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
1answer
14 views

How to interpret Difference-in-Difference results?

The code used was: didreg=ln (LCR~Group+Time =Group*Time, data=data) The two dummy variables are Time and Group. Time indicates the time when the treatment started. So, the years before the treatment,...
0
votes
0answers
3 views

Finding out whether a complexity premium exists for certain loans made - which model to use?

I am doing research on loans. There are two groups of loans and I assume for one of the groups a complexity premium exists (they have a higher spread on average). I would like to build a model that ...
0
votes
0answers
5 views

Collinearity in an event study

I am trying to augment a difference-in-difference analysis by carrying out an event study that looks at the effects of a shock ($M A _ { i } $) on an outcome $Y _ { i t }$ (with 4 leads and 4 lags). ...
0
votes
0answers
8 views

verifying pre-treatment trend assumption when there are multiple treatment time in Diff-in-Diff

One of my colleagues and I had a debate on Propensity Score Matching (PSM) + Diff-in-Diff (DD) when there are multiple time periods (some people called it staggered DD). Compared to the standard DD ...
0
votes
1answer
25 views

How do I test whether an intervention is significant when I don't have the counterfactual sample size?

Let's say I want to figure out whether a specific Public Service Announcement (PSA; you can think of it as an advertisement) to ask people to do an action is effective. That is, the independent ...
0
votes
1answer
37 views

difference-in-difference and omitted variable bias

i have a question concerning the difference-in-differences research design: if i can find a variable which is both correlated with the difference-in-difference estimator and the dependent variable of ...
6
votes
2answers
817 views

How do I test if regression slopes are statistically different?

I have a set of data that is composed of a measured parameter (dependent variable) as a function of time (independent variable), before and after an intervention event. I have calculated slope and ...
0
votes
0answers
18 views

Difference in differences with multiple treatment groups that all receive treatment at the same time

I have panel data measuring an outcome at the state-day level. I have data on 35 states. 10 of the states received treatment all on the same day. I want to setup a difference-in-difference design to ...
1
vote
0answers
17 views

Relative Time Model with missing time periods

I'm trying to replicate a relative time model to evaluate pre-treatment trends in a staggered diff-in-diff model. I've found the following description in literature (Rietveld, J., Schilling, M. A., &...
0
votes
0answers
15 views

Difference in differences regression with treatment at different times for different countries

I found an article about DID regression online: https://www.princeton.edu/~otorres/DID101R.pdf As far as I understand the countries A, B, C and D are the control group and E, F and G are the treatment ...
0
votes
1answer
16 views

diff-in-diff with continuous treatment vs cut-off point (and 2 periods)

I have panel data for a number of counties for two years only (t = 1,2). The treatment, let's assume it's a policy implementation programme, happens in between year 1 and 2 and it is a continuous ...
1
vote
0answers
27 views

Difference between “Within” estimator for $Y_\textit{diff} = Y_{t_i} - Y_{t_{i - 1}}$ vs “First Difference” estimator for $Y_{t_i}$

I am using a diff-in-diff strategy and have a few question. I am not getting equivalent coefficient estimates for the two following regressions on panel data: a panel regression with a fixed ...
0
votes
0answers
8 views

Assumptions for difference-in-difference regression using panel data

I'm doing a difference-in-difference analysis to measure the impact of removing financial incentives from healthcare quality indicators. I have data from 450 clinics, for 26 indicators in the '...
1
vote
1answer
35 views

Is difference-in-differences analysis with time as dummy better than 'ordinary' y=after, x = before regression?

I am a natural scientist dipping my toes into the more social, economical side of things where instead of GitHub and R, Stata is the go-to tool and almost everything is 'panel' data. Similar analyses ...
0
votes
0answers
11 views

How to remove collinearity from a fixed-effects difference-in-difference regression?

I'm doing a difference-in-difference regression with fixed effects. I'm analysing the effect of removing financial incentives from quality indicators, in health clinics. I have a dummy variable for '...
0
votes
0answers
20 views

Should I call this a fixed effects or differences in differences model?

