User Tools

Site Tools


c:ma:2019:multiple_regression_exercise

Differences

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

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
c:ma:2019:multiple_regression_exercise [2019/11/08 10:42] – [Ex. 2] hkimscilc:ma:2019:multiple_regression_exercise [2021/11/11 10:14] (current) – [Ex. 2] hkimscil
Line 6: Line 6:
   * Use ''?Carseats'' command for the explanation of the dataset   * Use ''?Carseats'' command for the explanation of the dataset
   * Use ''str'' function to see the characteristic of each variable. Make it sure that ''SelvesLoc'' variable should be factor, not int or anything.   * Use ''str'' function to see the characteristic of each variable. Make it sure that ''SelvesLoc'' variable should be factor, not int or anything.
 +  * 변인설명을 토대로 가설만들기 
 +    * 종속변인 = Sales
 +    * 독립변인 = 숫자변인 1 + 종류변인 1  (조별 선택)
 +    * Multiple regression without interactin
 +    * Multiple regression with interaction
 +  * 가설 만들기 
 +    * 종속변인 Sales
 +    * 독립변인 여러개 (interaction 없이)
 +    * Modeling 해 볼 것 
  
-  * Make a full model (with all variables) then reduce down the model until you find it fitted. +see [[:hierarchical regression]] 
-  * Make a null model (with no variables) then, build up the model with additional IVs until you find a fitted model.  +see also [[:statistical regression methods]] <- 많이 쓰이지 않음 
-  * Can we use ''step'' or ''stepAIC'' (MASS package needed) function? + 
-  * Interpret the result+  <del>Make a full model (with all variables) then reduce down the model until you find it fitted.</del> 
 +  * <del>Make a null model (with no variables) then, build up the model with additional IVs until you find a fitted model.</del>  
 +  * <del>Can we use ''step'' or ''stepAIC'' (MASS package needed) function?</del> 
 +  * <del>Interpret the result</del> 
 + 
 +<del>> step(lm.full, direction="back")</del>
  
-> step(lm.full, direction="back")+[[./eg_script]] 
  
 ===== Ex. 2 ===== ===== Ex. 2 =====
Line 18: Line 32:
   * load the tidyverse   * load the tidyverse
   * ''%%install.packages("car")%%''   * ''%%install.packages("car")%%''
-  * ''%%data("Salaries", package = "car")%%'' +  * ''%%install.packages("carData")%%'' 
-  * Use a dataset Salaries  +  * load the car and the carData  
-  * describe the data set+  * ''%%data("Salaries", package = "carData")%%'' 
 +  * ''%%?Salaries%%'' 
 +    * explain what it is 
 +    * describe the data set
 ---- ----
   * Regress sex variable on salary variable   * Regress sex variable on salary variable
   * Write the regression model    * Write the regression model 
-  * Discuss the difference+  * Discuss the difference male and female (sex)
  
   * Use rank variable for the same purpose   * Use rank variable for the same purpose
-  * --+  * Write the regression model 
  
-  * Use yrs.service + rank + discipline + sex  +  * Regress rank + sex on salary
-  * on salary+
   * How do you interpret the result?   * How do you interpret the result?
 +  * And regress rank + sex + rank:sex on salary
 +  * How do you interpret this result?
 +  * Do factorial ANOVA test with rank and sex on salary 
 +  * How do you interpret the result?
 +
 +  * Test regression model of your own choice
 +  * Interpret the result
 +
 ----- -----
 위의 Salaries 데이터사용이 안 될 때 위의 Salaries 데이터사용이 안 될 때
Line 41: Line 65:
 Please copy and paste the proper r command and output to a txt file (use notepad or some other text editing program). You could use MS Word, but, please make it sure that you use type-setting fonts such as "Courier New." The below output, as an example, includes the r command ''%%head(Salaries)%%'' and the output.  Please copy and paste the proper r command and output to a txt file (use notepad or some other text editing program). You could use MS Word, but, please make it sure that you use type-setting fonts such as "Courier New." The below output, as an example, includes the r command ''%%head(Salaries)%%'' and the output. 
 <code> <code>
-> head(Salaries) 
-       rank discipline yrs.since.phd yrs.service  sex salary 
-1      Prof          B            19          18 Male 139750 
-2      Prof          B            20          16 Male 173200 
-3  AsstProf          B                       3 Male  79750 
-4      Prof          B            45          39 Male 115000 
-5      Prof          B            40          41 Male 141500 
-6 AssocProf          B                       6 Male  97000 
-</code> 
- 
- 
-<code>> lm.sal.sex <- lm(salary ~ sex, data=Salaries) 
-> summary(lm.sal.sex) 
- 
-Call: 
-lm(formula = salary ~ sex, data = Salaries) 
- 
-Residuals: 
-   Min     1Q Median     3Q    Max  
--57290 -23502  -6828  19710 116455  
- 
-Coefficients: 
-            Estimate Std. Error 
-(Intercept)   101002       4809 
-sexMale        14088       5065 
-            t value Pr(>|t|)     
-(Intercept)  21.001  < 2e-16 *** 
-sexMale       2.782  0.00567 **  
---- 
-Signif. codes:   
-  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 
-  0.05 ‘.’ 0.1 ‘ ’ 1 
  
-Residual standard error: 30030 on 395 degrees of freedom 
-Multiple R-squared:  0.01921, Adjusted R-squared:  0.01673  
-F-statistic: 7.738 on 1 and 395 DF,  p-value: 0.005667 
-</code> 
 ====== Discussion ====== ====== Discussion ======
 Common topics Common topics
c/ma/2019/multiple_regression_exercise.1573177353.txt.gz · Last modified: 2019/11/08 10:42 by hkimscil

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki