This commit is contained in:
marcgauch committed 2022-11-18 21:10:07 +01:00
1 parent afd7d1babf
commit 51cd711da8
2 files changed
+90 -123

No files matched your search

+45 -61
View File
@@ -1494,11 +1494,11 @@ border-radius: 0px;
<div id="preparation" class="section level1" number="1">
<h1><span class="header-section-number">1</span> Preparation</h1>
<pre class="r"><code>if (!require(tidyverse)){
<pre class="r"><code>if (!require(tidyverse)) {
install.packages(&quot;tidyverse&quot;)
library(tidyverse)
}
if (!require(moments)){
if (!require(moments)) {
install.packages(&quot;moments&quot;)
library(moments)
}</code></pre>
@@ -1508,28 +1508,26 @@ if (!require(moments)){
<div id="frequency-table-ordered-from-wish.com" class="section level2" number="2.1">
<h2><span class="header-section-number">2.1</span> Frequency Table
ordered from wish.com</h2>
<pre class="r"><code>freq &lt;- function(data){
na_count = length(data[is.na(data)])
valid_count = length(data)-na_count
<pre class="r"><code>freq &lt;- function(data) {
na_count &lt;- length(data[is.na(data)])
valid_count &lt;- length(data) - na_count
frequency &lt;- table(data)
p &lt;- prop.table(frequency)
percent &lt;- round(p*100, digits = 2)
percent &lt;- round(p * 100, digits = 2)
frequency_sum &lt;- cumsum(frequency)
hkum &lt;- cumsum(p)
percent_sum &lt;- round(hkum*100, digits = 2)
percent_sum &lt;- round(hkum * 100, digits = 2)
freq_table &lt;- cbind(frequency, percent, frequency_sum, percent_sum)
valid_percent &lt;- round(valid_count / length(data)*100, digits = 2)
na_percent &lt;- round(na_count / length(data)*100, digits = 2)
valid_percent &lt;- round(valid_count / length(data) * 100, digits = 2)
na_percent &lt;- round(na_count / length(data) * 100, digits = 2)
print(freq_table)
count &lt;- c(valid_count, na_count, valid_count+na_count)
percent &lt;- c(valid_percent, na_percent, valid_percent+na_percent)
totall &lt;- c(valid_count+na_count, valid_percent+na_percent)
count &lt;- c(valid_count, na_count, valid_count + na_count)
percent &lt;- c(valid_percent, na_percent, valid_percent + na_percent)
df &lt;- data.frame(count, percent, row.names = c(&quot;valid&quot;, &quot;NA&quot;, &quot;Total&quot;))
print(df)
}</code></pre>
<p><em>Source: <a href="https://tellmi.psy.lmu.de/tutorials/deskriptive-statistiken-und-grafiken.html#haeufigkeiten-diskret" class="uri">https://tellmi.psy.lmu.de/tutorials/deskriptive-statistiken-und-grafiken.html#haeufigkeiten-diskret</a>
and adapted</em></p>
@@ -1537,9 +1535,9 @@ and adapted</em></p>
<div id="modus" class="section level2" number="2.2">
<h2><span class="header-section-number">2.2</span> Modus</h2>
<pre class="r"><code>getmode &lt;- function(v) {
uniqv &lt;- unique(v)
x &lt;- tabulate(match(v, uniqv))
uniqv[which(x==max(x))]
uniqv &lt;- unique(v)
x &lt;- tabulate(match(v, uniqv))
uniqv[which(x == max(x))]
}</code></pre>