I have a question regarding what terminology should I use in my paper when I consider the following model: $y_{it} = \alpha + \beta_0T_i + \beta_1\text{Time}_{t} + \beta_2(\text{Time}_{t} \times T_i)...
0
votes
0answers
12 views

Binary (dummy-variables) in a Difference-in-Difference Estimation

currently, I am conducting a Difference-in-Difference Analysis for which I designed a treatment Group (1) and a Control Group (0). The Regression for this works just fine, although not with the ...
1
vote
1answer
52 views

Group & Time fixed effects in a Difference-in-Difference Model

I'm fairly new to the field of econometrics and currently struggling to understand the literature regarding minimum wage policies and their effect on employment. So the equation that I see in almost ...
0
votes
1answer
155 views

Notation for leads and lags in difference-in-differences

I was hoping someone could help clarify a notational discrepancy. For example, Lord Pischke uses the following sigma notation in two different lecture notes published on the web, yet refers to the ...
1
vote
0answers
56 views

Failed parallel trend assumption in covariate for difference in difference analysis

Performing a difference in difference analysis and the parallel trend assumption fails for the treatment and control groups for a potential covariate to include in the analysis. Would it be ok to ...
0
votes
0answers
15 views

Difference-in-difference estimate with individual-level panel data

I've done a difference-in-difference analysis to estimate the impact of removing financial incentives on healthcare quality indicators. For every health clinic in the country, I have a 'performance' ...
1
vote
2answers
42 views

Refining a difference-in-difference analysis

I'm doing a difference-in-differences analysis with one pre-treatment time (0), and two post-treatment time points (1,2). My basic regression model is: = $β_0+β_1T_1 +β_2T_2 +β_3S+ β_4(S∗T_1)+β_5(S∗...
3
votes
0answers
119 views

If parallel trends assumption is not met for diff-in-diff analysis, why not add more interaction terms to regression model?

The literature presents a violation of the parallel trends assumption as a major obstacle when performing a difference-in-differences analysis. Why can't we model non-parallel trends by simply ...
0
votes
0answers
37 views

Combining difference-in-differences and fixed effects

I've seen several related posts to this topic here and elsewhere (e.g. Statalist). However, after reading through them I'm still somewhat confused on why we would want to combine DID with fixed ...
1
vote
0answers
23 views

Why this specification is not a difference-in-difference?

I was reading a recent article in my field and one thing was bothering me. The article can be find here : https://onlinelibrary.wiley.com/doi/abs/10.1002/smj.3018 and is an econometric paper about ...
1
vote
1answer
26 views

Forming hypothesis based on difference in difference test

I am trying to rewrite my hypothesis for my study which uses a difference in difference type design. My study is concerned with the causal effect of development aid on support for democracy in a ...
1
vote
1answer
32 views

After term not significant difference-in-differences

I ran a difference-in-differences model and I have an interpretation issue. My difference between treated and control is not significant before and after. In the same time, my interaction term is ...
0
votes
2answers
46 views

Test if the difference of differences is significant

How to test if the difference between two groups is lower, higher or equal than the difference between two independent groups? For example: Is the height difference between a sample of male and ...
0
votes
1answer
23 views

Causal Inference in Mortality Rates

I was wondering how does one study the average treatment affect in scenarios suchs as mortality rates. For example: suppose we want to study the effect that a certain medicine has on the mortality ...
1
vote
0answers
32 views

Causal Inference in a employee churn context (difference-in-differences / Propensity score matching)

For my master thesis I'm trying to determine the causes of an employee leaving a company. Currently I'm trying to study the effect that giving a raise has on employee leaving a company or not. So my ...
0
votes
2answers
89 views

Difference-in-difference to estimate gradual (i.e. slow) policy effect

I want to evaluate the impact of a policy on a variable $Y$. In the figure, I plot the mean of $Y$ over time in both the control and treatment groups (the vertical line represents the reform). The ...
0
votes
0answers
51 views

Modeling Pre-Trends in Difference-in-Differences

To get right to the point, the canonical difference-in-differences design is as follows: $$ y_{it} = \alpha + \gamma T_{i} + \lambda Post_{t} + \delta (T_{i} \times Post_{t}) + \varepsilon_{it}, $$ ...
0
votes
0answers
32 views

Estimate total effect of treatment when continuous treatment variable and its dichotomization show contradicting impacts

I am trying to estimate the total effect of a leak of a harmful gas on my dependent variable. While I do not know the actual exposure, I know the distance of a household to the origin of the leak in ...
0
votes
0answers
29 views

