02-17-2025
Emily_Chi
Fluorite | Level 6
Member since
05-06-2024
- 7 Posts
- 6 Likes Given
- 0 Solutions
- 1 Likes Received
-
Latest posts by Emily_Chi
Subject Views Posted 381 02-17-2025 12:06 PM 1859 05-10-2024 01:13 AM 1958 05-08-2024 04:24 AM 2050 05-06-2024 10:20 PM 1086 05-06-2024 10:03 PM 2299 05-06-2024 02:44 AM 1166 05-06-2024 02:21 AM -
Activity Feed for Emily_Chi
- Liked Re: Difference-in-difference with categorical outcomes for StatDave. 02-17-2025 12:29 PM
- Posted Difference-in-difference with categorical outcomes on Statistical Procedures. 02-17-2025 12:06 PM
- Posted Re: DID on Statistical Procedures. 05-10-2024 01:13 AM
- Liked Re: DID for sbxkoenk. 05-10-2024 01:11 AM
- Liked Re: DID for StatDave. 05-09-2024 05:28 AM
- Posted Re: DID on Statistical Procedures. 05-08-2024 04:24 AM
- Liked Re: DID for StatDave. 05-07-2024 10:40 PM
- Posted Re: DID on Statistical Procedures. 05-06-2024 10:20 PM
- Liked Re: DID for StatDave. 05-06-2024 10:04 PM
- Liked Re: Difference-in-difference for dpalmer1. 05-06-2024 10:04 PM
- Posted Re: Difference-in-difference on SAS Programming. 05-06-2024 10:03 PM
- Got a Like for DID. 05-06-2024 01:18 PM
- Posted DID on Statistical Procedures. 05-06-2024 02:44 AM
- Posted Difference-in-difference on SAS Programming. 05-06-2024 02:21 AM
-
Posts I Liked
Subject Likes Author Latest Post 3 1 1 1 1 -
02-17-2025
12:06 PM
I am working on a study with binary outcomes by using difference-in-difference. Traditionally, we know that outcomes usually are continuous in DID model. However, there is a paper discussed using categorical outcomes in DID analysis. Therefore, I am wondering if it is able to procedure in SAS. (Graves JA, Fry C, McWilliams JM, Hatfield LA. Difference-in-differences for categorical outcomes. Health Serv Res. 2022 Jun;57(3):681-692.) Also, as my understanding, they used transition effect in DID model. I am unsure is it estimate the difference of probabilities among two groups. Below is the example interpretation, I appreciate more interpretation and knowledge provided. Example Interpretation: Transition Control Group (R0R_0R0) Treatment Group (R1R_1R1) Difference (RDD) Stayed No (P_{00}) 70% 60% -10pp No → Yes (P_{01}) 20% 35% +15pp Yes → No (P_{10}) 5% 3% -2pp Stayed Yes (P_{11}) 5% 7% +2pp A 15pp increase in P01P_{01}P01 means the intervention led to more patients transitioning to intervention.
... View more
05-08-2024
04:24 AM
If the outcome is not binary, I cannot use logistic regression in DID, right? The outcome of my study is the number of medications, which is not the binary outcome. The outcome is continuous, however, it is a gamma distribution, so I used a log link to address the right-skew problem. I think that it could not use the DID with normal distribution, is there any suggestion for analysis of gamma distribution outcome in DID? Thank you.
... View more
05-06-2024
10:20 PM
Thank you for providing clarification on this issue! It's really helpful for me.
... View more
05-06-2024
02:44 AM
1 Like
I am currently analyzing the impact of an intervention on medication numbers using difference-in-difference analysis, but I have encountered several challenges. Following the SAS support instructions, I conducted the difference-in-difference analysis. However, I noticed a discrepancy between my results and SAS's example (Usage Note 61830: Estimating the difference in differences of means). In the example, the value of 'Mean Estimate' in 'Contrast Estimate Results' is identical to the 'Estimate' in 'Least Squares Means Estimate'. However, in my case, these values were different. I suspect this could be due to my use of the negative binomial distribution with a log link, resulting in exponential values. Consequently, I am unsure whether to rely on the 'Mean Estimate' in 'Contrast Estimate Results' or the 'Estimate' in 'Least Squares Means Estimate', and how to interpret the results." Contrast Estimate Results Label Mean Estimate Mean Confidence Limits L'Beta Estimate Standard Error diff in diff 1.51 1.49 0.41 0.0051 a*b Least Squares Means a b Estimate Standard Error z value Pr > |z| 1 1 0.77 0.00434 178.19 <.0001 1 0 0.03 0.00508 6.5 <.0001 0 1 0.72 0.00408 177.71 <.0001 0 0 0.40 0.00426 93.11 <.0001 Least Squares Means Estimate Effect Label Estimation Standard Error z value Pr > |z| time*hospitalize diff in diff 0.41 0.00509 81.01 <.0001
... View more
05-06-2024
02:21 AM
I am currently analyzing the impact of an intervention on medication numbers using difference-in-difference analysis, but I have encountered several problems. Following the SAS support instructions, I conducted the difference-in-difference analysis. However, I noticed a discrepancy between my results and SAS's example 61830. In the example, the value of 'Mean Estimate' in 'Contrast Estimate Results' is identical to the 'Estimate' in 'Least Squares Means Estimate'. However, in my case, these values were different. I suspect this could be due to my use of the negative binomial distribution with a log link, resulting in exponential values. Consequently, I am unsure whether to rely on the 'Mean Estimate' in 'Contrast Estimate Results' or the 'Estimate' in 'Least Squares Means Estimate', and how to interpret this results. Thank you very much. Here is my result: Contrast Estimate Results Label Mean Estimate Mean Confidence Limits L'Beta Estimate Standard Error Pr > ChiSq diff in diff 1.51 1.49-1.52 0.41 0.0051 <.0001 time*intervention Least Squares Means time intervention Estimate SE z value Pr > |z| 1 1 0.77 0.00434 178.19 <.0001 1 0 0.03 0.00508 6.5 <.0001 0 1 0.72 0.00408 177.71 <.0001 0 0 0.40 0.00426 93.11 <.0001 Least Squares Means Estimate Effect Label Estimate SE Z value Pr > |z| time*intervention diff in diff 0.41 0.00509 81.01 <.0001 SAS code: proc genmod data = ALL_DID;
class _MatchID intervention time /ref = first;
model drug_use = time intervention time*intervention/dist = negbin link=log;
repeated subject =_MatchID/type = exch;
estimate "diff in diff" time*intervention 1 -1 -1 1;
lsmeans time*intervention;
lsmestimate time*intervention "diff in diff" 1 -1 -1 1;
run;
... View more