Skip to main content

Questions tagged [econometrics]

Econometrics is a field of statistics dealing with applications to economics.

Filter by
Sorted by
Tagged with
2 votes
1 answer
225 views

Test for different time trend for different groups?

I have data (y) at different time points (t) for individuals (i) in 2 different groups (<...
0 votes
1 answer
19 views

Power estimate for an interaction term in factorial design

I am trying to estimate power for a factorial design (2x2). My initial approach was to estimate pair-wise minimum detectable effect sizes : i.e., if I know sample size, allocation to each group and ...
0 votes
0 answers
17 views

time trend interaction

I have a panel dataset, and I want to perform some econometric analyses on it. I want to use a trend that interacts with the initial value of certain economic variables. For the trend, does it make ...
1 vote
1 answer
226 views

2sls asssumptions vs IV assumptions

Silly question but I was confused about the independence assumption for instrumental variables when they are used in 2SLS. Is it the case that the instrumental variable used in 2SLS only has to be as ...
5 votes
2 answers
5k views

Fixed effects vs the dummy variables themselves: structural vs practical equation

I have a question about if there is a substantive difference between a fixed effect and the way we estimate them (e.g., dummy variables). Are the estimated dummy variables the fixed effect, or do they ...
1 vote
1 answer
258 views

Asymptotic variance of linear regression with homoskedasticity assumption (Wooldridge Panel book Eq. (4.10))

Jeffrey M. Wooldridge Econometric Analysis of Cross Section and Panel Data Chapter 4 The Single-Equation Linear Model and OLS Estimation Section 4.2 Asymptotic Properties of OLS Subsection 4.2.2 ...
2 votes
0 answers
18 views

Adjusting a multivariate predictive model for drifting seasonalities

This question is a repost of a question originally asked in Quantitative Finance. I was alerted that this would be a more appropriate place for it. I have a time series of daily observations that get ...
1 vote
0 answers
25 views

Linear regression applied to time series with trend - how to deal with it and how to interpret results?

I need to fit a linear regression model on time series. For simplicity, let's assume that we have only three variables: Y - has visible trend; after differencing is stationary X1 - has visible trend;...
4 votes
1 answer
329 views

What are some recommended Graduate-Level Probability and/or Statistics textbooks for an incoming Econ PhD Student?

Title covers most of it. I'm an undergrad who will be graduating in a few weeks and will be starting a PhD Program in Economics. I'm interested in Econometric theory. I've taken undergrad level ...
2 votes
1 answer
157 views

Non-stationary time series: what are the advantages of doing analysis in levels instead of differences?

Suppose we want to analyze some non-stationary time series, x(t) and y(t). For simplicity, assume they are I(1). We can analyze them in levels (using cointegration tests) or in differences. What are ...
2 votes
1 answer
19 views

Poisson model with left-censored data

I observe a setting where every individual may contract on a monthly annuity that pays out after event A realises and is contingent on survival. Therefore, some individuals might never receive ...
0 votes
0 answers
6 views

Using long-run propensities to compare magnitude of association among independent variables

Is it feasible to add up all significant lags of respective independent variables (disregarding insignificant ones) in order to compare the strength or magnitude of their respective association with ...
1 vote
0 answers
8 views

Question about Synthetic Control Method in ADH JASA 2010

I'm reading the famous JASA 2010 paper (https://web.stanford.edu/~jhain/Paper/JASA2010.pdf) by ADH and encounter a question in the Appendix B. The brief summary of my question is stated below and a ...
0 votes
0 answers
16 views

When is E[Xi*ui]=0 violated, given that the residuals are by construction of the model uncorrelated with the predictors?

To begin: I am aware that the concepts of the "error term" and "residual" two distinct ones. Yet, I have difficulties understanding their implications for (multiple) linear ...
0 votes
1 answer
19 views

Underdispersion handled with negative binomial distribution? [duplicate]

To get a more flexible model than Poisson regression, one can choose the negative binomial distribution instead for modeling with $E[y] = \mu$ and $Var(y) = \mu + \frac{1}{ \theta} \mu^2$. As a ...
4 votes
1 answer
119 views

Why can we formally test the relevance assumption of instrument variable?

