<div dir="ltr"><div><div>Estimados<br><br></div>Soy un nuevo usario de R, y estoy usando como base de datos el European Social Survey, que tiene datos de 40,000 individuos, y alrededor de 23 países europeos. Lo que he seleccionado es la útima ola, el round 7, para el año 2014.<br><br></div>He leido los datos, desde SPSS y aquí tienen la base de datos y que tipo de objetos se han generado, y tambíen la distribución por pais de la muestra. No he usado los weights del survey todavía, solo estoy explorando los datos.<br>
<p class="gmail-SourceCode"><span class="gmail-KeywordTok"><span lang="EN-US">class</span></span><span class="gmail-NormalTok"><span lang="EN-US">(ess)</span></span><span lang="EN-US"></span></p>
<p class="gmail-SourceCode"><span class="gmail-VerbatimChar"><span lang="EN-US">## [1]
"lbl_df"<span>
</span>"data.frame"</span></span><span lang="EN-US"></span></p>
<p class="gmail-SourceCode"><span class="gmail-KeywordTok"><span lang="EN-US">frq</span></span><span class="gmail-NormalTok"><span lang="EN-US">(ess$cntry)</span></span><span lang="EN-US"></span></p>
<p class="gmail-SourceCode"><span class="gmail-VerbatimChar"><span lang="EN-US">## # Country</span></span><span lang="EN-US"><br>
<span class="gmail-VerbatimChar">## </span><br>
<span class="gmail-VerbatimChar">##<span> </span>val<span> </span>label<span>
</span>frq raw.prc valid.prc cum.prc</span><br>
<span class="gmail-VerbatimChar">##<span> </span>1<span> </span>Austria 1795<span> </span>4.47<span>
</span>4.47<span> </span>4.47</span><br>
<span class="gmail-VerbatimChar">##<span> </span>2<span> </span>Belgium 1769<span> </span>4.40<span>
</span>4.40<span> </span>8.87</span><br>
<span class="gmail-VerbatimChar">##<span> </span>3<span> </span>Switzerland 1532<span> </span>3.81<span>
</span>3.81<span> </span>12.68</span><br>
<span class="gmail-VerbatimChar">##<span> </span>4 Czech
Republic 2148<span> </span>5.35<span> </span>5.35<span>
</span>18.03</span><br>
<span class="gmail-VerbatimChar">##<span> </span>5<span> </span>Germany 3045<span> </span>7.58<span>
</span>7.58<span> </span>25.60</span><br>
<span class="gmail-VerbatimChar">##<span> </span>6<span> </span>Denmark 1502<span> </span>3.74<span>
</span><span> </span>3.74<span> </span>29.34</span><br>
<span class="gmail-VerbatimChar">##<span> </span>7<span> </span>Estonia 2051<span> </span>5.10<span>
</span>5.10<span> </span>34.45</span><br>
<span class="gmail-VerbatimChar">##<span> </span>8<span> </span>Spain 1925<span> </span>4.79<span>
</span>4.79<span> </span>39.24</span><br>
<span class="gmail-VerbatimChar">##<span> </span>9<span> </span>Finland 2087<span> </span>5.19<span>
</span>5.19<span> </span>44.43</span><br>
<span class="gmail-VerbatimChar">##<span> </span>10<span> </span>France 1917<span> </span>4.77<span>
</span>4.77<span> </span>49.20</span><br>
<span class="gmail-VerbatimChar">##<span> </span>11 United
Kingdom 2264<span> </span>5.63<span> </span>5.63<span>
</span>54.83</span><br>
<span class="gmail-VerbatimChar">##<span> </span>12<span> </span>Hungary 1698<span> </span>4.23<span>
</span>4.23<span> </span>59.06</span><br>
<span class="gmail-VerbatimChar">##<span> </span>13<span> </span>Ireland 2390<span> </span>5.95<span>
</span>5.95<span> </span>65.01</span><br>
<span class="gmail-VerbatimChar">##<span> </span>14<span> </span>Israel 2562<span> </span>6.38<span>
</span>6.38<span> </span>71.38</span><br>
