIndex index applied pre_covid/post_covid across countries #check correlationmain[is.na(main)] <- 0
submain = as.data.frame(c(main[,4:8],main[,13:15]))
corrplot(cor(submain), method="circle")
##US Hotelling T square NOTE: drop Strigency Index, government response index, and economic support index since high correlation.
main_test = main %>% filter(Period != "COVID Month")
US = subset(main_test, Country %in% "USA")
US ## Country Year Month PMI Money_supply CPI Share_Price_Index
## 148 USA 2019 11 52.0 15270.4 257.21 125.89
## 149 USA 2019 12 52.7 15422.8 256.97 128.52
## 150 USA 2020 1 53.3 15405.2 257.97 130.91
## 151 USA 2020 2 49.6 15392.7 258.68 128.69
## 152 USA 2020 3 40.9 16066.5 258.12 100.46
## 153 USA 2020 5 37.0 17779.1 256.39 105.66
## 154 USA 2020 6 47.9 18118.9 257.80 113.17
## 155 USA 2020 7 50.3 18278.8 259.10 115.12
## 156 USA 2020 8 54.4 18369.1 259.92 120.64
## 157 USA 2020 9 54.3 18612.9 260.28 119.70
## unemployment_rate Population covid_cummulative Covid_share_pop_PCT
## 148 3.5 328240000 0 0.00%
## 149 3.5 328240000 0 0.00%
## 150 3.6 328240000 0 0.00%
## 151 3.5 328240000 19 0.00%
## 152 4.4 328240000 1718 0.00%
## 153 13.3 328240000 1382362 0.42%
## 154 11.1 328240000 2057838 0.63%
## 155 10.2 328240000 3344783 1.02%
## 156 8.4 328240000 5203206 1.59%
## 157 7.9 328240000 6462135 1.97%
## Period StringencyIndex GovernmentResponseIndex EconomicSupportIndex
## 148 Pre COVID 0 0 0
## 149 Pre COVID 0 0 0
## 150 Pre COVID 0 0 0
## 151 Pre COVID 6 7 0
## 152 Pre COVID 41 37 0
## 153 Post COVID 73 71 63
## 154 Post COVID 69 68 63
## 155 Post COVID 69 70 63
## 156 Post COVID 67 69 63
## 157 Post COVID 63 66 63
## PMI_PCT Money_Supply_PCT CPI_PCT Share_Price_Index_PCT
## 148 2.16% 0.97% -0.05% 3.74%
## 149 1.35% 1.00% -0.09% 2.09%
## 150 1.14% -0.11% 0.39% 1.86%
## 151 -6.94% -0.08% 0.28% -1.70%
## 152 -17.54% 4.38% -0.22% -21.94%
## 153 37.04% 3.89% 0.00% 3.79%
## 154 29.46% 1.91% 0.55% 7.11%
## 155 5.01% 0.88% 0.50% 1.72%
## 156 8.15% 0.49% 0.32% 4.79%
## 157 -0.18% 1.33% 0.14% -0.78%
## unemployment_rate_pct Covid_share_pop_num Date
## 148 -0.10% 0.0000 2019-11-30
## 149 0.00% 0.0000 2019-12-31
## 150 0.10% 0.0000 2020-01-31
## 151 -0.10% 0.0000 2020-02-29
## 152 0.90% 0.0000 2020-03-31
## 153 -1.40% 0.0042 2020-05-31
## 154 -2.20% 0.0063 2020-06-30
## 155 -0.90% 0.0102 2020-07-31
## 156 -1.80% 0.0159 2020-08-31
## 157 -0.50% 0.0197 2020-09-30m1 = with(US, HotellingsT2(cbind( PMI,Money_supply,CPI,Share_Price_Index,unemployment_rate) ~ Period))
m1##
## Hotelling's two sample T2-test
##
## data: cbind(PMI, Money_supply, CPI, Share_Price_Index, unemployment_rate) by Period
## T.2 = 475.47, df1 = 5, df2 = 4, p-value = 1.232e-05
## alternative hypothesis: true location difference is not equal to c(0,0,0,0,0)##Mancova
mancova(data = US,
deps = vars(PMI,Money_supply,CPI,Share_Price_Index,unemployment_rate), factors = Period)## Warning in log(unlist(lapply(mats, det))): NaNs produced##