I saw in my old slides about IV, the professor said we cannot test exclusion assumption of IV but we can test relevance assumption of IV. His argument for not able to test exclusion is: $y=\beta_1 ...
2 votes
1 answer
38 views

Demand curve estimation using variation over time

I am interested in the price elasticity of demand, i.e., the β in Di=a+β*pi+εi. Suppose I observe two time periods but different individuals in both years (i.e., I do not have a panel). In t=1, all ...
2 votes
1 answer
40 views

Proof Markov's Inequality

I have a question regarding the proof of Markov's Inequality, attached as a picture to the post, which is quite basic: It is comphrensible that $\int_{a}^{\infty} xf(x) \, dx \geq \int_{a}^{\infty} af(...
0 votes
0 answers
56 views

Using Controls that are time-invariant with the difference-in-differences estimators

I ran an experiment in which there was 2 groups of participants performing the exact same task during a first period. In the second period, the two groups had to perform the same task a second time. ...
1 vote
2 answers
829 views

Counterexample where E(u|x)=0 in a regression model cannot hold in the population?

Edit: Background information: I have two variables of interest, $y$ and $x$ that are linearly related via the following: $y = a + bx + u$, where "$a$" and "$b$" are fixed ...
1 vote
2 answers
154 views

Instrumental variable: Indirect effect of Z on Y

I have found an instrument variable ($Z$) for my econometric model. The relevance constraint holds, however I still have a question about the instrument exogeneity and that is: It is said that it ...
4 votes
1 answer
1k views

VAR, test for normality, autocorrelation and heteroskedasticity- should I use stationary first differences for these tests?

I am checking the long-term relationship between unemployment and labor force participation rate. I have an integration order $I(1)$ and I want to run VAR. As far as I understand, I need to use first ...
1 vote
0 answers
26 views

Mathematical derivation of why $O_p(N^{-1/2}) + O_p(T^{-1/2}) = O_p(N^{-1/2})$ if $T\gg N$ [migrated]

I will keep things simple. Say, we have a sequence of random variables, $X_{NT}$ which is bounded by the following expression: $X_{NT} = O_p(N^{-1/2}) + O_p(T^{-1/2})$. Now, this implies that $X_{NT} =...
1 vote
0 answers
16 views

R - Why is bgtest showing no autocorrelation when order is set to a higher number, but shows autocorrelation at order = 1

Upon reading, I saw that bgtest (Breusch-Godfrey test, from lmtest pkg) can diagnose autocorrelation of higher orders than just 1, which is the maximum order the dwtest (Durbin-Watson test, from ...
9 votes
1 answer
281 views

Test whether cross-sectional dependence in panel data follows known (network/spatial) structure

I want to test whether cross-sectional dependence in one specific variable (y) in panel data format follows a known structure (W) (e.g. network, spatial dependence), after controlling for individual ...
1 vote
0 answers
32 views

Staggered diff-in-diff vs Stacked diff-in-diff

Just trying to better understand what really is the technical difference between staggered diff-in-diff and stacked diff-in-diff. I understand that TWFE staggered DiD has its own troubles and that ...
0 votes
0 answers
9 views

Connection between multicollinearity and problem of identification in Simultaneous Equations Model

Is there any connection between multicollinearity and problem of identification in Simultaneous Equations Model? I know Multicollinearity is the occurrence of high intercorrelations among two or more ...
2 votes
1 answer
79 views

Granular difference-in-differences with non-repeating unit of observation

I want to analyze changes in characteristics of job postings around an (exogenous) event. However, rather than conducting the analysis at the job poster level (e.g., a company or geographic area), my ...
2 votes
1 answer
571 views

Normality test of latent residuals (Heckman) Probit?

I am running a Heckman Probit. Both steps assume normal errors of the latent variable, correct? My data is from a survey and a lot of variables are strongly skewed, so I am worried whether this ...
0 votes
0 answers
11 views

How can I measure paid search/SEM effects on sales with MMM while accounting for funnel effects?

I am reading hello fresh approach on building a Direct and Indirect marketing mix model to avoid funnel effects (details in this link : https://engineering.hellofresh.com/bayesian-media-mix-modeling-...
3 votes
1 answer
406 views

Forward/Backward Iteration and Stationary/Stability

Suppose I have an AR(1) process of the form: $$y_t = \phi y_{t-1} + \epsilon_t$$ where $\epsilon_t$ is a white noise process with mean zero and variance $\sigma^2$. If $|\phi| < 1 $ , the model is ...
3 votes
1 answer
78 views

Deriving a conditional joint probability model for the data in a Bayesian linear model

I have been reading Tony Lancaster's 2004 book "An Introduction to Modern Bayesian Econometrics." On pages 116-117, Lancaster derives a conditional joint distribution for the data $p(y,X|\...
3 votes
1 answer
116 views

Can using Fisherian inference help me to be more confident of an underpowered result?

I am running a discontinuous regression to see the effect of a cash transfer on an outcome using a poverty index as the running variable. The problem is that the score is not a very good predictor of ...
0 votes
0 answers
19 views

how should i analyze panel data if all units are treated simultaneously?

