Dimension reduction project
The aim of this project is to perform dimension reduction on the data set [link] that contains information on the statistical performance indicators in every country on the planet. The number of variables is 79, but some of them are categorical, meaning it is impossible to perform dimension reduction
Attaching package: 'dplyr'
The following objects are masked from 'package:stats':
filter, lag
The following objects are masked from 'package:base':
intersect, setdiff, setequal, union
Warning: package 'corrplot' was built under R version 4.3.2
Attaching package: 'MASS'
The following object is masked from 'package:dplyr':
select
Warning: package 'factoextra' was built under R version 4.3.2
Loading required package: ggplot2
Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
Data manipulation and overview
Reading data
<- read.csv ("C:/Users/mateu/Downloads/spi_index_labelled.csv" )head (spi_index_labelled)
country iso3c date SPI.INDEX.PIL1
1 NA Pillar 1 - Data Use - Score
2 Norway NOR 2019 100
3 Italy ITA 2019 100
4 Austria AUT 2019 100
5 Poland POL 2019 100
6 Slovenia SVN 2019 100
SPI.INDEX.PIL2 SPI.INDEX.PIL3
1 Pillar 2 - Data Services - Score Pillar 3 - Data Products - Score
2 92.2333333333333 77.56875
3 91.8666666666666 75.2875
4 91.3 74.55
5 95.1 70.5375
6 96.9333333333333 76.28125
SPI.INDEX.PIL4 SPI.INDEX.PIL5
1 Pillar 4 - Data Sources - Score Pillar 5 - Data Infrastructure - Score
2 80.6666666666667 100
3 81.825 100
4 79.75 100
5 79.7166666666667 100
6 71.4416666666667 100
SPI.INDEX SPI.DIM1.5.INDEX
1 SPI Overall Score Dimension 1.5: Data use by international organizations
2 90.09375 1
3 89.7958333333333 1
4 89.12 1
5 89.0708333333333 1
6 88.93125 1
SPI.DIM2.1.INDEX SPI.DIM2.2.INDEX
1 Dimension 2.1: Data Releases Dimension 2.2: Online access
2 1 0.767
3 1 0.756
4 1 0.739
5 1 0.853
6 1 0.908
SPI.DIM2.4.INDEX SPI.DIM3.1.INDEX
1 Dimension 2.4: Data services Dimension 3.1: Social Statistics
2 1 0.757833333333333
3 1 0.711166666666667
4 1 0.721666666666667
5 1 0.678666666666667
6 1 0.7335
SPI.DIM3.2.INDEX SPI.DIM3.3.INDEX
1 Dimension 3.2: Economic Statistics Dimension 3.3: Environmental Statistics
2 0.782166666666667 1
3 0.787166666666667 1
4 0.750666666666667 1
5 0.7515 0.75
6 0.791333333333333 1
SPI.DIM3.4.INDEX
1 Dimension 3.4: Institutional Statistics
2 0.5855
3 0.528
4 0.547
5 0.6025
6 0.528
SPI.DIM4.1.CEN.INDEX
1 Dimension 4.1: Censuses and Surveys - Censuses only
2 0.666666666666667
3 1
4 1
5 0.666666666666667
6 0.666666666666667
SPI.DIM4.1.SVY.INDEX
1 Dimension 4.1: Censuses and Surveys - Surveys only
2 1
3 0.934
4 0.866
5 0.934
6 0.934
SPI.DIM4.2.INDEX SPI.DIM4.3.INDEX
1 Dimension 4.2: Administrative Data Dimension 4.3: Geospatial Data
2 1 0.56
3 1 0.339
4 1 0.324
5 1 0.588
6 1 0.257
SPI.DIM5.1.INDEX
1 Dimension 5.1: Legislation and governance
2 1
3 1
4 1
5 1
6 1
SPI.DIM5.2.INDEX SPI.DIM5.5.INDEX
1 Dimension 5.2: Standards and Methods Dimension 5.5: Finance
2 1 1
3 1 1
4 1 1
5 1 1
6 1 1
SPI.D1.5.POV
1 Dimension 1.5: Data use by international organisations - Availability of Comparable Poverty headcount ratio at $1.90 a day
2 1
3 1
4 1
5 1
6 1