## MANCOVA
##
## Multivariate Tests
## --------------------------------------------------------------------------------------
## value F df1 df2 p
## --------------------------------------------------------------------------------------
## Period Pillai's Trace 0.9983203 475.4729 5 4 0.0000123
## Wilks' Lambda 0.001679709 475.4729 5 4 0.0000123
## Hotelling's Trace 594.3411 475.4729 5 4 0.0000123
## Roy's Largest Root 594.3411 475.4729 5 4 0.0000123
## --------------------------------------------------------------------------------------
##
##
## Univariate Tests
## --------------------------------------------------------------------------------------------------------
## Dependent Variable Sum of Squares df Mean Square F p
## --------------------------------------------------------------------------------------------------------
## Period PMI 2.116000 1 2.116000 0.05485276 0.8207071
## Money_supply 1.849926e+7 1 1.849926e+7 188.90866614 0.0000008
## CPI 2.061160 1 2.061160 1.34792546 0.2791100
## Share_Price_Index 161.443240 1 161.443240 1.64285419 0.2358315
## unemployment_rate 104.976000 1 104.976000 42.91741619 0.0001783
## Residuals PMI 308.608000 8 38.576000
## Money_supply 783416.220000 8 97927.027500
## CPI 12.233080 8 1.529135
## Share_Price_Index 786.159800 8 98.269975
## unemployment_rate 19.568000 8 2.446000
## --------------------------------------------------------------------------------------------------------Brazil
main_test = main %>% filter(Period != "COVID Month")
BR = subset(main_test, Country %in% "Brazil")
BR ## Country Year Month PMI Money_supply CPI Share_Price_Index
## 13 Brazil 2020 1 52.2 3032.1 5331.42 234.74
## 14 Brazil 2020 2 50.9 3043.0 5344.75 227.52
## 15 Brazil 2020 3 37.6 3209.5 5348.49 163.77
## 16 Brazil 2020 4 26.5 3392.9 5331.91 156.00
## 17 Brazil 2020 6 40.5 3633.6 5325.46 189.76
## 18 Brazil 2020 7 47.3 3708.1 5344.63 203.61
## 19 Brazil 2020 8 53.9 3745.7 5357.46 204.33
## 20 Brazil 2020 9 53.6 3818.6 5391.75 198.18
## unemployment_rate Population covid_cummulative Covid_share_pop_PCT
## 13 11.2 211050000 0 0.00%
## 14 11.6 211050000 0 0.00%
## 15 12.2 211050000 125 0.00%
## 16 12.6 211050000 23430 0.01%
## 17 13.3 211050000 850514 0.40%
## 18 13.8 211050000 1884967 0.89%
## 19 0.0 211050000 3224876 1.53%
## 20 0.0 211050000 4330455 2.05%
## Period StringencyIndex GovernmentResponseIndex EconomicSupportIndex
## 13 Pre COVID 0 0 0
## 14 Pre COVID 6 6 0
## 15 Pre COVID 42 30 0
## 16 Pre COVID 75 71 50
## 17 Post COVID 77 75 50
## 18 Post COVID 81 77 50
## 19 Post COVID 70 70 50
## 20 Post COVID 70 71 50
## PMI_PCT Money_Supply_PCT CPI_PCT Share_Price_Index_PCT unemployment_rate_pct
## 13 2.55% -2.17% 0.21% 3.28% 0.20%
## 14 -2.49% 0.36% 0.25% -3.08% 0.40%
## 15 -26.13% 5.47% 0.07% -28.02% 0.60%
## 16 -29.52% 5.71% -0.31% -4.74% 0.40%
## 17 44.13% 2.68% 0.26% 16.04% 0.40%
## 18 16.79% 2.05% 0.36% 7.30% 0.50%
## 19 13.95% 1.01% 0.24% 0.35%
## 20 -0.56% 1.95% 0.64% -3.01%
## Covid_share_pop_num Date
## 13 0.0000 2020-01-31
## 14 0.0000 2020-02-29
## 15 0.0000 2020-03-31
## 16 0.0001 2020-04-30
## 17 0.0040 2020-06-30
## 18 0.0089 2020-07-31
## 19 0.0153 2020-08-31
## 20 0.0205 2020-09-30m1 = with(BR, HotellingsT2(cbind( PMI,Money_supply,CPI,Share_Price_Index,unemployment_rate) ~ Period))
m1##
## Hotelling's two sample T2-test
##
## data: cbind(PMI, Money_supply, CPI, Share_Price_Index, unemployment_rate) by Period
## T.2 = 26.213, df1 = 5, df2 = 2, p-value = 0.03715
## alternative hypothesis: true location difference is not equal to c(0,0,0,0,0)##Mancova
mancova(data = BR,
