How to change the order of independent variables for regression summary output in R?

To change the order of independent variables in regression Output, we can pass the variables in the sequence we want while creating the regression model.

For example, if we want to have three independent variables and we want to display first at the last position then it can be done as follows −

lm(DP1~ ind_var_3+ ind_var_2+ind_var_1,data=”data_frame_name”)

Example

Following snippet creates a sample dataframe −

iv1<-rnorm(20)
iv2<-rnorm(20)
iv3<-rnorm(20)
DP1<-rnorm(20,1,0.05)
df1<-data.frame(iv1,iv2,iv3,DP1)
df1

The following dataframe is created −

output

     iv1            iv2         iv3           DP1
1   0.27622283    0.3993088   0.009604179   0.9870641
2  -1.61822694   -0.8481482   0.455201989   1.0419490
3  -0.16453686   -1.4879353  -0.350820394   0.9798238
4  -1.05644448   -0.6567911   1.345854317   0.9589660
5   0.16128004   -1.5530191   1.248949489   1.0337228
6   0.26490779    0.1905057   0.664826658   0.9612587
7   0.75145959   -0.2902165   0.005533312   1.0167088
8  -0.11785438    0.6260407   1.116348214   1.0087205
9   0.25632653   -0.4080989  -0.314622661   0.9548039
10 -0.70829294   -1.4721428   0.303353402   0.9456278
11  0.96142734   -0.8047216  -1.423814934   1.0133855
12  0.47065716   -0.0145821  -0.871918075   1.0242987
13 -2.23836059    1.7323083  -1.417109201   0.9578229
14  0.76295739   -0.3704564   0.839145422   1.0706470
15  0.40626379    1.9601237   1.457727929   1.0253645
16 -0.75012537   -0.6982455  -1.512548488   0.9916308
17 -0.27124742   -0.9710179   0.284963380   0.9459357
18 -0.26442340    0.6065156  -0.498311289   1.0158016
19 -0.37278740   -0.2710638   0.643670976   0.9794339
20 -0.05907976    0.9741651   0.273533270   1.0329243

Now, to create a regression model for data in df1, add the following code to the above snippet −

Example

Model1<-lm(DP1~iv1+iv2+iv3,data=df1)
summary(Model1)

Output

If you execute all the above given snippets as a single program, it generates the following Output −

Call:
lm(formula = DP1 ~ iv1 + iv2 + iv3, data = df1)

Residuals:
    Min      1Q       Median    3Q     Max
-0.047785 -0.021889 0.000682 0.018709 0.071298

Coefficients:
             Estimate  Std.rror t value  Pr(>|t|)
(Intercept) 1.000534  0.008392  119.230  <2e-16 ***
iv1         0.016620  0.010299  1.614    0.126
iv2         0.005927  0.008287  0.715    0.485
iv3         0.004480  0.008982  0.499    0.625
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.0357 on 16 degrees of freedom
Multiple R-squared: 0.1778, Adjusted R-squared: 0.02369
F-statistic: 1.154 on 3 and 16 DF, p-value: 0.3579

To create a regression model for data in df1 with different order of independent variables, add the following code to the above snippet −

Example

Model1<-lm(DP1~iv2+iv1+iv3,data=df1)
summary(Model1)

Output

If you execute all the above given snippets as a single program, it generates the following Output −

Call:
lm(formula = DP1 ~ iv2 + iv1 + iv3, data = df1)

Residuals:
    Min      1Q      Median     3Q      Max
-0.047785 -0.021889 0.000682 0.018709 0.071298

Coefficients:
            Estimate Std. Error   t value  Pr(>|t|)
(Intercept) 1.000534 0.008392     119.230   <2e-16 ***
iv2         0.005927 0.008287     0.715      0.485
iv1         0.016620 0.010299     1.614      0.126
iv3        0.004480   0.008982     0.499      0.625
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.0357 on 16 degrees of freedom
Multiple R-squared: 0.1778, Adjusted R-squared: 0.02369
F-statistic: 1.154 on 3 and 16 DF, p-value: 0.3579

Example

Following snippet creates a sample data frame −

x1<-rpois(20,4)
x2<-rpois(20,2)
x3<-rpois(20,2)
x4<-rpois(20,5)
y<-rpois(20,10)
df2<-data.frame(x1,x2,x3,x4,y)
df2

The following dataframe is created −

output

    x1 x2 x3 x4 y
1   3  1  4  7 15
2   6  2  5  1  8
3   7  2  1  5 15
4   6  0  4  6 14
5   4  3  2  2  8
6   3  0  3  6  9
7   1  2  1  9 13
8   7  1  3  5 14
9   3  1  0  6  9
10  5  4  3  8 11
11  6  3  1  7  8
12  2  0  3  1 11
13  2  2  1  5  6
14  5  0  1  4 10
15  4  2  0  4  5
16  5  0  3  5 14
17  2  4  2  7 10
18  5  4  3  4  6
19  3  1  3  1  5
20  3  4  1 4 12

To create a regression model for data in df2 with different order of independent variables, add the following code to the above snippet −

Example

Model2<-lm(y~x3+x2+x4+x1,data=df2)
summary(Model2)

Output

If you execute all the above given snippets as a single program, it generates the following Output −

Call:
lm(formula = y ~ x3 + x2 + x4 + x1, data = df2)

Residuals:
   Min    1Q     Median  3Q     Max
-3.3049 -2.6574 -0.2113 1.6365 5.1192

Coefficients:
     Estimate Std.  Error  t value  Pr(>|t|)
(Intercept) 4.7478  2.6181  1.813  0.0898 .
x3         0.5544   0.5061  1.095  0.2906
x2        -0.6848   0.4622 -1.482  0.1591
x4         0.7880   0.2979  2.645  0.0184 *
x1         0.3886   0.3839  1.012  0.3274
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 2.873 on 15 degrees of freedom
Multiple R-squared: 0.4061, Adjusted R-squared: 0.2478
F-statistic: 2.565 on 4 and 15 DF, p-value: 0.08123