SPI.D1.5.CHLD.MORT
1 Dimension 1.5: Data use by international organisations - Availability of Mortality rate, under-5 (per 1,000 live births) data meeting quality standards according to UN IGME
2 1
3 1
4 1
5 1
6 1
SPI.D1.5.DT.TDS.DPPF.XP.ZS
1 Dimension 1.5: Data use by international organisations - Quality of Debt service data according to World Bank
2 1
3 1
4 1
5 1
6 1
SPI.D1.5.SAFE.MAN.WATER
1 Dimension1.5: Data use by international organisations - Safely Managed Drinking Water
2 1
3 1
4 1
5 1
6 1
SPI.D1.5.LFP
1 Dimension 1.5: Data use by international organisations - Labor force participation rate by sex and age (%)
2 1
3 1
4 1
5 1
6 1
SPI.D2.1.GDDS
1 Dimension 2.1: Data releases - SDDS/e-GDDS subscription
2 1
3 1
4 1
5 1
6 1
SPI.D2.2.Machine.readable
1 Dimension 2.2: Online access - Machine Readability Score
2 1
3 0.771
4 0.907
5 1
6 0.963
SPI.D2.2.Non.proprietary
1 Dimension 2.2: Online access - Non-Proprietary format Score
2 1
3 0.786
4 0.963
5 1
6 1
SPI.D2.2.Download.options
1 Dimension 2.2: Online access - Download Options Score
2 0.623
3 0.69
4 0.686
5 0.68
6 0.784
SPI.D2.2.Metadata.available
1 Dimension 2.2: Online access - Metadata Available Score
2 0.67
3 0.762
4 0.703
5 0.679
6 0.897
SPI.D2.2.Terms.of.use
1 Dimension 2.2: Online access - Terms of Use Score
2 0.542
3 0.771
4 0.434
5 0.905
6 0.897
SPI.D2.2.Openness.subscore
1 Dimension 2.2: Online access - ODIN Open Data Openness score
2 0.767
3 0.756
4 0.739
5 0.853
6 0.908
SPI.D2.4.NADA
1 Dimension 2.4: Data access services - NADA metadata
2 1
3 1
4 1
5 1
6 1
SPI.D3.1.POV
1 Dimension 3.1: SDG Goal 1 - GOAL 1: No Poverty
2 1
3 0.857
4 1
5 0.714
6 1
SPI.D3.2.HNGR
1 Dimension 3.2: SDG Goal 2 - GOAL 2: Zero Hunger
2 0.889
3 0.8
4 0.6
5 0.7
6 0.7
SPI.D3.3.HLTH
1 Dimension 3.3: SDG Goal 3 - GOAL 3: Good Health and Well-being
2 0.905
3 0.857
4 0.9
5 0.905
6 0.857
SPI.D3.4.EDUC
1 Dimension 3.4: SDG Goal 4 - GOAL 4: Quality Education
2 0.545
3 0.545
4 0.455
5 0.545
6 0.636
SPI.D3.5.GEND
1 Dimension 3.5: SDG Goal 5 - GOAL 5: Gender Equality
2 0.375
3 0.375
4 0.375
5 0.375
6 0.375
SPI.D3.6.WTRS
1 Dimension 3.6: SDG Goal 6 - GOAL 6: Clean Water and Sanitation
2 0.833
3 0.833
4 1
5 0.833
6 0.833
SPI.D3.7.ENRG
1 Dimension 3.7: SDG Goal 7 - GOAL 7: Affordable and Clean Energy
2 0.8
3 0.8
4 0.8
5 0.8
6 0.8
SPI.D3.8.WORK
1 Dimension 3.8: SDG Goal 8 - GOAL 8: Decent Work and Economic Growth
2 0.643
3 0.769
4 0.692
5 0.692
6 0.769
SPI.D3.9.INDY
1 Dimension 3.9: SDG Goal 9 - GOAL 9: Industry, Innovation and Infrastructure
2 1
3 1
4 1
5 1
6 1
SPI.D3.10.NEQL
1 Dimension 3.10: SDG Goal 10 - GOAL 10: Reduced Inequality
2 0.5
3 0.571
4 0.429
5 0.667
6 0.429
SPI.D3.11.CITY
1 Dimension 3.11: SDG Goal 11 - GOAL 11: Sustainable Cities and Communities
2 1
3 0.833
4 0.833
5 0.6
6 1
SPI.D3.12.CNSP
1 Dimension 3.12: SDG Goal 12 - GOAL 12: Responsible Consumption and Production
2 0.75
3 0.75
4 0.75
5 0.75
6 0.75
SPI.D3.15.LAND
1 Dimension 3.15: SDG Goal 15 - GOAL 15: Life on Land
2 1
3 1
4 1
5 1
6 1
SPI.D3.16.INST
1 Dimension 3.16: SDG Goal 16 - GOAL 16: Peace and Justice Strong Institutions
2 0.556
3 0.556
4 0.556
5 0.667
6 0.556
SPI.D3.17.PTNS