deps = vars(PMI,Money_supply,CPI,Share_Price_Index,unemployment_rate), factors = Period)## Warning in log(unlist(lapply(mats, det))): NaNs produced##
## MANCOVA
##
## Multivariate Tests
## -------------------------------------------------------------------------------------
## value F df1 df2 p
## -------------------------------------------------------------------------------------
## Period Pillai's Trace 0.9849695 26.21253 5 2 0.0371538
## Wilks' Lambda 0.01503051 26.21253 5 2 0.0371538
## Hotelling's Trace 65.53132 26.21253 5 2 0.0371538
## Roy's Largest Root 65.53132 26.21253 5 2 0.0371538
## -------------------------------------------------------------------------------------
##
##
## Univariate Tests
## -------------------------------------------------------------------------------------------------------
## Dependent Variable Sum of Squares df Mean Square F p
## -------------------------------------------------------------------------------------------------------
## Period PMI 98.70125 1 98.70125 1.05208856 0.3445892
## Money_supply 620776.53125 1 620776.53125 35.74236463 0.0009829
## CPI 491.88161 1 491.88161 1.14952201 0.3248678
## Share_Price_Index 23.97781 1 23.97781 0.02731058 0.8741675
## unemployment_rate 52.53125 1 52.53125 1.70475289 0.2394929
## Residuals PMI 562.88750 6 93.81458
## Money_supply 104208.52750 6 17368.08792
## CPI 2567.40597 6 427.90100
## Share_Price_Index 5267.80807 6 877.96801
## unemployment_rate 184.88750 6 30.81458
## -------------------------------------------------------------------------------------------------------Colombia
main_test = main %>% filter(Period != "COVID Month")
CL = subset(main_test, Country %in% "Colombia")
CL ## Country Year Month PMI Money_supply CPI Share_Price_Index
## 29 Colombia 2020 3 0 527111.5 105.53 93.55
## 30 Colombia 2020 4 0 539776.4 105.70 89.57
## 31 Colombia 2020 5 0 543768.8 105.36 84.09
## 32 Colombia 2020 7 0 553114.8 104.97 89.39
## 33 Colombia 2020 8 0 551098.7 104.96 91.07
## 34 Colombia 2020 9 0 549796.4 105.29 93.88
## unemployment_rate Population covid_cummulative Covid_share_pop_PCT
## 29 12.6 50340000 28 0.00%
## 30 19.8 50340000 2852 0.01%
## 31 21.4 50340000 12930 0.03%
## 32 20.2 50340000 154277 0.31%
## 33 16.8 50340000 433805 0.86%
## 34 0.0 50340000 716319 1.42%
## Period StringencyIndex GovernmentResponseIndex EconomicSupportIndex
## 29 Pre COVID 34 27 0
## 30 Pre COVID 84 84 75
## 31 Pre COVID 87 86 75
## 32 Post COVID 87 86 75
## 33 Post COVID 87 86 75
## 34 Post COVID 71 61 63
## PMI_PCT Money_Supply_PCT CPI_PCT Share_Price_Index_PCT unemployment_rate_pct
## 29 5.85% 0.56% -26.48% 0.47%
## 30 2.40% 0.16% -4.25% 7.18%
## 31 0.74% -0.32% -6.12% 1.57%
## 32 0.44% 0.00% 0.04% 0.41%
## 33 -0.36% -0.01% 1.88% -3.46%
## 34 -0.24% 0.31% 3.09%
## Covid_share_pop_num Date
## 29 0.0000 2020-03-31
## 30 0.0001 2020-04-30
## 31 0.0003 2020-05-31
## 32 0.0031 2020-07-31
## 33 0.0086 2020-08-31
## 34 0.0142 2020-09-30m1 = with(CL, HotellingsT2(cbind( Money_supply,CPI,Share_Price_Index,unemployment_rate) ~ Period))
m1##
