Dummy Variables in R - Revision history

Rb: /* Interaction terms */

2015-07-10T08:40:26Z

‎Interaction terms

Rb: /* Using factor variables directly */

2015-07-07T15:50:14Z

‎Using factor variables directly

Rb: /* Using factor variables directly */

2015-07-07T15:48:13Z

‎Using factor variables directly

Rb at 15:47, 7 July 2015

2015-07-07T15:47:03Z

Rb at 15:25, 7 July 2015

2015-07-07T15:25:49Z

Rb at 15:23, 7 July 2015

2015-07-07T15:23:07Z

Rb at 15:07, 7 July 2015

2015-07-07T15:07:48Z

Rb: /* Translating into dummy variables */

2015-07-07T14:57:07Z

‎Translating into dummy variables

Rb at 14:56, 7 July 2015

2015-07-07T14:56:31Z

Rb at 14:54, 7 July 2015

2015-07-07T14:54:59Z

@@ Line 83: / Line 83: @@
       F-statistic: 60.66 on 3 and 349 DF,  p-value: < 2.2e-16
-It has included the simple explanatory variables <source enclose=none>years</source></ref> and <source enclose=none>black</source></ref>. To understand this we need to understand that in the context of model building (which is what we do here) R understands the operator <source enclose=none>*</source> as an invitation to include the variables itself and its cross term<ref>See [http://stat.ethz.ch/R-manual/R-patched/library/stats/html/formula.html] for details.</ref>. This is, at times, very convenient as this is often what you want to do.
+It has included the simple explanatory variables <source enclose=none>years</source> and <source enclose=none>black</source>. To understand this we need to understand that in the context of model building (which is what we do here) R understands the operator <source enclose=none>*</source> as an invitation to include the variables itself and its cross term<ref>See [http://stat.ethz.ch/R-manual/R-patched/library/stats/html/formula.html] for details.</ref>. This is, at times, very convenient as this is often what you want to do.
 But, if we want to include cross terms only we need to use the operator <source enclose=none>:</source> instead of <source enclose=none>*</source>. So

@@ Line 165: / Line 165: @@
 Inherent in a factor variable in R is that R uses one of the values as its reference value and by default this is the value first in the alphabet as we saw in the above regression. There is, however, a way to let R know to change the reference value. The way to do this is as follows:
-      mydata$position <- relevel(mydata$position, ref = "outfielder")
+      mydata<source enclose=none>$</source>position <- relevel(mydata<source enclose=none>$</source>position, ref = "outfielder")
 This ensures that from now on R will use "outfielder" as the reference. If you know run the same regression as above

@@ Line 161: / Line 161: @@
       F-statistic: 77.24 on 7 and 345 DF,  p-value: < 2.2e-16
-When you compare the summary statistics to those of the first regression we estimated in this [[Dummy_Variables_in_R#Dummy_variables_as_independent_variables|dummy variable section]], then you will realise that they are identical, we essentially estimated the same model. There is, however, one difference. In the previous estimation we use outfielders as the base category (i.e. the respective dummy variables was excluded). Here we can see that R automatically includes dummy variables for the different positions, but for one, here the catcher the position. R chose to drop the catcher position as this is the position which comes first in the alphabet.
+When you compare the summary statistics to those of the first regression we estimated in this [[Dummy_Variables_in_R#Dummy_variables_as_independent_variables|dummy variable section]], then you will realise that they are identical, we essentially estimated the same model. There is, however, one difference. In the previous estimation we use outfielders as the base category (i.e. the respective dummy variables was excluded). Here we can see that R automatically includes dummy variables for the different positions, but for one, here the catcher position. R chose to drop the catcher position as this is the position which comes first in the alphabet.
 Inherent in a factor variable in R is that R uses one of the values as its reference value and by default this is the value first in the alphabet as we saw in the above regression. There is, however, a way to let R know to change the reference value. The way to do this is as follows:

@@ Line 161: / Line 161: @@
       F-statistic: 77.24 on 7 and 345 DF,  p-value: < 2.2e-16
-When you compare the summary statistics to those of the first regression we estimated in this [[Dummy_Variables_in_R#Dummy_variables_as_independent_variables|dummy variable section]], then you will realise that they are identical, we essentially estimated the same model. There is, however, one difference. In the previous estimation we use outfielders as the base category (i.e. the respective dummy variables was excluded). Here we can see that R automatically includes dummy variables for the different positions, but for one, here the catcher the position. R chose to drop the cather position as this is the position which comes first in the alphabet.
+When you compare the summary statistics to those of the first regression we estimated in this [[Dummy_Variables_in_R#Dummy_variables_as_independent_variables|dummy variable section]], then you will realise that they are identical, we essentially estimated the same model. There is, however, one difference. In the previous estimation we use outfielders as the base category (i.e. the respective dummy variables was excluded). Here we can see that R automatically includes dummy variables for the different positions, but for one, here the catcher the position. R chose to drop the catcher position as this is the position which comes first in the alphabet.
 == References ==
 <references />