1 Dimension 3.17: SDG Goal 17 - GOAL 17: Partnerships to achieve the Goal
2 0.615
3 0.5
4 0.538
5 0.538
6 0.5
SPI.D3.13.CLMT
1 Dimension 3.13: SDG Goal 13 - GOAL 13: Climate Action
2 1
3 1
4 1
5 0.5
6 1
SPI.D4.1.1.POPU
1 Dimension 4.1: censuses and surveys - Population & Housing census
2 1
3 1
4 1
5 1
6 1
SPI.D4.1.2.AGRI
1 Dimension 4.1: censuses and surveys - Agriculture census
2 1
3 1
4 1
5 1
6 1
SPI.D4.1.3.BIZZ
1 Dimension 4.1: censuses and surveys - Business/establishment census
2 0
3 1
4 1
5 0
6 0
SPI.D4.1.4.HOUS
1 Dimension 4.1: censuses and surveys - Household Survey on income, etc
2 1
3 1
4 1
5 1
6 1
SPI.D4.1.5.AGSVY
1 Dimension 4.1: censuses and surveys - Agriculture survey
2 1
3 1
4 1
5 1
6 1
SPI.D4.1.6.LABR
1 Dimension 4.1: censuses and surveys - Labor Force Survey
2 1
3 1
4 1
5 1
6 1
SPI.D4.1.7.HLTH
1 Dimension 4.1: censuses and surveys - Health/Demographic survey
2 1
3 0.67
4 0.33
5 0.67
6 0.67
SPI.D4.1.8.BZSVY
1 Dimension 4.1: censuses and surveys - Business/establishment survey
2 1
3 1
4 1
5 1
6 1
SPI.D4.2.3.CRVS
1 Dimension 4.2: administrative data - CRVS (WDI)
2 1
3 1
4 1
5 1
6 1
SPI.D4.3.GEO.first.admin.level
1 Dimension 4.3: geospatial data - Geospatial data available at 1st Admin Level
2 0.56
3 0.339
4 0.324
5 0.588
6 0.257
SPI.D5.1.DILG
1 Dimension 5.1: Legislation and governance - Legislation Indicator based on PARIS21 indicators on SDG 17.18.2
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.1.SNAU
1 Dimension 5.2: standards - System of national accounts in use
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.2.NABY
1 Dimension 5.2: standards - National Accounts base year
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.3.CNIN
1 Dimension 5.2: standards - Classification of national industry
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.4.CPIBY
1 Dimension 5.2: standards - CPI base year
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.5.HOUS
1 Dimension 5.2: standards - Classification of household consumption
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.6.EMPL
1 Dimension 5.2: standards - Classification of status of employment
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.7.CGOV
1 Dimension 5.2: standards - Central government accounting status
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.8.FINA
1 Dimension 5.2: standards - Compilation of government finance statistics
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.9.MONY
1 Dimension 5.2: standards - Compilation of monetary and financial statistics
2 1
3 1
4 1
5 1
6 1
SPI.D5.2.10.GSBP
1 Dimension 5.2: standards - Business process
2 1
3 1
4 1
5 1
6 1
SPI.D5.5.DIFI
1 Dimension 5.5: Finance - Finance Indicator based on PARIS21 indicators on SDG 17.18.3 & SDG 17.19.1
2 1
3 1
4 1
5 1
6 1
income region weights population
1 NA NA
2 High income Europe & Central Asia 1 5347896
3 High income Europe & Central Asia 1 60297396
4 High income Europe & Central Asia 1 8877067
5 High income Europe & Central Asia 1 37970874
6 High income Europe & Central Asia 1 2087946
We are going to use only data from 2019 for 173 countries. We need to delete the first row as well.