I possess a dataset of 273 companies from the time period 2001-2017, and i want to study whether the effect of the policy (that was implemented in 2009) on profit was moderated by industry type. My ...
0 votes
2 answers
465 views

What should I conclude if a Unit Root Test gives contradictory results with & without a trend?

I have a data set for a variable, for which I have run some unit-root tests: ADF (constant/without trend): t-stat=-1.0816, p-val=0.7218 - DNR ADF (constant & trend): t-stat=-4.5203, p-val=0.0021 -...
3 votes
3 answers
227 views

Omit continuous variable in categorical by continuous interaction

I'm trying to understand whether excluding the main effect of income in this specification is valid. Gender is a 0/1 variable whether the individual is male/female. Income and NetWorth are continuous. ...
2 votes
1 answer
231 views

What's the minimum number of datapoints in order to run a diff-in-diff?

I was thinking about running a diff-in-diff with fixed effect in order to deal with a panel data experiment. The problem is that I don't know how many datapoints I need in order to the experiment be ...
0 votes
0 answers
6 views

Reversing a First Difference Error Correction Model: Converting the Forecasted FD results back

I'm doing a study on how market rates affect interest rates. The model I've chosen is an Error Correction Model. I address the unit root issue in my dataset by taking the first difference. I then ran ...
1 vote
1 answer
25 views

can add of interaction term makes a third term insignificant?

I was reading a paper. There are 3 regression: the baseline regression: financial development of city i on city level deposit amount, control for road density, and the coefficient on road density is ...
0 votes
0 answers
15 views

What is the best way to model the impact of multiple therapies/diagnostic tests on healthcare resource utilization and costs pre- and post-treatment?

I have a methods question that I'm hoping this group might be able to answer. I'm planning an causal inference analysis in R where we want to see how the use of Diagnostic Test 1 rather than ...
0 votes
0 answers
17 views

OLS Model with Lags - logged coeff

i am building a OLS model using python, where the dependant and independent variables are lagged. This is a form of econometrics model where i want to figure out how much each independent variable ...
3 votes
1 answer
1k views

Expression for the unconditional variance in the EGARCH model

Given the EGARCH specification: $\log(\sigma_t^2)=\omega + \alpha(|z_{t-1}| + E[|z_{t-1}|]) + \gamma z_{t-1} + \beta \log(\sigma_{t-1}^2)$ Is it possible to find a closed-form solution for the ...
5 votes
1 answer
15k views

Propensity Scores Weighted DID

I have a tough challenge using the DID. I have only 2 year data set, 2010 and 2015. The first is the baseline and the latter is follow-up year. In order to obtain true causal effect using DID, I ...
2 votes
1 answer
92 views

Event study regression specification: interacting covariates with leads and lags

I want to create an event study regression specification for the following: $$ \ln(y_{ijt}) = \gamma \ln (x_{jt}) + \tau \ln(p_{t}) + \lambda \ln(x_{jt}) * \ln(\mbox{p}_{t}) + \epsilon_{ijt}. $$ I am ...
0 votes
0 answers
24 views

Maximum Likelihood Estimation - Nested(?) Distributions

I am trying to estimate the parameters of an underlying Beta distribution using observations that arise from Geometric distributions that are conditional on the draws from the aforementioned Beta ...
0 votes
0 answers
37 views

Using results of log-log regression for forecasting

If I have a regression in with logs taken of both sides to give the equation: $ln(y) = \beta_0 + \beta_1 ln(x)$ and need to calculate the expected change in $y$ for a given $x$. I can see from reading ...
0 votes
1 answer
1k views

Log transformation of TS-stationary time series?

I have another question about main econometric time series transformation. I usually see the $log$ transformation of prices: $$p_{new}\left(t\right) = \ln\left(\frac{p_t}{p_{t-1}}\right), t \in [2\...
0 votes
1 answer
53 views

Only first differencing the independent variable?

I am trying to study the relationship between income and preferences for redistribution. I have a panel dataset. I can simply the model (1): preferences = alpha + income + e. However, I'm also ...
1 vote
0 answers
55 views

Event study: Group periods at margins

For an event study (staggered Diff-in-Diff with different treatment periods) I would like to group the periods at the edges so that we get the coefficients for <=x / >=x , such as: For starters,...
0 votes
1 answer
27 views

How to know whether I should use DiD or Spatial RDD?

I'm quite new in econometrics. I want to study a nationwide policy change at the city-level. In year T-1, cities are divided in three zones (green, orange, red) depending on their tension on the ...

1
2 3 4 5
52