@@ Line 161: / Line 161: @@
       F-statistic: 77.24 on 7 and 345 DF,  p-value: < 2.2e-16
-When you compare the summary statistics to those of the first regression we estimated in this [[Dummy_Variables_in_R#Dummy_variables_as_independent_variables|dummy variable section]], then you will realise that they are identical, we essentially estimated the same model. There is, however, one difference. In the previous estimation we use outfielders as the base category (i.e. the respective dummy variables was excluded). Here we can see that R automatically includes dummy variables for the different positions.
+When you compare the summary statistics to those of the first regression we estimated in this [[Dummy_Variables_in_R#Dummy_variables_as_independent_variables|dummy variable section]], then you will realise that they are identical, we essentially estimated the same model. There is, however, one difference. In the previous estimation we use outfielders as the base category (i.e. the respective dummy variables was excluded). Here we can see that R automatically includes dummy variables for the different positions, but for one, here the catcher the position. R chose to drop the cather position as this is the position which comes first in the alphabet.
 == References ==
 <references />

@@ Line 111: / Line 111: @@
 and inspecting the variables and their datatypes by using <source enclose=none>str(mydata)</source> we find that the variables <source enclose=none>position</source> and <source enclose=none>race</source> are indeed factor variables.
-      'data.frame':	353 obs. of  4 variables:
+      'data.frame':	353 obs. of  5 variables:
        <source enclose=none>$</source> years   : int  12 8 5 8 12 17 4 10 4 3 ...
        <source enclose=none>$</source> position: Factor w/ 6 levels "catcher","first base",..: 4 5 2 6 3 3 3 1 5 3 ...
        <source enclose=none>$</source> race    : Factor w/ 3 levels "black","hispan",..: 3 1 3 3 1 1 2 3 2 1 ...
        <source enclose=none>$</source> lsalary : num  15.7 15 14.9 14.9 14.3 ...
@@ Line 129: / Line 130: @@
 === Using factor variables directly ===
-One very nice aspect of R is that you can use such factor variables directly in regressions. For instance we could estimate a regression with
+One very nice aspect of R is that you can use such factor variables directly in regressions. For instance we could estimate a regression <source enclose=none>lsalary</source>, using <source enclose=none>years</source> and <source enclose=none>gamesyr</source> as explanatory variables but also include intercept dummies for the different positions. The straightforward way to do that is as follows:
 == References ==
 <references />

@@ Line 123: / Line 123: @@
 We can translate the factor variable into dummy variables. We can do this using the following type of commands
-     mydata<source enclose=none>$</source>fstbase <- as.numeric(mydata<source enclose=none>$</source>position == "first base")  # as.numeric translates to numerical - here from logical
+     mydata<source enclose=none>$</source>frstbase <- as.numeric(mydata<source enclose=none>$</source>position == "first base")  # as.numeric translates to numerical - here from logical
-which creates a new variable in the data frame called <source enclose=none>fstbase</source> that takes a value of 1 if the player is a first base player and 0 otherwise. Other dummy variables can be used accordingly. Once you have done this you can proceed as in the previous sections.
+which creates a new variable in the data frame called <source enclose=none>frstbase</source> that takes a value of 1 if the player is a first base player and 0 otherwise. Other dummy variables can be used accordingly. Once you have done this you can proceed as in the previous sections.
 === Using factor variables directly ===

← Older revision		Revision as of 14:54, 7 July 2015
Line 121:		Line 121:
	=== Translating into dummy variables ===		=== Translating into dummy variables ===

		+	We can translate the factor variable into dummy variables. We can do this using the following type of commands

		+	mydata$fstbase <- as.numeric(mydata$position == "first base") # as.numeric translates to numerical - here from logical
		+
		+	which creates a new variable in the data frame called <source enclose=none>fstbase</source> that takes a value of 1 if the player is a first base player and 0 otherwise. Other dummy variables can be used accordingly. Once you have done this you can proceed as in the previous sections.

	=== Using factor variables directly ===		=== Using factor variables directly ===