<- spi_index_labelled[2 : 175 ,]
[1] "country" "iso3c"
[3] "date" "SPI.INDEX.PIL1"
[5] "SPI.INDEX.PIL2" "SPI.INDEX.PIL3"
[7] "SPI.INDEX.PIL4" "SPI.INDEX.PIL5"
[9] "SPI.INDEX" "SPI.DIM1.5.INDEX"
[11] "SPI.DIM2.1.INDEX" "SPI.DIM2.2.INDEX"
[13] "SPI.DIM2.4.INDEX" "SPI.DIM3.1.INDEX"
[15] "SPI.DIM3.2.INDEX" "SPI.DIM3.3.INDEX"
[17] "SPI.DIM3.4.INDEX" "SPI.DIM4.1.CEN.INDEX"
[19] "SPI.DIM4.1.SVY.INDEX" "SPI.DIM4.2.INDEX"
[21] "SPI.DIM4.3.INDEX" "SPI.DIM5.1.INDEX"
[23] "SPI.DIM5.2.INDEX" "SPI.DIM5.5.INDEX"
[25] "SPI.D1.5.POV" "SPI.D1.5.CHLD.MORT"
[27] "SPI.D1.5.DT.TDS.DPPF.XP.ZS" "SPI.D1.5.SAFE.MAN.WATER"
[29] "SPI.D1.5.LFP" "SPI.D2.1.GDDS"
[31] "SPI.D2.2.Machine.readable" "SPI.D2.2.Non.proprietary"
[33] "SPI.D2.2.Download.options" "SPI.D2.2.Metadata.available"
[35] "SPI.D2.2.Terms.of.use" "SPI.D2.2.Openness.subscore"
[37] "SPI.D2.4.NADA" "SPI.D3.1.POV"
[39] "SPI.D3.2.HNGR" "SPI.D3.3.HLTH"
[41] "SPI.D3.4.EDUC" "SPI.D3.5.GEND"
[43] "SPI.D3.6.WTRS" "SPI.D3.7.ENRG"
[45] "SPI.D3.8.WORK" "SPI.D3.9.INDY"
[47] "SPI.D3.10.NEQL" "SPI.D3.11.CITY"
[49] "SPI.D3.12.CNSP" "SPI.D3.15.LAND"
[51] "SPI.D3.16.INST" "SPI.D3.17.PTNS"
[53] "SPI.D3.13.CLMT" "SPI.D4.1.1.POPU"
[55] "SPI.D4.1.2.AGRI" "SPI.D4.1.3.BIZZ"
[57] "SPI.D4.1.4.HOUS" "SPI.D4.1.5.AGSVY"
[59] "SPI.D4.1.6.LABR" "SPI.D4.1.7.HLTH"
[61] "SPI.D4.1.8.BZSVY" "SPI.D4.2.3.CRVS"
[63] "SPI.D4.3.GEO.first.admin.level" "SPI.D5.1.DILG"
[65] "SPI.D5.2.1.SNAU" "SPI.D5.2.2.NABY"
[67] "SPI.D5.2.3.CNIN" "SPI.D5.2.4.CPIBY"
[69] "SPI.D5.2.5.HOUS" "SPI.D5.2.6.EMPL"
[71] "SPI.D5.2.7.CGOV" "SPI.D5.2.8.FINA"
[73] "SPI.D5.2.9.MONY" "SPI.D5.2.10.GSBP"
[75] "SPI.D5.5.DIFI" "income"
[77] "region" "weights"
[79] "population"
Dropping the columns that are not related with statistical offices quality. Also the aggregated indicators.
<- data.frame (data2019)<- c ("iso3c" ,"date" ,"SPI.INDEX.PIL1" ,"SPI.INDEX.PIL2" ,"SPI.INDEX.PIL3" ,"SPI.INDEX.PIL4" ,"SPI.INDEX.PIL5" ,"SPI.INDEX" ,"income" ,"region" ,"weights" ,"population" , "SPI.DIM1.5.INDEX" )<- data2019[,! (names (data2019) %in% drop)]head (data2019)
country SPI.DIM2.1.INDEX SPI.DIM2.2.INDEX SPI.DIM2.4.INDEX
2 Norway 1 0.767 1
3 Italy 1 0.756 1
4 Austria 1 0.739 1
5 Poland 1 0.853 1
6 Slovenia 1 0.908 1
7 United States 1 0.82 1
SPI.DIM3.1.INDEX SPI.DIM3.2.INDEX SPI.DIM3.3.INDEX SPI.DIM3.4.INDEX
2 0.757833333333333 0.782166666666667 1 0.5855
3 0.711166666666667 0.787166666666667 1 0.528
4 0.721666666666667 0.750666666666667 1 0.547
5 0.678666666666667 0.7515 0.75 0.6025