</div>
</div>
@@ -1816,7 +1814,7 @@ inspection of data</h2>
<div id="converting-strings-to-numbers-and-keine-antwort-zu-nan" class="section level2" number="4.1">
<h2><span class="header-section-number">4.1</span> Converting Strings to
numbers and <em>Keine Antwort</em> zu <em>NaN</em></h2>
<pre class="r"><code>litdata &lt;- litdata %&gt;%
<pre class="r"><code>litdata &lt;- litdata %&gt;%
mutate_all(~ replace(., . == &quot;Stimme voll zu5&quot;, 5)) %&gt;%
mutate_all(~ replace(., . == &quot;Stimme überhaupt nicht zu1&quot;, 1)) %&gt;%
mutate_all(~ replace(., . == &quot;Keine Antwort-&quot;, NaN))</code></pre>
@@ -1826,17 +1824,17 @@ numbers and <em>Keine Antwort</em> zu <em>NaN</em></h2>
<p>The following code will <strong>NOT</strong> be run. The Idea is to
show a way to automatically edit all columns. It works but some columns
are NOT numeric.</p>
<pre class="r"><code> # All colnames that exist
litdataColnames &lt;- colnames(litdata)
# the ones we don&#39;t want to change
litdataNonNumericCols &lt;- c(&quot;submitdate&quot;, &quot;startlanguage&quot;, &quot;startdate&quot;, &quot;datestamp&quot;, &quot;lastpage&quot;, &quot;seed&quot;)
# the colnames that should be changed
litdataColsToMakeNumeric &lt;- litdataColnames[!(litdataColnames %in% litdataNonNumericCols)]
print(litdataColsToMakeNumeric)
litdataColsToMakeNumeric &lt;- c(&quot;R1&quot;)
for (col in litdataColsToMakeNumeric) {
litdata[[col]] &lt;- as.numeric(litdata[[col]])
}</code></pre>
<pre class="r"><code># All colnames that exist
litdataColnames &lt;- colnames(litdata)
# the ones we don&#39;t want to change
litdataNonNumericCols &lt;- c(&quot;submitdate&quot;, &quot;startlanguage&quot;, &quot;startdate&quot;, &quot;datestamp&quot;, &quot;lastpage&quot;, &quot;seed&quot;)
# the colnames that should be changed
litdataColsToMakeNumeric &lt;- litdataColnames[!(litdataColnames %in% litdataNonNumericCols)]
print(litdataColsToMakeNumeric)
litdataColsToMakeNumeric &lt;- c(&quot;R1&quot;)
for (col in litdataColsToMakeNumeric) {
litdata[[col]] &lt;- as.numeric(litdata[[col]])
}</code></pre>
<p>First we rename all the columns</p>
<pre class="r"><code>litdata &lt;- litdata %&gt;% rename(
&quot;A1&quot; = &quot;W001&quot;,
@@ -1848,7 +1846,6 @@ are NOT numeric.</p>
&quot;A7&quot; = &quot;W007&quot;,
&quot;A8&quot; = &quot;W008&quot;,
&quot;A9&quot; = &quot;W009&quot;,
&quot;B1&quot; = &quot;K001&quot;,
&quot;B2&quot; = &quot;K002&quot;,
&quot;B3&quot; = &quot;K003&quot;,
@@ -1858,37 +1855,30 @@ are NOT numeric.</p>
&quot;B7&quot; = &quot;K007&quot;,
&quot;B8&quot; = &quot;K008&quot;,
&quot;B9&quot; = &quot;K009&quot;,
&quot;C1_1&quot; = &quot;TK001_01&quot;,
&quot;C1_2&quot; = &quot;TK001_02&quot;,
&quot;C1_3&quot; = &quot;TK001_03&quot;,
&quot;C1_4&quot; = &quot;TK001_04&quot;,
&quot;C2_1&quot; = &quot;TK002_01&quot;,
&quot;C2_2&quot; = &quot;TK002_02&quot;,