<span class="gmail-VerbatimChar">##<span> </span>15<span> </span>Lithuania 2250<span> </span>5.60<span>
</span>5.60<span> </span>76.98</span><br>
<span class="gmail-VerbatimChar">##<span> </span>16<span> </span>Netherlands 1919<span> </span>4.78<span>
</span>4.78<span> </span>81.76</span><br>
<span class="gmail-VerbatimChar">##<span> </span>17<span> </span>Norway 1436<span> </span>3.57<span>
</span>3.57<span> </span>85.33</span><br>
<span class="gmail-VerbatimChar">##<span> </span>18<span> </span>Poland 1615<span> </span>4.02<span>
</span>4.02<span> </span>89.35</span><br>
<span class="gmail-VerbatimChar">##<span> </span>19<span> </span>Portugal 1265<span> </span>3.15<span>
</span>3.15<span> </span>92.50</span><br>
<span class="gmail-VerbatimChar">##<span> </span>20<span> </span>Sweden 1791<span> </span>4.46<span>
</span>4.46<span> </span>96.95</span><br>
<span class="gmail-VerbatimChar">##<span> </span>21<span> </span>Slovenia 1224<span> </span>3.05<span>
</span>3.05<span> </span>100.00</span><br>
<span class="gmail-VerbatimChar">##<span> </span>NA<span> </span>NA<span> </span>0<span>
</span>0.00<span> </span>NA<span> </span>NA</span></span></p>
Ahora voy a hacer un histograma de la variable satisfaccion con la vida, cuyo rango es de 0-10 (numeros enteros, donde mayor valor indica mayor satisfacción con la vida.<br><div>
<p class="gmail-SourceCode"><span class="gmail-KeywordTok"><span lang="EN-US">get_labels</span></span><span class="gmail-NormalTok"><span lang="EN-US">(ess$stflife)</span></span><span lang="EN-US"></span></p>
<p class="gmail-SourceCode"><span class="gmail-VerbatimChar"><span lang="EN-US"><br></span></span><span lang="EN-US"><span class="gmail-VerbatimChar"></span></span></p>
<p class="gmail-SourceCode"><span class="gmail-VerbatimChar"><span lang="EN-US">##<span> </span>[1] "Extremely dissatisfied"
"1"<span> </span></span></span><span lang="EN-US"><br>
<span class="gmail-VerbatimChar">##<span> </span>[3]
"2"<span>
</span>"3"<span> </span><span> </span></span><br>
<span class="gmail-VerbatimChar">##<span> </span>[5]
"4"<span>
</span>"5"<span> </span></span><br>
<span class="gmail-VerbatimChar">##<span> </span>[7]
"6"<span>
</span>"7"<span> </span></span><br>
<span class="gmail-VerbatimChar">##<span> </span>[9]
"8"<span>
</span>"9"<span> </span></span><br>
<span class="gmail-VerbatimChar">## [11] "Extremely satisfied"<span> </span>"Refusal"<span> </span></span><span class="gmail-VerbatimChar"><br></span></span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar">## [13] "Don't know"<span> </span>"No answer"</span></span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar"></span></span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar">Lo que he hecho es hacer una tabla de la distribución de esa variable para un sólo pais Dinamarca (DK)<br></span></span></p>
<div><div><div>
<p class="gmail-SourceCode"><span class="gmail-KeywordTok"><span lang="EN-US">flat_table</span></span><span class="gmail-NormalTok"><span lang="EN-US">(</span></span><span class="gmail-KeywordTok"><span lang="EN-US">subset</span></span><span class="gmail-NormalTok"><span lang="EN-US">(ess,
cntry %in%</span></span><span class="gmail-StringTok"><span lang="EN-US"> </span></span><span class="gmail-KeywordTok"><span lang="EN-US">c</span></span><span class="gmail-NormalTok"><span lang="EN-US">(</span></span><span class="gmail-StringTok"><span lang="EN-US">"DK"</span></span><span class="gmail-NormalTok"><span lang="EN-US">)), stflife, </span></span><span class="gmail-DataTypeTok"><span lang="EN-US">margin=</span></span><span class="gmail-NormalTok"><span lang="EN-US"> </span></span><span class="gmail-StringTok"><span lang="EN-US">"row"</span></span><span class="gmail-NormalTok"><span lang="EN-US">)</span></span><span lang="EN-US"></span></p>