6 0.7335 0.791333333333333 1 0.528
7 0.593 0.604833333333333 0.9445 0.5115
SPI.DIM4.1.CEN.INDEX SPI.DIM4.1.SVY.INDEX SPI.DIM4.2.INDEX SPI.DIM4.3.INDEX
2 0.666666666666667 1 1 0.56
3 1 0.934 1 0.339
4 1 0.866 1 0.324
5 0.666666666666667 0.934 1 0.588
6 0.666666666666667 0.934 1 0.257
7 1 1 1 0.5
SPI.DIM5.1.INDEX SPI.DIM5.2.INDEX SPI.DIM5.5.INDEX SPI.D1.5.POV
2 1 1 1 1
3 1 1 1 1
4 1 1 1 1
5 1 1 1 1
6 1 1 1 1
7 1 1 1 1
SPI.D1.5.CHLD.MORT SPI.D1.5.DT.TDS.DPPF.XP.ZS SPI.D1.5.SAFE.MAN.WATER
2 1 1 1
3 1 1 1
4 1 1 1
5 1 1 1
6 1 1 1
7 1 1 1
SPI.D1.5.LFP SPI.D2.1.GDDS SPI.D2.2.Machine.readable SPI.D2.2.Non.proprietary
2 1 1 1 1
3 1 1 0.771 0.786
4 1 1 0.907 0.963
5 1 1 1 1
6 1 1 0.963 1
7 1 1 0.83 0.952
SPI.D2.2.Download.options SPI.D2.2.Metadata.available SPI.D2.2.Terms.of.use
2 0.623 0.67 0.542
3 0.69 0.762 0.771
4 0.686 0.703 0.434
5 0.68 0.679 0.905
6 0.784 0.897 0.897
7 0.566 0.797 0.952
SPI.D2.2.Openness.subscore SPI.D2.4.NADA SPI.D3.1.POV SPI.D3.2.HNGR
2 0.767 1 1 0.889
3 0.756 1 0.857 0.8
4 0.739 1 1 0.6
5 0.853 1 0.714 0.7
6 0.908 1 1 0.7
7 0.82 1 0.857 0.7
SPI.D3.3.HLTH SPI.D3.4.EDUC SPI.D3.5.GEND SPI.D3.6.WTRS SPI.D3.7.ENRG
2 0.905 0.545 0.375 0.833 0.8
3 0.857 0.545 0.375 0.833 0.8
4 0.9 0.455 0.375 1 0.8
5 0.905 0.545 0.375 0.833 0.8
6 0.857 0.636 0.375 0.833 0.8
7 0.762 0.364 0.375 0.5 0.6
SPI.D3.8.WORK SPI.D3.9.INDY SPI.D3.10.NEQL SPI.D3.11.CITY SPI.D3.12.CNSP
2 0.643 1 0.5 1 0.75
3 0.769 1 0.571 0.833 0.75
4 0.692 1 0.429 0.833 0.75
5 0.692 1 0.667 0.6 0.75
6 0.769 1 0.429 1 0.75
7 0.571 0.625 0.5 0.833 0.5
SPI.D3.15.LAND SPI.D3.16.INST SPI.D3.17.PTNS SPI.D3.13.CLMT SPI.D4.1.1.POPU
2 1 0.556 0.615 1 1
3 1 0.556 0.5 1 1
4 1 0.556 0.538 1 1
5 1 0.667 0.538 0.5 1
6 1 0.556 0.5 1 1
7 0.889 0.556 0.467 1 1
SPI.D4.1.2.AGRI SPI.D4.1.3.BIZZ SPI.D4.1.4.HOUS SPI.D4.1.5.AGSVY
2 1 0 1 1
3 1 1 1 1
4 1 1 1 1
5 1 0 1 1
6 1 0 1 1
7 1 1 1 1
SPI.D4.1.6.LABR SPI.D4.1.7.HLTH SPI.D4.1.8.BZSVY SPI.D4.2.3.CRVS
2 1 1 1 1
3 1 0.67 1 1
4 1 0.33 1 1
5 1 0.67 1 1
6 1 0.67 1 1
7 1 1 1 1
SPI.D4.3.GEO.first.admin.level SPI.D5.1.DILG SPI.D5.2.1.SNAU SPI.D5.2.2.NABY
2 0.56 1 1 1
3 0.339 1 1 1
4 0.324 1 1 1
5 0.588 1 1 1
6 0.257 1 1 1
7 0.5 1 1 1
SPI.D5.2.3.CNIN SPI.D5.2.4.CPIBY SPI.D5.2.5.HOUS SPI.D5.2.6.EMPL
2 1 1 1 1
3 1 1 1 1
4 1 1 1 1
5 1 1 1 1
6 1 1 1 1
7 1 1 1 1
SPI.D5.2.7.CGOV SPI.D5.2.8.FINA SPI.D5.2.9.MONY SPI.D5.2.10.GSBP
2 1 1 1 1
3 1 1 1 1
4 1 1 1 1
5 1 1 1 1
6 1 1 1 1
7 1 1 1 1
SPI.D5.5.DIFI
2 1
3 1
4 1
5 1
6 1
7 1
Now filtering out the ordinal data.
