Anyone who engages in econometrics pays attention to this account
Manuscript: [email protected]
All the code programs, macro and micro databases and various software of the econometric circle methodology are placed in the community. Welcome to the econometric circle community for exchanges and visits.
Regarding the DID double difference method, scholars can refer to the following articles: 1. DID use classic literature, compulsory license: evidence from the enemy's trade law, 2. continuous DID classic literature, potatoes made the old world civilization, 3. cross section Data DID tells the paradigm of double-differential policy evaluation in cross-section, 4. RDD classic literature, RDD model validity and robustness test, 5. Event research method used in DID classic literature "environmental regulation" thesis data and procedures, 6. Generalized The DID method is very classic JHE literature, 7. DID’s classic literature "compulsory license" paper data and do program, 8. MLM activities on economic development, AER cross-sectional data analysis classic text, 9. Multi-period DID classic Literature big bad banks data and do files, 10. Causal inference IV method classic literature, is it system or human capital that promotes economic development? , 11. The establishment of causality on AER, sensitivity testing, heterogeneity analysis and cross-data use classic articles, 12. The second classic of causal inference, the impact of work interruption on the subsequent productivity of workers? 13. Density Economics: Natural Experiments from the Berlin Wall, Best Econometrica Papers, 14. Labor and Health Economics with DID and DDD as identification strategies on AER, 15. A policy evaluation method using cross-sectional data, can also be issued AER, 16. Multi-period DID model classic literature, big bad banks explain ",", 17. Multi-period DID classic literature big bad banks data and do files, 18. Non-linear DID, double transformation model CIC, quantile DID, 19. What is Fuzzy DID? How to use data to achieve it? 20. Multi-issue DID big bad banks Chinese translation version and detailed explanation, 21. DID industry/region and time trend interaction items, common trend test, dynamic policy effect test, etc. 22. Cross-sectional data DID operating procedure guide, Teach you step by step, 23. DID research dynamics and literature review applied in policy evaluation, 24. Continuous DID classic literature, potatoes made the civilization of the old world, 25. DID double difference method, some error-prone places, 26 .Continuous DID, DDD and proportional DID, unobservable selection deviation, 27. Weighted DID,
text
About below the text content, author: Zeng Xuan, Wuhan University School of Economics and Management, Communication E-mail: [email protected]
One of the authors of this article is Professor Fang Hanming (refer to 2 "Chinese Professors" newly elected as Fellows of the World Econometric Society). Professor Fang's main research fields are public economics and labor economics. He is one of the academic leaders in the field of applied microeconomics in American economics; he was once the co-editor of the Public Economics Journal and the International Economic Review, including the editorial board of the top economic journal, the American Economic Review.
He has a wide range of research interests and is good at combining theory with empirical research methods. His specific research topics include the theory and empirical methods of discrimination economics, the social security system includes theoretical and empirical research on the medical insurance market and the welfare system for the poor, life insurance market and social economics. His research results in the medical insurance market and the economics of discrimination are far-reaching.
The structure of the paper "Restrictions on Movement of People and the Spread of New Coronavirus: Empirical Research Based on Chinese Data"
is the total score, but we interpret it in the form of total score.
Introduction, data and conclusions The
new crown virus first appeared in Wuhan, Hubei Province in early December 2019 and spread rapidly from person to person. However, the authorities only publicly announced the human-to-human transmission of the new crown virus on January 20, 2020, and began to block Wuhan, a large city with more than 11 million people, starting at 10 o'clock on January 23, 2020.
Although a series of measures to restrict the movement of people, such as lockdown, can better prevent the further spread of the virus, its specific impact is difficult to estimate, because in addition to the lockdown effect, there are also panic effects, virus effects, and Spring Festival effects. In order to overcome this difficulty, this article uses nearly 3 million detailed, high-quality urban daily data provided by Baidu Migration, and uses the double-difference method to more accurately isolate the specific impacts of various effects. On this basis, a counterfactual was constructed, estimating the contribution of the Wuhan city closure measure to the specific reduction of the number of confirmed cases of the new crown virus in Wuhan and 16 non-Wuhan cities in Hubei Province. 
The impact of the lockdown of Wuhan on the movement of people.
We tried to quantify the causality of restricting the movement of people to prevent the spread of the new crown virus, but there are several mixtures: panic effect. Since Wuhan is the epicenter of the new crown virus, the number of people flowing into Wuhan will be greatly reduced, while outflow The number of people in Wuhan will increase significantly; the virus effect, due to the characteristics of human-to-human transmission of the new crown virus, people will deliberately avoid exposure to the virus during travel and public places; the Spring Festival effect, because the outbreak of the new crown virus coincides with the eve of the Chinese Lunar New Year, just in time When the population is moving in a large area.
We use equations 1 and 2 to estimate the inter-city and intra-city effects, and the explanation of the key variables in the model is shown in the figure below: The 
estimation results are shown in the following table :
Panel A, B, and C in Table 2 are the results of the inflow and outflow of Wuhan population, and the population flow in Wuhan, respectively. Models 1, 2 and 3 are the comparison between Wuhan and 284 unclosed cities, and Wuhan in 2020. Comparison with 2019, and comparison between Wuhan and 7 other closed cities. In contrast, we prefer models 2 and 3, so we only explain the estimated parameters of models 2 and 3 (the shaded parts are the parameters that need to be paid attention to), and the explanation is as follows:
Because the equation is in log-level form, since we have also estimated the various parameters of the model, we only need to transform the model into the form of level-level influence to get the specific influence of each effect, as shown in the following table:
From the table, we can see that the impact of the lockdown of Wuhan on the inflow and outflow of Wuhan population and the population flow in Wuhan is significant at the 1% level, and the specific effects are reduced by 76.64%, 56.35% and respectively. 54.45% of the population is mobile.
