Differences

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

--- using_dummy_variables [2018/05/14 09:01] – [2 variables, categorical] hkimscil
+++ using_dummy_variables [2019/10/18 10:18] (current) – hkimscil
@@ Line 2: / Line 2: @@
 ===== 2 groups =====
 data:
-{{:elemapi2.sav}} \\
+{{:elemapi2.sav}}
-{{elemapi2_categories.sps}} \\
+{{:elemapi2_categories.sps}}
+{{:elemapi2.csv}}
+in r <code>datavar <- read.csv("http://commres.net/wiki/_media/r/elemapi2.csv")</code>
 <code>	Variable Labels
@@ Line 107: / Line 110: @@
 만약에 ANOVA 테스트에서와 같이 종류가 3개 이상인 변인은 어떻게 처리해야 할까? 아래는 이를 regression으로 테스트 한 결과이다.
-<code>		Model Summary
+<code>
-Model	R	R Square	Adjusted R Square	Std. Error of the Estimate
+> mod2 <- lm(api00 ~ factor(mealcat), data=datavar)
-	.867a	.752		.752			70.908
+> mod2
-a. Predictors: (Constant), Percentage free meals in 3 categories
+Call:
+lm(formula = api00 ~ factor(mealcat), data = datavar)
+Coefficients:
+     (Intercept)  factor(mealcat)2  factor(mealcat)3
+.7            -166.3            -301.3
+> summary(mod2)
+Call:
+lm(formula = api00 ~ factor(mealcat), data = datavar)
+Residuals:
+     Min       1Q   Median       3Q      Max
+-253.394  -47.883    0.282   52.282  185.620
+Coefficients:
+                 Estimate Std. Error t value Pr(>|t|)
+(Intercept)       805.718      6.169  130.60   <2e-16 ***
+factor(mealcat)2 -166.324      8.708  -19.10   <2e-16 ***
+factor(mealcat)3 -301.338      8.629  -34.92   <2e-16 ***
+---
+Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
-			ANOVA(b)
+Residual standard error: 70.61 on 397 degrees of freedom
-Model			Sum of Squares	df	Mean Square	F		Sig.
+Multiple R-squared:  0.7548,	Adjusted R-squared:  0.7536
-	Regression	6072527.519	1	6072527.519	1207.742	.000a
+F-statistic: 611.1 on 2 and 397 DF,  p-value: < 2.2e-16
-	Residual	2001144.479	398	5028.001
-	Total		8073671.997	399
-a. Predictors: (Constant), Percentage free meals in 3 categories
-b. Dependent Variable: api 2000
-			Coefficients(a)
+>
-		Unstandardized Coefficients		Standardized Coefficients
-Model		B			Std. Error	Beta	t	Sig.
-	(Constant)	950.987		9.422		100.935		.000
-	Percentage of 	-150.553	4.332		-.867	-34.753	.000
-	free meals in
-categories
-a. Dependent Variable: api 2000
 </code>