<- 5 <- sapply (data2019, function (x) length (unique (x))) <= threshold# Filter the dataframe <- data2019[, ! selected_columns]
<- filtered_data[! complete.cases (filtered_data), ]
[1] country SPI.DIM2.2.INDEX
[3] SPI.DIM3.1.INDEX SPI.DIM3.2.INDEX
[5] SPI.DIM3.3.INDEX SPI.DIM3.4.INDEX
[7] SPI.DIM4.1.CEN.INDEX SPI.DIM4.1.SVY.INDEX
[9] SPI.DIM4.3.INDEX SPI.DIM5.2.INDEX
[11] SPI.D2.2.Machine.readable SPI.D2.2.Non.proprietary
[13] SPI.D2.2.Download.options SPI.D2.2.Metadata.available
[15] SPI.D2.2.Terms.of.use SPI.D2.2.Openness.subscore
[17] SPI.D3.1.POV SPI.D3.2.HNGR
[19] SPI.D3.3.HLTH SPI.D3.4.EDUC
[21] SPI.D3.5.GEND SPI.D3.6.WTRS
[23] SPI.D3.8.WORK SPI.D3.9.INDY
[25] SPI.D3.10.NEQL SPI.D3.11.CITY
[27] SPI.D3.15.LAND SPI.D3.16.INST
[29] SPI.D3.17.PTNS SPI.D4.3.GEO.first.admin.level
<0 rows> (or 0-length row.names)
As we can see, now there are no incomplete cases.
<- filtered_data<- names (data2019n)[- 1 ]<- lapply (data2019n[, columns_to_convert], function (x) as.numeric (as.character (x)))summary (data2019n)
country SPI.DIM2.2.INDEX SPI.DIM3.1.INDEX SPI.DIM3.2.INDEX
Length:174 Min. :0.0190 Min. :0.3028 Min. :0.3607
Class :character 1st Qu.:0.3040 1st Qu.:0.5371 1st Qu.:0.4985
Mode :character Median :0.3980 Median :0.6490 Median :0.6073
Mean :0.4660 Mean :0.6234 Mean :0.5958
3rd Qu.:0.6188 3rd Qu.:0.7168 3rd Qu.:0.6775
Max. :1.0000 Max. :0.9072 Max. :0.9153
SPI.DIM3.3.INDEX SPI.DIM3.4.INDEX SPI.DIM4.1.CEN.INDEX SPI.DIM4.1.SVY.INDEX
Min. :0.2220 Min. :0.2670 Min. :0.0000 Min. :0.0000
1st Qu.:0.4445 1st Qu.:0.5220 1st Qu.:0.3333 1st Qu.:0.4000
Median :0.6945 Median :0.5790 Median :0.6667 Median :0.6000
Mean :0.7276 Mean :0.5789 Mean :0.5699 Mean :0.6124
3rd Qu.:0.9445 3rd Qu.:0.6659 3rd Qu.:0.6667 3rd Qu.:0.8000
Max. :1.0000 Max. :0.8290 Max. :1.0000 Max. :1.0000
SPI.DIM4.3.INDEX SPI.DIM5.2.INDEX SPI.D2.2.Machine.readable
Min. :0.0000 Min. :0.0000 Min. :0.0000
1st Qu.:0.1128 1st Qu.:0.3000 1st Qu.:0.1323
Median :0.1780 Median :0.4500 Median :0.4175
Mean :0.1969 Mean :0.5460 Mean :0.4677
3rd Qu.:0.2785 3rd Qu.:0.8375 3rd Qu.:0.8093
Max. :0.6980 Max. :1.0000 Max. :1.0000
SPI.D2.2.Non.proprietary SPI.D2.2.Download.options SPI.D2.2.Metadata.available
Min. :0.0000 Min. :0.0240 Min. :0.0000
1st Qu.:0.5952 1st Qu.:0.2530 1st Qu.:0.3772
Median :0.7715 Median :0.3495 Median :0.4715
Mean :0.7214 Mean :0.3975 Mean :0.4929
3rd Qu.:0.8890 3rd Qu.:0.5312 3rd Qu.:0.5753
Max. :1.0000 Max. :1.0000 Max. :1.0000
SPI.D2.2.Terms.of.use SPI.D2.2.Openness.subscore SPI.D3.1.POV
Min. :0.0000 Min. :0.0190 Min. :0.0000
1st Qu.:0.0000 1st Qu.:0.3040 1st Qu.:0.4290
Median :0.0000 Median :0.3980 Median :0.7140
Mean :0.2508 Mean :0.4660 Mean :0.6773
3rd Qu.:0.4765 3rd Qu.:0.6188 3rd Qu.:0.8570
Max. :1.0000 Max. :1.0000 Max. :1.0000
SPI.D3.2.HNGR SPI.D3.3.HLTH SPI.D3.4.EDUC SPI.D3.5.GEND
Min. :0.1430 Min. :0.2380 Min. :0.091 Min. :0.1250
1st Qu.:0.5560 1st Qu.:0.7140 1st Qu.:0.364 1st Qu.:0.2500
Median :0.7000 Median :0.8000 Median :0.455 Median :0.3750
Mean :0.6595 Mean :0.7805 Mean :0.453 Mean :0.3505
3rd Qu.:0.8000 3rd Qu.:0.8570 3rd Qu.:0.545 3rd Qu.:0.5000
Max. :1.0000 Max. :1.0000 Max. :0.818 Max. :0.7500
SPI.D3.6.WTRS SPI.D3.8.WORK SPI.D3.9.INDY SPI.D3.10.NEQL
Min. :0.3330 Min. :0.143 Min. :0.1250 Min. :0.1670
1st Qu.:0.7003 1st Qu.:0.308 1st Qu.:0.3750 1st Qu.:0.3330
Median :0.8330 Median :0.462 Median :0.6250 Median :0.4290
Mean :0.8195 Mean :0.480 Mean :0.6073 Mean :0.4586
3rd Qu.:1.0000 3rd Qu.:0.615 3rd Qu.:0.7500 3rd Qu.:0.6000
Max. :1.0000 Max. :0.923 Max. :1.0000 Max. :0.8000
SPI.D3.11.CITY SPI.D3.15.LAND SPI.D3.16.INST SPI.D3.17.PTNS
Min. :0.1670 Min. :0.4440 Min. :0.2220 Min. :0.2940
1st Qu.:0.3330 1st Qu.:0.8890 1st Qu.:0.4440 1st Qu.:0.5343
Median :0.6670 Median :0.8890 Median :0.5560 Median :0.6000
Mean :0.5947 Mean :0.8718 Mean :0.5666 Mean :0.5913
3rd Qu.:0.8000 3rd Qu.:0.8890 3rd Qu.:0.6670 3rd Qu.:0.6670
Max. :1.0000 Max. :1.0000 Max. :0.8890 Max. :0.7860
SPI.D4.3.GEO.first.admin.level
Min. :0.0000
1st Qu.:0.1128
Median :0.1780
Mean :0.1969
3rd Qu.:0.2785
Max. :0.6980
PCA
<- prcomp (data2019n[,- 1 ], center = T, scale= T)summary (data_pca)
Importance of components:
PC1 PC2 PC3 PC4 PC5 PC6 PC7
Standard deviation 3.4960 2.1288 1.45733 1.25356 1.06860 0.99761 0.89102
Proportion of Variance 0.4215 0.1563 0.07324 0.05419 0.03938 0.03432 0.02738
Cumulative Proportion 0.4215 0.5777 0.65096 0.70514 0.74452 0.77884 0.80621
PC8 PC9 PC10 PC11 PC12 PC13 PC14
Standard deviation 0.85272 0.79446 0.74459 0.70718 0.67600 0.67312 0.62752
Proportion of Variance 0.02507 0.02176 0.01912 0.01725 0.01576 0.01562 0.01358
Cumulative Proportion 0.83129 0.85305 0.87217 0.88941 0.90517 0.92079 0.93437
PC15 PC16 PC17 PC18 PC19 PC20 PC21
Standard deviation 0.60089 0.55592 0.51816 0.48957 0.44278 0.40587 0.39342
Proportion of Variance 0.01245 0.01066 0.00926 0.00826 0.00676 0.00568 0.00534
Cumulative Proportion 0.94682 0.95748 0.96674 0.97500 0.98176 0.98745 0.99278
PC22 PC23 PC24 PC25 PC26 PC27
Standard deviation 0.35125 0.23835 0.1706 0.001427 1.125e-15 6.157e-16
Proportion of Variance 0.00425 0.00196 0.0010 0.000000 0.000e+00 0.000e+00
Cumulative Proportion 0.99704 0.99900 1.0000 1.000000 1.000e+00 1.000e+00
PC28 PC29
Standard deviation 3.681e-16 2.827e-16
Proportion of Variance 0.000e+00 0.000e+00
Cumulative Proportion 1.000e+00 1.000e+00
As we can see we can reduce the number of variables to 6 while explaining 75% of variance or to 12 while explaining 90% of variance. Let’s look at the scree plot.
