Random graphs (39): Plotting on a log axis

Rather than looking at a variable in absolute terms, namely GDP per capita in the upper panel of the Figure, it is also sometimes helpful to look at it in terms of percentage increases, as in the lower panel. Equal distances on the x-axis refer to equal percentage increases in GDP per capita. Four equidistant points on the x-axis are labeled, each indicating a fourfold increase in GDP.

use wvs2005_v20090901a.dta, clear

// Country variable
// 1) Turn into string
decode v2, gen(ctry)

// 2) Abbreviate
kountry ctry, from(other) stuck marker
ren _ISO3N_ cntry
kountry cntry, from(iso3n) to(iso2c)
ren _ISO2C_ country

// Generate outcome: % in good health
generate goodhealth = 100 if v11 <= 2
replace  goodhealth =   0 if v11  > 2
replace  goodhealth =   . if v11 == .

// Collapse data set
collapse (mean) goodhealth [pw = v259], by(country)

// Generate year variable
gen year = 2006

// Preserve collapsed data set
preserve

// Get GDP from World Bank data base
wbopendata, language(en - English) country() topics() indicator(NY.GDP.PCAP.PP.CD) clear long

// Fix obtained data set
ren ny_gdp_pcap_pp_cd gdp
ren iso2code country
keep if year == 2006
keep gdp country
drop if country == ""

// Save obtained GDP data
tempfile gdp
save `gdp'

// Restore 
restore

// Merge GDP with collapsed data set
merge m:1 country using `gdp'
keep if _merge == 3
drop _merge

// Create labels with thousand separator
label define gdp 20000 "20,000" ///
                 40000 "40,000" ///
                 60000 "60,000"
label val gdp gdp

// Plot on unlogged axis
twoway (scatter goodhealth gdp, mlabel(country) mlabpos(0) msymbol(none)) ///
       (lfit goodhealth gdp) ///
      , legend(off) xtitle("GDP per capita, 2006, PPP in current international $") ///    
        ytitle("% in good health") ///
        xlabel(0(20000)60000, valuelabels) ///
        name(unlogged, replace)

// Generate logged variable
gen loggdp = log(gdp) * 1000  // Multiply by 1,000 because only integers can be labeled

// Generate numbers for labeling
//  Round them to three decimal digits, then multiply by 1,000 to get integers
local log1 = round(log(1000), .001) * 1000
local log2 = round(log(1000 * 4), .001) * 1000
local log3 = round(log(1000 * 4 * 4), .001) * 1000
local log4 = round(log(1000 * 4 * 4 * 4), .001) *1000

*di `log1' _skip(2) `log2' _skip(2) `log3' _skip(2) `log4' 

// Create labels for numbers to be labeled
label define loggdp `log1' "1,000" ///
                    `log2' "4,000" ///
                    `log3' "16,000" ///                    
                    `log4' "64,000"
label value loggdp loggdp

// Plot on log axis
twoway (scatter goodhealth loggdp, mlabel(country) mlabpos(0) msymbol(none)) ///
       (lfit goodhealth loggdp) ///
      , legend(off) xtitle("GDP per capita, 2006, PPP in current international $") ///   
        ytitle("% in good health") ///
        xlabel(`log1' `log2' `log3' `log4', valuelabels) ///
        name(logged, replace)

// Combine plots
graph combine unlogged logged, col(1) ysize(8)

Random graphs (14): Combining dot plots

collapse (mean) incocomp, by(quintile)

graph dot incocomp, ///
      over(quintile, relabel(1 `""1" "(poorest)""'  5 `""5" "(richest)""')) ///
      vertical /// // Labels with line break
      ytitle("Income comparison orientation") ///
      yscale(range(1.5 3.0)) ///
      ylabel(1.5 (.25) 3.0, format(%6.2f)) /// // Format axis numbering
      exclude0 ///
      b1title("Income quintile averages") /// // Label over() axis
      name(byquintile, replace) ///
      fxsize(50) // Reduce size for combining

restore 
collapse (mean) incocomp, by(cntry)

// Create neatly ordered variable for x-axis
egen order = rank(-incocomp), unique
encode cntry, gen(geo)
labmask order, value(geo) decode

graph dot incocomp, over(order, label(alternate)) vertical ///
          ytitle("Income comparison orientation") ///
          name(bycountry, replace) ///
          ylabel(1.5 (.25) 3.0, format(%6.2f)) exclude0 yscale(off) ///
   b1title("Country averages") fxsize(100)

graph combine byquintile bycountry, xsize(6) ycommon imargin(zero)

restore
collapse (mean) incocomp, by(quintile cntry)

// Get data into proper shape
sort cntry quintile
reshape wide incocomp, i(cntry) j(quintile)

// Create ordered variable for x-axis labels
gen diff = incocomp5 - incocomp1 // Income comparison gap
egen order = rank(incocomp5), unique
encode cntry, gen(geo)
labmask order, value(geo) decode
sort order

// Create variables as marker labels
gen incocomp1l = 1
gen incocomp3l = 3
gen incocomp5l = 5

twoway (pcspike incocomp1 order incocomp5 order, lcolor(gs14)) ///
       (scatter incocomp1 order, mlabel(incocomp1l) mlabpos(0) msymbol(none)) ///
       (scatter incocomp5 order, mlabel(incocomp5l) mlabpos(0) msymbol(none)) ///
        , xlab(1/23, valuelabels ang(v)) ///
   ytitle("Average income comparison orientation") ///
   ylabel(, format(%6.1f)) ///
   xtitle("") ///
   name(bycountry, replace) ///
   legend(label(1 "Test") ///
          label(2 "1 First quintile (poorest)") ///
   label(3 "5 Fifth quintile (richest)") ///
   order(2 3) ring(0) pos(5))