<p class="gmail-SourceCode"><span class="gmail-VerbatimChar"><span lang="EN-US">## x<span> </span>0<span>
</span>1<span> </span>2<span> </span>3<span>
</span>4<span> </span>5<span> </span>6<span>
</span>7<span> </span>8<span> </span>9<span>
</span>10</span></span><span lang="EN-US"><br>
<span class="gmail-VerbatimChar">##<span> </span><span> </span></span><br>
</span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar">##<span> </span>0.33<span> </span>0.27<span>
</span>0.47<span> </span>1.33<span> </span>0.93<span>
</span>2.87<span> </span>3.67<span> </span>8.20 28.40 29.53 24.00</span></span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar"><br></span></span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar">Sin embargo al hacer un histrogama para los paises con ggplot, anda algo mal con los porcentajes. Por ejemplo sabemos que un 24 % respondió que están muy satisfechos en DK. Sin embargo</span></span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar">los porcentajes son muy pequeños.<br></span></span></p><p class="gmail-SourceCode"><span lang="EN-US"><span class="gmail-VerbatimChar"></span></span></p><p class="gmail-SourceCode"><br>
</p><p class="gmail-SourceCode"><span class="gmail-NormalTok"><span lang="EN-US">myplot =</span></span><span class="gmail-StringTok"><span lang="EN-US"> </span></span><span class="gmail-KeywordTok"><span lang="EN-US">ggplot</span></span><span class="gmail-NormalTok"><span lang="EN-US">(ess, </span></span><span class="gmail-KeywordTok"><span lang="EN-US">aes</span></span><span class="gmail-NormalTok"><span lang="EN-US"> (stflife)) +</span></span><span class="gmail-StringTok"><span lang="EN-US"> </span></span><span lang="EN-US"><br>
<span class="gmail-StringTok"><span> </span></span><span class="gmail-KeywordTok">geom_bar</span><span class="gmail-NormalTok">(</span><span class="gmail-KeywordTok">aes</span><span class="gmail-NormalTok">(</span><span class="gmail-DataTypeTok">y =</span><span class="gmail-NormalTok"> (..count..)/</span><span class="gmail-KeywordTok">sum</span><span class="gmail-NormalTok">(..count..))) +</span><br>
<span class="gmail-StringTok"><span> </span></span><span class="gmail-KeywordTok">scale_y_continuous</span><span class="gmail-NormalTok">(</span><span class="gmail-DataTypeTok">labels=</span><span class="gmail-NormalTok">scales::percent) +</span><br>
<span class="gmail-StringTok"><span> </span></span><span class="gmail-KeywordTok">ylab</span><span class="gmail-NormalTok">(</span><span class="gmail-StringTok">"Relative frequencies"</span><span class="gmail-NormalTok">)
+</span><span class="gmail-StringTok"> </span><span class="gmail-KeywordTok">facet_wrap</span><span class="gmail-NormalTok">(~cntry)</span><br>
<br>
<span class="gmail-KeywordTok">plot</span><span class="gmail-NormalTok">(myplot)</span></span></p>
<span style="font-size:12pt;font-family:"Cambria",serif" lang="EN-US"><br></span></div><img src="cid:ii_15cbc02d4211ee37" alt="Inline images 1" width="481" height="385"><br><div><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div dir="ltr"><br></div></div></div></div></div>
</div></div></div></div></div>