## Hotelling's two sample T2-test
##
## data: cbind(Money_supply, CPI, Share_Price_Index, unemployment_rate) by Period
## T.2 = 171.3, df1 = 4, df2 = 1, p-value = 0.05723
## alternative hypothesis: true location difference is not equal to c(0,0,0,0)##Mancova
mancova(data = CL,
deps = vars(Money_supply,CPI,Share_Price_Index,unemployment_rate), factors = Period)## Warning in log(unlist(lapply(mats, det))): NaNs produced##
## MANCOVA
##
## Multivariate Tests
## --------------------------------------------------------------------------------------
## value F df1 df2 p
## --------------------------------------------------------------------------------------
## Period Pillai's Trace 0.9985427 171.2981 4 1 0.0572344
## Wilks' Lambda 0.001457317 171.2981 4 1 0.0572344
## Hotelling's Trace 685.1925 171.2981 4 1 0.0572344
## Roy's Largest Root 685.1925 171.2981 4 1 0.0572344
## --------------------------------------------------------------------------------------
##
##
## Univariate Tests
## ----------------------------------------------------------------------------------------------------
## Dependent Variable Sum of Squares df Mean Square F p
## ----------------------------------------------------------------------------------------------------
## Period Money_supply 3.132500e+8 1 3.132500e+8 7.9880652 0.0475223
## CPI 0.3128167 1 0.31281667 9.7551975 0.0354125
## Share_Price_Index 8.4728167 1 8.47281667 0.6116048 0.4778873
## unemployment_rate 47.0400000 1 47.04000000 0.6770943 0.4568148
## Residuals Money_supply 1.568590e+8 4 3.921475e+7
## CPI 0.1282667 4 0.03206667
## Share_Price_Index 55.4136667 4 13.85341667
## unemployment_rate 277.8933333 4 69.47333333
## ----------------------------------------------------------------------------------------------------Spain
main_test = main %>% filter(Period != "COVID Month")
SP = subset(main_test, Country %in% "Spain")
SP ## Country Year Month PMI Money_supply CPI Share_Price_Index
## 117 Spain 2019 9 51.7 1241.0 104.12 83.81
## 118 Spain 2019 10 51.2 1231.2 105.13 85.28
## 119 Spain 2019 11 51.9 1253.6 105.30 86.11
## 120 Spain 2019 12 52.7 1247.9 105.23 87.61
## 121 Spain 2020 1 51.5 1229.5 104.20 88.08
## 122 Spain 2020 2 51.8 1238.7 104.08 89.07
## 123 Spain 2020 5 29.2 1311.2 103.99 62.02
## 124 Spain 2020 6 49.7 1337.8 104.47 67.94
## 125 Spain 2020 7 52.8 1335.9 103.53 67.17
## 126 Spain 2020 8 48.4 1339.5 103.58 64.57
## 127 Spain 2020 9 44.3 1344.2 103.73 62.74
## unemployment_rate Population covid_cummulative Covid_share_pop_PCT
## 117 13.9 47080000 0 0.00%
## 118 0.0 47080000 0 0.00%
## 119 0.0 47080000 0 0.00%
## 120 13.8 47080000 0 0.00%
## 121 0.0 47080000 0 0.00%
## 122 0.0 47080000 2 0.00%
## 123 0.0 47080000 230487 0.49%
## 124 15.3 47080000 244862 0.52%
## 125 0.0 47080000 257116 0.55%
## 126 0.0 47080000 351054 0.75%
## 127 16.3 47080000 615384 1.31%
## Period StringencyIndex GovernmentResponseIndex EconomicSupportIndex
## 117 Pre COVID 0 0 0
## 118 Pre COVID 0 0 0
## 119 Pre COVID 0 0 0
## 120 Pre COVID 0 0 0
## 121 Pre COVID 0 0 0
## 122 Pre COVID 11 17 0
## 123 Post COVID 83 78 88
## 124 Post COVID 57 63 88
## 125 Post COVID 64 68 88
## 126 Post COVID 63 66 88
## 127 Post COVID 61 65 88
## PMI_PCT Money_Supply_PCT CPI_PCT Share_Price_Index_PCT
## 