Hira Farooqi (Work Log)
19/06/2017 - Abstract added to Hubs (Academic Paper)
27/06/2017 - Cleaned data files for income at MSA level. Data description added to Income Data section on Hubs
28/07/2017 - Cleaned data files for income at MSA level. For further information on final income data tables and merging, refer to Income Data section in Hubs. Data on Houston's current entrepreneurial ecosystem, including R&D expenditure by firms, NSF, NIH grants and STEM Grad students compiled and added to the following location
10/07/2017 - Received VC data from Adrian. Cleaned and prepared data on grants (NSF, NIH, Clinical trials), income, publicly traded firms and other variables to merge with VC data. Further details in Hubs.
11/07/2017 - All previous data work on Hubs has been shifted to new page Hubs Summer 2016. The new master data set is titled final.txt. Hubs includes more information on the columns included in the final data set.
12/07/2017 - In addition to grants information on NSF, NIH and clinical trials, we also decided to add SBIR grants data to our final data set. SBIR are government grants given to small businesses. SBIR data and summary tables are now available in the cities db. Further information is included in Hubs.
13-14/07/2017 - The term hubs does not have a definition yet. In order to obtain a sample of hubs for this study, we need to finalize our definition of Hubs. Currently I am gathering further information on hubs listed in the sample of hubs from last year and deciding what the most suitable definition of hubs could be for our study. Updates posted on Hubs.
17/07/2017 - Last year a scorecard was used in order to determine whether a candidate hub would qualify to be in the study sample. This method produced a sample size of ~ 30. In order to increase the sample size, I have started working with 5 main characteristics that our sample hub should possess. Joe and I are going through the list of 125 candidate hubs from last year to check whether any hub rejected last year fulfills our slightly more "relaxed" definition. For further details see Hubs.
19/07/2017 - Developed the definition of hubs. Cleaned hubs data for stata.
20/07/2017 - Cleaned hubs data. Performed preliminary analysis for hubs in stata. See the section on analysis in page Hubs Analysis 2017.
21/07/2017 - review of propensity score matching.
24/07/2017 - Review of propensity score matching and the Hochberg and Fehder (2015) paper.
25/07/2017 - Review of instrumental variables in panel data methods.
26/07/2017 - in order to eliminate any endogeneity in the categorical variable "hub", a potential instrument is real estate taxes. If the real estate taxes are higher, there might be a higher demand for Hubs. Data on mortgage based real estate taxes was downloaded from the census data, using the American Communities Survey. A fixed effects IV regression shows that taxes don't perform as satisfactory IVs in this model.
31/07/2017 - Estimated hazard rate using stcox in stata. Relevant do-file is hubs_load_data. It is located in Z>Hubs>2017>hubs_data.
1/08/2017 - Explored stata routines for performing matching based on manually supplied scores. teffects only matches on automatically estimated probabilities. psmatch2 has more scope of taking a manually estimated variable to match on.
2/07/2017 - Estimated matched sample using Cox proportional hazard ratios. Relevant do-file is hubs_load_data. It is located in Z>Hubs>2017>hubs_data.
3/07/2017 - After matching on hazard ratios, we need to first create a panel of T-C observations for diff in diff. More explanation on processing data for creating this panel is in Hubs Analysis 2017.