&quot;C2_3&quot; = &quot;TK002_03&quot;,
&quot;C2_4&quot; = &quot;TK002_04&quot;,
&quot;C3_1&quot; = &quot;TK003_01&quot;,
&quot;C3_2&quot; = &quot;TK003_02&quot;,
&quot;C3_3&quot; = &quot;TK003_03&quot;,
&quot;C3_4&quot; = &quot;TK003_04&quot;,
&quot;C4_1&quot; = &quot;TK004_01&quot;,
&quot;C4_2&quot; = &quot;TK004_02&quot;,
&quot;C4_3&quot; = &quot;TK004_03&quot;,
&quot;C4_4&quot; = &quot;TK004_04&quot;,
&quot;C5_1&quot; = &quot;TK005_01&quot;,
&quot;C5_2&quot; = &quot;TK005_02&quot;,
&quot;C5_3&quot; = &quot;TK005_03&quot;,
&quot;C5_4&quot; = &quot;TK005_04&quot;,
&quot;C6_1&quot; = &quot;TK006_01&quot;,
&quot;C6_2&quot; = &quot;TK006_02&quot;,
&quot;C6_3&quot; = &quot;TK006_03&quot;,
&quot;C6_4&quot; = &quot;TK006_04&quot;,
&quot;D1_1&quot; = &quot;H001_001&quot;,
&quot;D1_2&quot; = &quot;H001_002&quot;,
&quot;D1_3&quot; = &quot;H001_003&quot;,
@@ -1896,23 +1886,15 @@ are NOT numeric.</p>
&quot;D1_5&quot; = &quot;H001_005&quot;,
&quot;D1_6&quot; = &quot;H001_006&quot;,
&quot;D1_7&quot; = &quot;H001_007&quot;,
&quot;D2&quot; = &quot;H002&quot;,
&quot;D3&quot; = &quot;H003&quot;,
&quot;D4&quot; = &quot;H004&quot;,
&quot;D4_comment&quot; = &quot;H004_other&quot;,
&quot;D5&quot; = &quot;H005&quot;,
&quot;D5_comment&quot; = &quot;H005_other&quot;,
&quot;D6&quot; = &quot;H006&quot;,
&quot;D7&quot; = &quot;H007&quot;,
&quot;D8&quot; = &quot;H008&quot;,
&quot;E1&quot; = &quot;R1&quot;
)</code></pre>
<p>Then we change the datatype and fix the values</p>
@@ -2278,16 +2260,18 @@ Data</h2>
tmp &lt;- rename(tmp, value = all_of(column))
tmp &lt;- tmp %&gt;%
count(value) %&gt;%
mutate(percentage = prop.table(n)*100)
mutate(percentage = prop.table(n) * 100)
print(tmp, n = 100)
ggplot(tmp,
aes(x = value, y=n)) +
geom_bar(stat = &quot;identity&quot;) +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
ggplot(
tmp,
aes(x = value, y = n)
) +
geom_bar(stat = &quot;identity&quot;) +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
}</code></pre>
<div id="a3-w003" class="section level3 unnumbered">
<h3 class="unnumbered">A3 (W003)</h3>
<pre class="r"><code> displayFunction1(litdata, &quot;A3&quot;)</code></pre>
<pre class="r"><code>displayFunction1(litdata, &quot;A3&quot;)</code></pre>
<pre><code>## # A tibble: 6 × 3
## value n percentage
## &lt;dbl&gt; &lt;int&gt; &lt;dbl&gt;
@@ -2302,7 +2286,7 @@ Data</h2>
</div>
<div id="b3-k003" class="section level3 unnumbered">
<h3 class="unnumbered">B3 (K003)</h3>
<pre class="r"><code> displayFunction1(litdata, &quot;B3&quot;)</code></pre>
<pre class="r"><code>displayFunction1(litdata, &quot;B3&quot;)</code></pre>
<pre><code>## # A tibble: 7 × 3
## value n percentage
## &lt;dbl&gt; &lt;int&gt; &lt;dbl&gt;
@@ -2318,7 +2302,7 @@ Data</h2>
</div>
<div id="d1_1-h001_001" class="section level3 unnumbered">
<h3 class="unnumbered">D1_1 (H001_001)</h3>
