BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
PJP
Calcite | Level 5 PJP
Calcite | Level 5

In a logistic regression using SAS PROC QLIM, I have an independent variable, the natural log of annual earnings.

 
The average marginal effect on the dependent variable of this independent variable = -0.0204.

 

EXP(-.0204) = 0.9798 AND (1-0.9798) = 0.0202.
 
Does this mean that a 1.0 percent increase in log earnings reduces the probability of the event by 2.02 percent?

 

Or is the marginal effect interpreted differently?
 
Thanks.

 

 

1 ACCEPTED SOLUTION

Accepted Solutions
gunce_sas
SAS Employee

Hello,

 For a logit model, the marginal effect of change in a regressor, say jth regressor for observation i, on the conditional probability that y_i=1 is

G(x_i'b)[1 - G(x_i'b)]b_j

where, G(x’b) = exp(x’b)/[1+exp(x’b)].

You can request these marginal effects for each regressor from PROC QLIM by specifying the OUTPUT statement and its MARGINAL option. For example,  

OUTPUT OUT=myoutputdata MARGINAL; 

The average marginal effect is the sample average of these marginal effects. For a logit model, this is 

(1/N)*SUMOVER_i{ G(x_i'b)[1 - G(x_i'b)] }b_j 

You can obtain this by averaging the column for the marginal effect of the log of annual earnings over the observations in the data set you specify with the OUT option (myoutputdata in the example above).

If you calculated the average marginal effect of the log of annual earnings as described above and obtained the value -0.0204, then the interpretation of this is that on average a 1 percent increase in log earnings reduces the probability of the event occurring by 2.04 percent.

I hope this helps,

Gunce

View solution in original post

2 REPLIES 2
gunce_sas
SAS Employee

Hello,

 For a logit model, the marginal effect of change in a regressor, say jth regressor for observation i, on the conditional probability that y_i=1 is

G(x_i'b)[1 - G(x_i'b)]b_j

where, G(x’b) = exp(x’b)/[1+exp(x’b)].

You can request these marginal effects for each regressor from PROC QLIM by specifying the OUTPUT statement and its MARGINAL option. For example,  

OUTPUT OUT=myoutputdata MARGINAL; 

The average marginal effect is the sample average of these marginal effects. For a logit model, this is 

(1/N)*SUMOVER_i{ G(x_i'b)[1 - G(x_i'b)] }b_j 

You can obtain this by averaging the column for the marginal effect of the log of annual earnings over the observations in the data set you specify with the OUT option (myoutputdata in the example above).

If you calculated the average marginal effect of the log of annual earnings as described above and obtained the value -0.0204, then the interpretation of this is that on average a 1 percent increase in log earnings reduces the probability of the event occurring by 2.04 percent.

I hope this helps,

Gunce

sas-innovate-2024.png

Don't miss out on SAS Innovate - Register now for the FREE Livestream!

Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.

 

Register now!

Multiple Linear Regression in SAS

Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 2 replies
  • 2759 views
  • 2 likes
  • 2 in conversation