117 -1.71% 0.44% 0.00% 3.43%
## 118 -0.97% -0.79% 0.97% 1.75%
## 119 1.37% 1.82% 0.16% 0.97%
## 120 1.54% -0.45% -0.07% 1.74%
## 121 -2.28% -1.47% -0.98% 0.54%
## 122 0.58% 0.74% -0.12% 1.12%
## 123 217.39% 1.35% 0.00% -0.64%
## 124 70.21% 2.03% 0.46% 9.55%
## 125 6.24% -0.15% -0.90% -1.13%
## 126 -8.33% 0.27% 0.05% -3.87%
## 127 -8.47% 0.35% 0.14% -2.83%
## unemployment_rate_pct Covid_share_pop_num Date
## 117 -0.10% 0.0000 2019-09-30
## 118 0.0000 2019-10-31
## 119 0.0000 2019-11-30
## 120 -0.14% 0.0000 2019-12-31
## 121 0.0000 2020-01-31
## 122 0.0000 2020-02-29
## 123 0.0049 2020-05-31
## 124 0.92% 0.0052 2020-06-30
## 125 0.0055 2020-07-31
## 126 0.0075 2020-08-31
## 127 0.93% 0.0131 2020-09-30m1 = with(SP, HotellingsT2(cbind( PMI, Money_supply,CPI,Share_Price_Index,unemployment_rate) ~ Period))
m1##
## Hotelling's two sample T2-test
##
## data: cbind(PMI, Money_supply, CPI, Share_Price_Index, unemployment_rate) by Period
## T.2 = 82.524, df1 = 5, df2 = 5, p-value = 8.411e-05
## alternative hypothesis: true location difference is not equal to c(0,0,0,0,0)##Mancova
mancova(data = SP,
deps = vars(PMI,Money_supply,CPI,Share_Price_Index,unemployment_rate), factors = Period)##
## MANCOVA
##
## Multivariate Tests
## -------------------------------------------------------------------------------------
## value F df1 df2 p
## -------------------------------------------------------------------------------------
## Period Pillai's Trace 0.9880275 82.52440 5 5 0.0000841
## Wilks' Lambda 0.01197255 82.52440 5 5 0.0000841
## Hotelling's Trace 82.52440 82.52440 5 5 0.0000841
## Roy's Largest Root 82.52440 82.52440 5 5 0.0000841
## -------------------------------------------------------------------------------------
##
##
## Univariate Tests
## ---------------------------------------------------------------------------------------------------------
## Dependent Variable Sum of Squares df Mean Square F p
## ---------------------------------------------------------------------------------------------------------
## Period PMI 130.599273 1 130.5992727 3.3987805 0.0983505
## Money_supply 23793.225485 1 23793.2254848 193.1030871 0.0000002
## CPI 1.818939 1 1.8189394 6.8595122 0.0278535
## Share_Price_Index 1292.781775 1 1292.7817745 250.1132002 < .0000001
## unemployment_rate 7.912758 1 7.9127576 0.1281219 0.7286385
## Residuals PMI 345.828000 9 38.4253333
## Money_supply 1108.936333 9 123.2151481
## CPI 2.386533 9 0.2651704
## Share_Price_Index 46.519080 9 5.1687867
## unemployment_rate 555.836333 9 61.7595926
## ---------------------------------------------------------------------------------------------------------Russia
main_test = main %>% filter(Period != "COVID Month")
RU = subset(main_test, Country %in% "Russia")
RU ## Country Year Month PMI Money_supply CPI Share_Price_Index