fviz_eig (data_pca, addlbales = T, ylim= c (0 ,80 ))
<- data_pca$ rotationprint ("Variable Loadings:" )
PC1 PC2 PC3 PC4 PC5
SPI.DIM2.2.INDEX -0.2234130 0.26929068 -0.05763134 0.01599882 -0.10877895
SPI.DIM3.1.INDEX -0.2434693 -0.22172500 -0.03924868 -0.04389728 -0.07708868
SPI.DIM3.2.INDEX -0.2539881 -0.06898791 0.15249745 -0.16012299 0.12946325
SPI.DIM3.3.INDEX -0.1622832 -0.21119647 0.36514427 -0.03859310 -0.27979753
SPI.DIM3.4.INDEX -0.1444984 -0.26863986 -0.36601656 0.15214387 0.02860233
SPI.DIM4.1.CEN.INDEX -0.1540554 0.07040690 -0.05101389 0.02530164 -0.17283094
PC6 PC7 PC8 PC9
SPI.DIM2.2.INDEX 0.09564713 -0.08335476 0.16489383 -0.04194902
SPI.DIM3.1.INDEX 0.01406155 -0.08443059 -0.10545640 0.01245611
SPI.DIM3.2.INDEX -0.10217419 0.01917857 -0.11453245 -0.07140584
SPI.DIM3.3.INDEX -0.11309458 -0.03235520 0.17237008 -0.12700812
SPI.DIM3.4.INDEX -0.03825113 0.04217487 0.24178301 -0.06565367
SPI.DIM4.1.CEN.INDEX 0.07125570 0.80970381 -0.01048636 0.17502805
PC10 PC11 PC12 PC13
SPI.DIM2.2.INDEX 0.04486835 0.026529843 0.01796801 0.016305557
SPI.DIM3.1.INDEX 0.01920430 0.140817916 0.03721249 0.008578093
SPI.DIM3.2.INDEX -0.06843817 -0.056024272 0.01460682 -0.024560873
SPI.DIM3.3.INDEX -0.11438816 -0.001088628 -0.12161740 0.086113589
SPI.DIM3.4.INDEX 0.04511480 -0.171195285 -0.13147559 -0.037672647
SPI.DIM4.1.CEN.INDEX -0.12160595 0.296191359 -0.23092402 0.040511366
PC14 PC15 PC16 PC17
SPI.DIM2.2.INDEX -0.02956448 -0.03532554 -0.01374741 0.010622187
SPI.DIM3.1.INDEX -0.07102327 -0.06302166 -0.08235706 0.016499590
SPI.DIM3.2.INDEX -0.06889699 0.04353947 0.01402071 0.059390120
SPI.DIM3.3.INDEX -0.04008307 0.02174968 0.06418388 0.003995137
SPI.DIM3.4.INDEX 0.08996936 0.16819440 0.13949232 -0.013847339
SPI.DIM4.1.CEN.INDEX -0.16195906 -0.03240969 0.04074945 -0.198863947
PC18 PC19 PC20 PC21
SPI.DIM2.2.INDEX 0.026397610 0.003742454 0.06816913 -0.090311855
SPI.DIM3.1.INDEX 0.025461814 -0.081270866 -0.07228833 0.053370516
SPI.DIM3.2.INDEX -0.052437586 0.258315586 0.18503911 0.057516065
SPI.DIM3.3.INDEX -0.007705645 -0.102853644 -0.02671311 -0.092606065
SPI.DIM3.4.INDEX -0.119665239 -0.013155927 0.05035510 -0.001022566
SPI.DIM4.1.CEN.INDEX -0.018532982 0.015910795 -0.09734680 0.010549376
PC22 PC23 PC24 PC25
SPI.DIM2.2.INDEX -0.00861016 0.02019766 0.009312399 -5.452527e-01
SPI.DIM3.1.INDEX -0.22405515 0.06801869 -0.007307258 -6.190692e-06
SPI.DIM3.2.INDEX 0.24603550 0.34753940 0.727120419 7.113507e-04
SPI.DIM3.3.INDEX 0.09255094 -0.72658147 0.241562637 2.826801e-04
SPI.DIM3.4.INDEX 0.03453889 0.01220599 0.009471488 -3.034242e-07
SPI.DIM4.1.CEN.INDEX 0.08739951 0.05250852 -0.014183338 1.933318e-04
PC26 PC27 PC28 PC29
SPI.DIM2.2.INDEX -7.071068e-01 0.000000e+00 0.000000e+00 0.000000e+00
SPI.DIM3.1.INDEX 6.755707e-14 8.670967e-01 6.127789e-02 9.341307e-04
SPI.DIM3.2.INDEX 2.081668e-16 -1.165734e-15 7.268491e-16 -3.840786e-17
SPI.DIM3.3.INDEX 3.348016e-16 5.967449e-16 4.297777e-16 1.512394e-16
SPI.DIM3.4.INDEX -2.167017e-14 5.153745e-02 -7.314640e-01 1.441136e-01
SPI.DIM4.1.CEN.INDEX 1.595946e-16 2.775558e-17 1.231654e-16 -2.919214e-17
As two first PCs explain about 57% of variance I do not think it is appropriate to show them on a biplot.
Now, what can we do with it?
Depends on the task we wanted to perform. If we were to analyze the continuous variables only we could finish here. If we were asked to perform some operations on the whole data set we could add the rest of variables back to the data set.
