Differences

This shows you the differences between two versions of the page.

--- b:head_first_statistics:variability_and_spread [2020/09/21 14:04] – [Percentile] hkimscil
+++ b:head_first_statistics:variability_and_spread [2023/09/13 08:59] (current) – [Variability and Spread] hkimscil
@@ Line 59: / Line 59: @@
 >
 >
 > sapply(data,sd)
 [1] 1.825742 1.563472 7.362065
@@ Line 87: / Line 88: @@
 아웃라이어의 (극단치의) 문제
-''a <- c(1,1,1,2,2,2,2,3,3,3,3,3,4,4,4,4,5,5,5}
+<code>
-b <- c(1,1,1,2,2,2,2,3,3,3,3,3,4,4,4,4,5,5,5, 10}''
+a <- c(1,1,1,2,2,2,2,3,3,3,3,3,4,4,4,4,5,5,5}
+b <- c(1,1,1,2,2,2,2,3,3,3,3,3,4,4,4,4,5,5,5, 10}
+</code>
 range(a) vs. range(b)
@@ Line 137: / Line 140: @@
 * ( 125 / 100) = 12.5
 이 숫자를 반올림하면 13이므로 13번째 숫자가 10번째 페센타일이 된다 (13).
+<code>
+> k <- c(1:10)
+> length(k)
+[1] 10
+> k
+ [1]  1  2  3  4  5  6  7  8  9 10
+</code>
+th percentile을 구하려면
+$ 20 * (10 /100) = 2 $ 이므로
+번째와 3번째 사이의 점수의 평균이므로, 2.5이다.
+====== Boxplot ======
+<code>
+# j <- c(6,7,7,8,9,10,10,11,11,13)
+j <- c(7,9,9,10,10,10,10,11,11,13)
+# m <- c(3,3,6,7,7,10,10,10,11,13,30)
+m <- c(3,3,6,7,8,9,9,10,11,13,30)
+median(j)
+median(m)
+</code>
+[{{hf.boxplot.ex.jpg}}]
+<code>
+boxplot(j)
+boxplot(m)
+</code>
+<code>
+boxplot(j, m)
+boxplot(j, m, horizontal = T)
+</code>
 ====== Variance ======
@@ Line 154: / Line 197: @@
   * calculation of variance (an easy way) see [[:variance#variance_cal|variance calculation]]
     * $ \displaystyle \frac{\sum(X_{i})}{N} - \mu^2$
+    * [{{variance.cal.jpg?600}}]
 [[:standard deviation]]
+====== Standard score ======
 [[:standard score]]
+$ z = \large\frac {x-\mu}{\sigma} $