<pre class="r"><code> displayFunction1(litdata, &quot;D1_1&quot;)</code></pre>
<pre class="r"><code>displayFunction1(litdata, &quot;D1_1&quot;)</code></pre>
<pre><code>## # A tibble: 3 × 3
## value n percentage
## &lt;lgl&gt; &lt;int&gt; &lt;dbl&gt;
@@ -2329,7 +2313,7 @@ Data</h2>
</div>
<div id="d5-h005" class="section level3 unnumbered">
<h3 class="unnumbered">D5 (H005)</h3>
<pre class="r"><code> displayFunction1(litdata, &quot;D5&quot;)</code></pre>
<pre class="r"><code>displayFunction1(litdata, &quot;D5&quot;)</code></pre>
<pre><code>## # A tibble: 18 × 3
## value n percentage
## &lt;fct&gt; &lt;int&gt; &lt;dbl&gt;
@@ -2355,7 +2339,7 @@ Data</h2>
</div>
<div id="d7-h007" class="section level3 unnumbered">
<h3 class="unnumbered">D7 (H007)</h3>
<pre class="r"><code> displayFunction1(litdata, &quot;D7&quot;)</code></pre>
<pre class="r"><code>displayFunction1(litdata, &quot;D7&quot;)</code></pre>
<pre><code>## # A tibble: 24 × 3
## value n percentage
## &lt;dbl&gt; &lt;int&gt; &lt;dbl&gt;
@@ -2390,7 +2374,7 @@ gibt.</p>
</div>
<div id="d8-h008" class="section level3 unnumbered">
<h3 class="unnumbered">D8 (H008)</h3>
<pre class="r"><code> displayFunction1(litdata, &quot;D8&quot;)</code></pre>
<pre class="r"><code>displayFunction1(litdata, &quot;D8&quot;)</code></pre>
<pre><code>## # A tibble: 3 × 3
## value n percentage
## &lt;fct&gt; &lt;int&gt; &lt;dbl&gt;
@@ -2407,7 +2391,7 @@ gibt.</p>
<pre class="r"><code>birthyears &lt;- litdata$D7
# remove NAs
birthyears &lt;- birthyears[!is.na(birthyears)]
age &lt;- 2021-birthyears</code></pre>
age &lt;- 2021 - birthyears</code></pre>
<div id="frequency" class="section level2" number="6.1">
<h2><span class="header-section-number">6.1</span> Frequency</h2>
<pre class="r"><code>freq(age)</code></pre>
@@ -2440,7 +2424,7 @@ age &lt;- 2021-birthyears</code></pre>
## NA 0 0
## Total 106 100</code></pre>
<pre class="r"><code># with NA
freq(2021-litdata$D7)</code></pre>
freq(2021 - litdata$D7)</code></pre>
<pre><code>## frequency percent frequency_sum percent_sum
## 19 1 0.94 1 0.94
## 20 2 1.89 3 2.83
@@ -2492,7 +2476,7 @@ Mittelwert</h3>
</div>
<div id="spannweite" class="section level3" number="6.2.4">
<h3><span class="header-section-number">6.2.4</span> Spannweite</h3>
<pre class="r"><code>max(age)-min(age)</code></pre>
<pre class="r"><code>max(age) - min(age)</code></pre>
<pre><code>## [1] 31</code></pre>
</div>
<div id="quartilsabstand" class="section level3" number="6.2.5">
@@ -2643,7 +2627,7 @@ sozialen Herkunft 5.6, er ist also genauso hoch wie in der
Gesamtschweiz. Was ist zur Lage dieses Wertes bezogen auf die Verteilung
in Graubünden zu sagen? Also: Wie viele Schüler in GR liegen mit ihrem
Wert darunter?</p>
<pre class="r"><code>pnorm(5.6, mean = 5.1, sd=2.0)</code></pre>
<pre class="r"><code>pnorm(5.6, mean = 5.1, sd = 2.0)</code></pre>
<pre><code>## [1] 0.5987063</code></pre>
</div>
</div>