Differences

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

--- c:ms:2025:schedule:week06_t-test_and_anova_note [2025/04/10 10:25] – [t-test] hkimscil
+++ c:ms:2025:schedule:week06_t-test_and_anova_note [2025/04/14 08:35] (current) – [t-test, different approach] hkimscil
@@ Line 73: / Line 73: @@
 [1] -2.13145
 > qt(0.025, df=150000000000000)
+[1] -1.959964
+> # 샘플사이즈가 충분히 크면 qt값과 qnorm값이 동일한
+> # 1.96임을 주의
+> qnorm(0.025)
 [1] -1.959964
 >
@@ Line 458: / Line 462: @@
 abline(v = mean.a, lty=2, lwd=3, col="blue")
 abline(v = mean.b, lty=2, lwd=3, col="darkgreen")
+# or
+hist(A, xlim=c(0,50), ylim=c(0,8), col="red")
+hist(B, add=T, col=rgb(0, 1, 0, 0.5))
+abline(v=mean(dat), col="black")
+abline(v=mean(A), col="red")
+abline(v=mean(B), col="darkgreen")
 </code>
@@ Line 533: / Line 544: @@
 f.calculated.pvalue <- 1-pf(f.calculated, df1=df.between, df2=df.within)
 f.calculated.pvalue
+</code>
+<code>
+x <- rf(500000, df1 = df.between, df2 = df.within)
+hist(x,
+     breaks = "Scott",
+     freq = FALSE,
+     xlim = c(0, 7),
+     ylim = c(0, 3),
+     xlab = "",
+     main = "Histogram for a F-distribution
+     with df1 = 1 and df2 = 30",
+     cex.main = 0.9
+)
+curve(df(x, df1 = df.between, df2 = df.within),
+      from = 0, to = 8, n = 5000,
+      col = "red", lwd = 2,
+      add = T)
+abline(v=f.calculated, col="blue", lwd=2, lty="dotted")
+f.calculated.pvalue
+- f.calculated.pvalue
+</code>
+<code>
 # 한편,  t test를 했었을 때 (A, B 그룹을 가지고 independent
 # samples t-test를) 아웃 풋은
@@ Line 644: / Line 680: @@
 > abline(v = mean.b, lty=2, lwd=3, col="darkgreen")
 >
+> # or
+> hist(A, xlim=c(0,50), ylim=c(0,8), col="red")
+> hist(B, add=T, col=rgb(0, 1, 0, 0.5))
+> abline(v=mean(dat), col="black")
+> abline(v=mean(A), col="red")
+> abline(v=mean(B), col="darkgreen")
 </code>
 {{c:ms:2025:schedule:pasted:20250409-075631.png?550}}
+{{:c:ms:2025:schedule:pasted:20250414-083514.png?550}}
 <code>
 > # mean.total 에서 그룹a의 평균까지의 차이를 구한 후