Questions tagged [difference-in-difference]

Often abbreviated DID or DD, this is a technique for inferring causality from observational data. It involves comparing measurements before and after a treatment occurs (hence, the growth rate) in both a group that received the treatment, and an otherwise comparable group that did not.

Filter by
Sorted by
Tagged with
0 votes
1 answer
13 views

Difference-in-difference age groups

I would appreciate your help with a question I have. I'm creating a Difference-in-Difference study to examine how a conditional cash transfer to individuals 18 years of age to be spent in sport ...
Retir's user avatar
  • 1
0 votes
0 answers
14 views

Using diff-in-diff and fixed effects in Stata

I am doing research using Stata on state-level contraception policy effects on male labour outcomes (e.g. wages). I am utilizing the laws between 1960 and 1976 when Roe vs. Wade was not ruling and the ...
Jonathan Thorsell's user avatar
0 votes
0 answers
28 views

Fixed effects difference in differences issue

I am currently conducting a difference in difference (DID) analysis and fail to understand the benefits of fixed effects models in such cases. I ran a regular DID model with three regular independent ...
p_mercer123's user avatar
1 vote
0 answers
10 views

I have a significant change in my outcome with the opposite sign in the lead period. Is this an issue?

Suppose I have a negative significant effect of a variable x on y. Also negative significant effect of the lag ie variable L1.x on y . But I get a positive sign significant effect on y in the future ...
Sara's user avatar
  • 11
0 votes
0 answers
26 views

Aggregated data and difference in difference esimators

I am trying to find causal effects of a policy change in the UK that allows graduates with a student visa to stay in the country after their graduation to find work without having to return back home ...
lazer's user avatar
  • 1
0 votes
0 answers
14 views

Using instrumental variable in a difference-in-differences setup using feols

I have the following regression model: $$y_{ist} = \beta_0 + \beta_1 Post_{ist} + \beta2 Post_{ist} \times Distance_{i} + \theta_i + \alpha_t + \gamma_{st} + \epsilon_{ist} $$ Where, $y_{ist}$ is the ...
Jerry's user avatar
  • 187
0 votes
0 answers
21 views

What happens to the parallel trends assumption when we estimate unit fixed effects at the micro level in TWFE?

I am a bit confused about the recent difference-in-differences/ two-way fixed effects literature. For example, in this paper the authors analyse a policy effect that happened at a state level on ...
Izzy's user avatar
  • 11
0 votes
1 answer
26 views

What is the difference between pointwise confidence interval and uniform confidence interval in econometrics?

I'm reading Callaway, Bacon, Sant'Anna (2021) paper on continuous treatment. In section 6 they show their result of applying their proposed method to Acemoglu and Finkelstein (2008) medicare example. ...
Eileen's user avatar
  • 25
4 votes
1 answer
71 views

Performing a Difference-in-Difference Analysis where the Control Group is Already Treated

I'm involved in a project where the outcome is the proportion of cancer patients who have received surgery. The treatment event is a state-level policy change that mandated moving all these cancer ...
user8408275's user avatar
0 votes
0 answers
24 views

Difference in differences when treatment status is revoked

I am trying to analyze the effect of receiving "elite" status on a university's number of international first-year students. I have a perfectly balanced panel of 17 universities over an 18-...
Stephanie's user avatar
4 votes
1 answer
127 views

Event study renders treatment effect significant

Currently, I am working with crime panel data (county-day level over several years) to investigate the effect of police presence on crime. I use an "exogenous" increase in police presence ...
Schwa97's user avatar
  • 51
0 votes
0 answers
44 views

Staggered DiD: Single Treatment

Consider a study involving subjects from 30 cohorts. The key event is a law passed by the Federal Government in 2017, which banned the use of certain vaping products. Among the 30 cohorts, individuals ...
Sundown Brownbear's user avatar
0 votes
0 answers
14 views

If I use repeated cross-sectional data in a DiD setting, what are the conditions required for my study to be causal?

I am new to statistics and I want to explore the impact of a specific policy reform. The treatment year is 2014, and I have 7 waves of post-treatment surveys along with 9 waves of pre-treatment ...
Val's user avatar
  • 1
0 votes
0 answers
17 views

Robust Difference-in-Differences: What is the propensity score doing?