State-specific trends in staggered diff-in-diff model

I am running a staggered diff-in-diff model where I have four states implementing the same policy with different timings and three control states where the policy has not been implemented at all. My ...
0
votes
0answers
37 views

Difference-in-differences analysis with multiple time periods

I am looking at the effects of a law on listed companies. I have a control group and a treatment group, but instead of having a pre treatment period and a treatment period I have 3 time periods. I ...
0
votes
0answers
23 views

Convert regression coefficient from fixed effects model to percentage increase

I'm running the following fixed-effect model in R: felm(DV ~ treatment*intervention | week + participant | 0 | participant_id) i.e., I'm controlling for the fixed ...
0
votes
0answers
34 views

Why are the confidence intervals so large for the difference of differences?

I have run a generalized linear mixed effects model with the glmmTMB package to determine if there is an interaction between two categorical predictors, treatment and location, in predicting the ...
0
votes
0answers
4 views

Which fixed effects it is worth including in DiD specification?

I analyze a reform which softened administrative pressure on firms. I estimated a general two-way fixed effect model with the treatment dummy. I also obtained data on region and industry. Should I ...
0
votes
0answers
86 views

How to check parallel trends assumption in DiD when treatment occurred in different moments of time?

I analyze a reform which introduced tax cuts for small firms. Different regions pursued this policy in different years. I estimated the effect using a fixed-effect model with a dummy on being treated. ...
0
votes
0answers
45 views

The impact of other continuous variable on the DID estimate

I have searched around but didn't have any luck. I am trying to estimate and then compare the DID estimates of the effect of a Treatment on Life-expectation across different Income levels, to know if ...
0
votes
0answers
13 views

Mechanics of FE in DiD estimation

I created a toy data set to test what goes on when I use FE in a DiD regression, with twelve observations in two states and three sectors where I observe an effect in only one state-sector pair with ...
0
votes
0answers
25 views

Difference-in-difference analysis: more than one control group

I'm doing a difference-in-difference analysis of the impact of financial incentives on healthcare delivery. I have one treatment group (where there were financial incentives), and two separate ...
1
vote
1answer
41 views

Regression model for a difference-in-difference analysis with three time points

I'm doing a difference-in-differences analysis with one pre-treatment time point (0), and two post-treatment time points (1, 2). What would the regression model be?
0
votes
1answer
103 views

DiD with time fixed effects does not drop Post dummy

Following the copied link (https://www.statalist.org/forums/forum/general-stata-discussion/general/1323707-fixed-effect-difference-in-differences-model) I was expecting the classic dummy 'Post' to be ...
0
votes
1answer
26 views

Difference-in-difference (DD) estimator for non-discrete, longitudinal data?

There are many examples of how to set up a DD model for two points in time and with dummy variables (0s and 1s) separating the treated from control units and before and after intervention periods. ...
0
votes
0answers
72 views

Event Study: Event time coefficients vs post change coefficient

I have an event study regression with an unbalanced panel. I include unit and time fixed effects as well as a linear time trend control: $Y_{st} = \sum_{\tau \neq -1} \delta_{\tau} \mathbf{1}(YS_{st} ...
1
vote
0answers
32 views

How to test for a difference between differences?

I have 6 sites with 3 sites as constant food in a feeder and 3 sites as pulsed food in a feeder. For the pulsed food sites, there are days with food and without food.So, I have 2 treatments: constant, ...
1
vote
0answers
28 views

Setting up fixed effect regression with specific baseline comparison group

I'd like to set up a fixed effects regression equation where the coefficients and standard errors can be interpreted to represent a specific comparison that I am interested in. That is, I want to ...
1
vote
0answers
19 views

Regressing the “fixed effect” on time invariant characteristics. Is it possible? [duplicate]

I would like to use estimations of "fixed effect" from my panel data model as a dependent variable and study whether this depends on time invariant characteristics. I've not been able to find an ...
0
votes
0answers
46 views

Difference-in-differences or something else? Regrouping after intervening event

I'm working on a project for my econometrics class and I could use some help. I'm looking at the effects of a Supreme Court decision, Tapia v. U.S, on the length of sentences handed out for drug ...