## 105 Russia 2020 1 52.6 50622.9 182.99 185.47
## 106 Russia 2020 2 50.9 51314.2 183.72 182.01
## 107 Russia 2020 3 39.5 52327.0 184.82 146.90
## 108 Russia 2020 4 13.9 52951.7 186.30 153.70
## 109 Russia 2020 6 48.9 54392.6 187.23 164.28
## 110 Russia 2020 7 56.8 54687.4 187.98 167.35
## 111 Russia 2020 8 57.3 55294.2 187.98 178.70
## 112 Russia 2020 9 53.7 56023.9 188.55 173.58
## unemployment_rate Population covid_cummulative Covid_share_pop_PCT
## 105 4.7 144370000 0 0.00%
## 106 4.6 144370000 2 0.00%
## 107 4.7 144370000 34 0.00%
## 108 5.8 144370000 24490 0.02%
## 109 6.2 144370000 537210 0.37%
## 110 6.3 144370000 746369 0.52%
## 111 6.4 144370000 917884 0.64%
## 112 0.0 144370000 1073849 0.74%
## Period StringencyIndex GovernmentResponseIndex EconomicSupportIndex
## 105 Pre COVID 0 0 0
## 106 Pre COVID 8 8 0
## 107 Pre COVID 36 32 0
## 108 Pre COVID 85 76 50
## 109 Post COVID 75 76 63
## 110 Post COVID 68 70 63
## 111 Post COVID 68 70 63
## 112 Post COVID 39 47 38
## PMI_PCT Money_Supply_PCT CPI_PCT Share_Price_Index_PCT
## 105 1.54% -2.01% 0.40% 4.63%
## 106 -3.23% 1.37% 0.40% -1.87%
## 107 -22.40% 1.97% 0.60% -19.29%
## 108 -64.81% 1.19% 0.80% 4.63%
## 109 39.71% 2.50% 0.20% 3.24%
## 110 16.16% 0.54% 0.40% 1.87%
## 111 0.88% 1.11% 0.00% 6.78%
## 112 -6.28% 1.32% 0.30% -2.87%
## unemployment_rate_pct Covid_share_pop_num Date
## 105 0.10% 0.0000 2020-01-31
## 106 -0.10% 0.0000 2020-02-29
## 107 0.10% 0.0000 2020-03-31
## 108 1.10% 0.0002 2020-04-30
## 109 0.10% 0.0037 2020-06-30
## 110 0.10% 0.0052 2020-07-31
## 111 0.10% 0.0064 2020-08-31
## 112 0.0074 2020-09-30m1 = with(RU, HotellingsT2(cbind( Money_supply,CPI,Share_Price_Index,unemployment_rate) ~ Period))
m1##
## Hotelling's two sample T2-test
##
## data: cbind(Money_supply, CPI, Share_Price_Index, unemployment_rate) by Period
## T.2 = 8.5504, df1 = 4, df2 = 3, p-value = 0.05448
## alternative hypothesis: true location difference is not equal to c(0,0,0,0)##Mancova
mancova(data = RU,
deps = vars(PMI,Money_supply,CPI,Share_Price_Index,unemployment_rate), factors = Period)## Warning in log(unlist(lapply(mats, det))): NaNs produced##
## MANCOVA
##
## Multivariate Tests
## -------------------------------------------------------------------------------------
## value F df1 df2 p
## -------------------------------------------------------------------------------------
## Period Pillai's Trace 0.9635481 10.57336 5 2 0.0886536
## Wilks' Lambda 0.03645191 10.57336 5 2 0.0886536
## Hotelling's Trace 26.43340 10.57336 5 2 0.0886536
## Roy's Largest Root 26.43340 10.57336 5 2 0.0886536
## -------------------------------------------------------------------------------------
##
##
## Univariate Tests
## ----------------------------------------------------------------------------------------------------------
## Dependent Variable Sum of Squares df Mean Square F p
## ----------------------------------------------------------------------------------------------------------
## Period PMI 447.0050000 1 447.0050000 2.67845426 0.1528298
## Money_supply 2.172163e+7 1 2.172163e+7 27.22234384 0.0019810
## CPI 24.1860125 1 24.1860125 20.43032321 0.0040176
## Share_Price_Index 31.3236125 1 31.3236125 0.14778023 0.7139215
## unemployment_rate 0.1012500 1 0.1012500 0.01975128 0.8928334
## Residuals PMI 1001.3350000 6 166.8891667
## Money_supply 4787602.9975000 6 797933.8329167
## CPI 7.1029750 6 1.1838292
## Share_Price_Index 1271.7646750 6 211.9607792
## unemployment_rate 30.7575000 6 5.1262500
## ----------------------------------------------------------------------------------------------------------