Callaway and Sant'Anna (2022) describe a doubly robust difference-in-differences (DiD) method that is attractive in staggered DiD (multi-group treatment times) for several reasons. It can prevent &...
dcoy's user avatar
  • 317
0 votes
0 answers
25 views

How to interpret results from diff-in-diff binary treatment

I ran a dynamic diff-in-diff , of the form $$ y_{it} = \gamma_{i} + \lambda_{t} + \delta T_{it} + \epsilon_{it} $$ y : log(lead concentration) , log concentration of lead in drinking water. $\gamma_{...
Bridgeport BaaS's user avatar
0 votes
0 answers
42 views

two fixed effect question

I was reading this journal article on two way fixed effects by Michelle M. Marcus & Pedro H. C. Sant'Anna The Role of Parallel Trends in Event Study Settings: An Application to Environmental ...
Science11's user avatar
  • 503
1 vote
0 answers
38 views

Adjusting for time-invariant covariates in diff-in-diff using TWFE approach

I am planning a staggered difference-in-differences analysis examining the impact of a change in health policy at the county level. The policy was implemented at different times in different counties, ...
telegraph's user avatar
0 votes
0 answers
26 views

Difference in Difference and Selection Into Treatment

Suppose I impose that the true model of some variable of interest is: $$ Y_{it} = \alpha_i + \beta_t+\tau_{it}D_{it}+\epsilon_{it} $$ Where $ D_{it} = 1\{E_i \geq t\} $. This is a kind of DID model ...
DarkenExcalibur's user avatar
0 votes
0 answers
23 views

standardizing an indicator variable and coefficients to 0

I am fitting a distributed lead, lag models to understand the impact of an event that took place in 2017. My outcome y is a continuous variable. The event took place in 2017. I am interested in ...
Science11's user avatar
  • 503
0 votes
1 answer
25 views

Difference in differences when pre and post outcomes are different variables

Diff in diff question: Can you do difference in differences if the pre-treatment outcome is a different measure to the post-treatment outcome? For example, in Education, imagine there is a new ...
Rob_research's user avatar
2 votes
0 answers
29 views

Using Difference-in-Differences With No Natural Groupings

I'm running across a number of analyses at my organization where people are doing difference-in-differences on individual-level data with no natural groupings. For example, one looked at the effect ...
kypc's user avatar
  • 21
1 vote
1 answer
58 views

Implementing 2way Fixed Effects

My objective is to assess the impact on BMI following the establishment of a new donut shop in the neighborhood, particularly considering that the donut shop commenced operations in 2017. Researchers ...
Science11's user avatar
  • 503
1 vote
1 answer
17 views

Statistical test for aggregated proportion difference in difference

I would like to statistically test if difference in difference estimate is significant, but I do not know what test to use. I am trying to answer a question if war is affecting wellbeing. I have ...
AAAA's user avatar
  • 133
0 votes
0 answers
19 views

Difference in Difference Regression (Showing a change in independent variable coefficient for treat-post group)

I want to measure the the change in the relationship between one of my independent variables (gold price) and my dependent (conflict deaths) for my treatment post group. Any help would be greatly ...
L-Marr's user avatar
  • 1
0 votes
0 answers
71 views

Diff-In-Diff with no aggregation group with cross-sectional data

I was wondering whether there are papers covering the possibility of conducting a DiD analysis with no aggregation group. I am tryng to highlight the impact of a reform on a set of health outcomes, my ...
tryingtogetsmth's user avatar
2 votes
0 answers
17 views

Statistical approach to comparing deviations between two groups before and after a treatment

I have two groups - device X and Y - and measured a continuous variable (angle) before and after treatment. I would like to test which device showed a larger difference in angle after the treatment. ...
Arav's user avatar
  • 31
0 votes
0 answers
30 views

Before-after intervention variation: difference in-difference or broken-stick regression?

I am trying to figure out which analysis would best answer our research question. Our study aimed to find out whether the variation in surgical rate decreases in a group of hospitals after an ...
Ilan Halperin's user avatar
1 vote
0 answers
16 views

Covariance calculation in a DiD estimation

I am estimating a difference-in-difference model estimating the effect of a parental leave reform on female wages. It is not possible to take the logarithm of the varaibles as a lot of wages are 0. I ...
Rstrobaek's user avatar
0 votes
0 answers
21 views

why the treatment-dummy coefficient in a DID reg is different from that of a reg for the pre-treatment period?

The value of the "ever_treated" coefficient obtained with this DID regression is .0397682: ...
Alessandro's user avatar
1 vote
1 answer
215 views

Matching controls in staggered difference-in-differences

I am planning a staggered difference-in-differences analysis examining the impact of a change in health policy at the county level. The policy was implemented at different times in different counties, ...
telegraph's user avatar
2 votes
1 answer
152 views

Difference-in-difference regression design

I'm working with a large panel dataset tracking various units (i-dimension) over an extended period (t-dimension). These units are classified as either 'blue' or 'brown', and some (not all) of these ...
John's user avatar
  • 247
1 vote
0 answers
157 views

Stacked difference in difference with treated units appearing in different cohorts

I am estimating a stacked difference in difference following slide 35 here: I will call a subexperiment as a "cohort". Here, $\theta_{sd}$ are unit $\times$ cohort fixed effects and $\...
elbarto's user avatar
  • 469
1 vote
1 answer
34 views

Is my estimation a difference-in-difference estimate?

I have a sample where a treatment is applied at a given time on all members of the sample - there is no control group, in the traditional sense. However, the sample has two types of members, and my ...
VolsCanAlsoSmile's user avatar
0 votes
0 answers
16 views

Can fixed effect absorb the anticipation effect?