Quantify the impact of the lockdown on the spread of the new crown virus in the country.
In addition to the lockdown of Wuhan, 16 other cities in Hubei Province have also been locked down, so we want to construct the counterfactual of the unsealed city to compare with the reality of the lockdown. , In order to estimate the specific impact of the closure of the city on the spread of the new crown virus in the city. And because the incubation period of the new coronavirus is 22 days at the longest, we establish a dynamic equation that lags 22 periods:
In order to construct a counterfactual world where Wuhan is not closed, we need to replace the first explanatory variable of Equation 3 with the daily flow of people in Wuhan, that is, replace the subscript i with WH. For the 16 cities in Hubei Province except Wuhan, this is also the case. The following picture shows the counterfactual world, A is Wuhan, B is the 16 cities in Hubei Province except Wuhan, the dotted line is the officially reported confirmed cases, the solid line is the counterfactual world, and the daily confirmed cases have sharp points. The reason is that the detection methods of nucleic acid reagents are replaced with the detection methods of clinical symptoms:
In the figure, we can see that although the number of confirmed cases in the counterfactual world was indeed higher than the real world at the beginning of the lockdown, it will gradually converge to the real world data in the end. There may be three reasons for this: due to Wuhan 16 cities in Hubei province except Wuhan are the epicenters of the epidemic. The Health Commission was too late to test one by one due to the rapid increase in the number of people infected with the new crown virus in the initial period; because there is no time to test one by one, some patients may heal themselves or die; the government Officials have an incentive to conceal the number of infected people.
The above picture shows the comparison between the 347 counterfactual worlds outside Hubei Province and the real world, as well as the comparison between the counterfactual world and the real world in 16 other cities in Hubei Province except Wuhan. The estimation methods and corresponding explanations are the same as the previous ones.
The impact of expanding social distancing on the spread of the virus
Although many cities have implemented a series of measures to restrict the movement of people, the methods are different: some cities are completely closed, some cities are partially closed, and some cities are tested. Point and quarantine area.
In order to study the impact of these measures in detail, we further split Equation 5 into Equation 6. 
The explanation of the parameters to be estimated in Equation 6 is as follows:
The estimation results show that the estimation is statistically and economically significant, that is, these measures have effectively curbed the spread of the virus. 
Long press the above two-dimensional code to read the original text for
extended reading:
①Summary of 120 classic empirical literatures on various causal identification methods", ②The newly revised classic masterpiece of causal inference from Harvard University is free to download! With data and code, ③Summary of statistical methods of causal inference, 177 documents, ④Policy evaluation A review of the measurement methods, including the latest causal inference methods, ⑤Do you use IV, RDD, DID, PSM more in the education field? Use specific literature, ⑥After reading the top journal articles, organize the endogenous treatment booklet, ⑤Innovative tool variables Explain, to ensure that you will never forget it forever, ⑦DID, synthesis control, matching, RDD four methods comparison, applicable scope and characteristics, ⑧32 selected Articles about double difference method DID!⑨About (fuzzy) breakpoint regression design 100 selected Articles! ⑩Matching method (matching) operation guide, 16 articles worth collecting, etc., ⑪ MIT's widely circulated policy "processing effect" reader, ⑫DID research trends and literature review applied in policy evaluation, ⑬Four methods of the latest policy effect evaluation, ⑭Basic problems of policy effect evaluation.
For a compilation of some measurement methods, scholars can refer to the following articles: ① "200 articles used in empirical research, a toolkit for social science scholars", ② 50 famous experience posts commonly used in empirical article writing, a must-read series for students ③The Articles album on Chinese topics on the AER in the past 10 years. ④AEA announced the top ten research topics that received the most attention in 2017-19, giving you the direction of the topic selection. ⑤The key topic selection direction of the top Chinese journals in 2020, just write the paper These, ⑥The road map of the "high light moment" of RCT, DID, RDD, LE, ML, DSGE and other methods in the past thirty years. Later, we introduced a collection of selected articles using CFPS, CHFS, CHNS data for empirical research! ②These 40 micro-databases are enough for you to graduate with a Ph.D. Anyway, with these libraries, you become a professor. ③The most complete collection of shortcut keys in the history of Python, Stata, and R software! ④100 featured Articles album about (fuzzy) breakpoint regression design! ⑤ 32 selected Articles of DID about the double difference method! ⑥ 33 selected Articles of SCM about synthesis control method! ⑦Compilation of the latest 80 papers about China's international trade field! ⑧Compilation of 70 recent economic papers on China's environmental ecology! ⑨A collection of selected articles using CEPS, CHARLS, CGSS, CLHLS database empirical research! ⑩Compilation of the last 50 papers using the system GMM to conduct empirical research!
The following short-linked articles belong to a collection, you can collect them and read them, or you won't find them in the future.
In 2.5 years, nearly 1,000 non-weighted measurement articles in the econometric circle,
You can search for any measurement related issues directly in the official account menu bar,
Econometrics Circle