I'm working on a research regarding natural disasters across counties in the US. I'm using these events as exogenous shocks for my Difference-in-Difference analysis. One assumption for the DiD is the ...
Viet Tran's user avatar
0 votes
1 answer
36 views

Help with Difference-in-Difference Experiment Simulation

I came across this article/blog post by Spotify R&D in which they talk about a statistical method called Difference-In-Difference (DID) that they use in the context of A/B testing and how they are ...
rusiano's user avatar
  • 394
0 votes
1 answer
27 views

Is Difference in Difference estimator an annual effect? [closed]

Hi I have a difference in difference framework with multiple pre-periods and post-periods. I get the coefficient of Treatment * Post from the DiD regression. Is this coefficient an annual effect? ( My ...
Jane's user avatar
  • 3
0 votes
1 answer
37 views

About difference in difference with a lot of zero in outcome variable

Hi I use a difference in difference framework to study the policy effect. My outcome variable has a lot of zero, actually 75% are zero. My question is that how to interpret the aggregate effect based ...
Jane's user avatar
  • 3
1 vote
0 answers
19 views

Should I adjust for inflation in a staggereded DiD with money as outcome and if so, how?

This question is currently making my head spin, and I haven't been able to find a discussion on it so far: Suppose I am interested in the effect of an intervention, such as a healthcare reform, on a ...
Izzy's user avatar
  • 11
0 votes
0 answers
16 views

Difference in differences to estimate differential impact of treatment?

I'm having some trouble thinking through the implementation of difference-in-differences / if DD is the best approach to use when I am comparing two groups who are both treated, but which I ...
stats_novice's user avatar
0 votes
1 answer
41 views

difference in differences

I'm looking to work out the difference in effect (time to surgery) between two patient populations (exposed and unexposed groups) and compare between two countries (i.e. difference in differences). i ...
MFA's user avatar
  • 1
0 votes
0 answers
29 views

Testing the common trends assumption

I am reading Cusato and Castillo (2023), an IDB Working paper on the effect of broadband internet expansion and access to credit in Peru. The authors use a staggered difference in difference approach -...
Ploit88's user avatar
  • 45
1 vote
1 answer
81 views

Staggered diff-in-diff - interpretation

Reading a great study by D’Andrea and Limodio (2020), on the effects of expansion of broadband in Africa on fintech adoption and credit markets. They use a staggered diff-in-diff, taking advantage of ...
Ploit88's user avatar
  • 45
0 votes
1 answer
16 views

Seeking Literature on Triple Difference (DDD) for Heterogeneous Effects in DD Evaluation

I'm currently exploring the use of difference-in-differences (DD) for my evaluation and have estimated my primary DD effects. I'm interested in understanding if there are differentiated effects ...
Ricardo's user avatar
0 votes
0 answers
56 views

Figuring out if my problem is about a difference-in-differences with a continuous treatment

I am interested to find the causal effects of a state level policy on some outcome of interest. The policy affects some states each year but not other states. The states that are affected can vary ...
funcard's user avatar
  • 51
0 votes
0 answers
32 views

Diff-in-Diff analysing policy affecting parental income that may affect child health

I am interested to see if a particular policy that increases parental income may impact child health for mothers and fathers. So it would be a diff-in-diff model I would be running. Below is my ...
Lily Tee's user avatar
2 votes
0 answers
42 views

How to use Kernel weighted PSM and IPW in Triple Difference estimator (ika Difference in Difference-in-Differences)

I have learned a lot from @dimitriy answer in this post: Propensity Scores Weighted DID I am currently utilizing the triple difference estimator for estimating treatment effects (please see the paper ...
leon xf's user avatar
  • 21
0 votes
0 answers
42 views

Which groups/time periods to compare in staggered Difference in Difference (DiD) with unit and time fixed effect logistic regression model?

I am trying to build a logistic regression with staggered DiD (for not yet treated) that incoporates unit and time fixed effect. I am stuck with the logic of building the model as I am trying to ...
Zeinab Elashidy's user avatar
1 vote
1 answer
489 views

Power Analysis for Difference in Differences Regression

How would you approach conducting a power analysis to estimate how large of a sample you would need to conduct a difference in differences estimate? For example, for a T-test, I would just set effect ...
Anthony Chu's user avatar
0 votes
0 answers
78 views

How to perform two-way fixed effect Difference in Difference test?

I am doing a research on the effect of Covid on fundraising success. I already implemented logisitc regression models with Covid as interaction variable but my supervisor wants me to use DiD. I asked ...
Zeinab Elashidy's user avatar
0 votes
0 answers
47 views

Difference-in-differences approach validity when binary outcome is 0 during pre-treatment period & always 0 for control units

In the context of evaluating the effectiveness of some intervention on a binary outcome, using a difference-in-differences design, if the outcome is 0 for all study units during the pre-treatment ...
JupiterM104's user avatar

1
2 3 4 5
16