https://www.lecy.info/home daily 1.0 2025-07-23 https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1440362528040-7NG33QX9HXCFMB3Y9OD6/image-asset.jpeg Home https://www.lecy.info/data-driven-management daily 0.75 2018-08-26 https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1466357319238-9N7ZA3HWLGZ9CJO5E4FP/image-asset.png Data-Driven Management https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1440364830367-D1V6SUKV1099E3LMM1GV/image-asset.png Data-Driven Management https://www.lecy.info/r-for-public-policy daily 0.75 2019-02-04 https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1491093143703-XYVJVESS0BBHMMGDRSP3/image-asset.png R for Public Policy https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1546801832661-SXMKFSA7YR9B8SJU9KCB/image-asset.png R for Public Policy Image and data from Zip Recruiter spring 2019 https://www.lecy.info/teaching daily 0.75 2024-10-03 https://www.lecy.info/contact-me daily 0.75 2015-08-24 https://www.lecy.info/program-evaluation daily 0.75 2019-07-25 https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1503519821265-BJ7CYV3G0A4PAUMM4YZ4/reg_sample_orange.gif Program Evaluation https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445295667847-YR71M68YGGUBM20KL8BX/image-asset.gif Program Evaluation Demonstration of 95% confidence intervals. Approximately 95 out of 100 samples will result in confidence intervals that contain the true slope. Note, if a confidence interval contains zero, the slope is not statistically significant at the 0.05 level. https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445297152740-X96V20MWLTN1LFGU0GQU/increase+sample+size Program Evaluation If we have a small sample size, but a large effect size, we still have good statistical power. There is a trade-off between the size of the program effect, and how much data we need to detect it. https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445296950584-BSPUN5G4ZF79MND0UWBZ/image-asset.gif Program Evaluation https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445295683822-IR5UDBNRVMI9F9B3AN2B/image-asset.gif Program Evaluation If we want to increase the statistical power to ensure that we have more confidence in our results (achieve statistical significance) we can increase the sample size from 10 to 25. Notice how much smaller the confidence intervals become. https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445297080363-ATYX0R2EV9P4N33CGKXB/image-asset.gif Program Evaluation https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1488562701461-8KF5IMDMXKWMMGDH3T7H/image-asset.gif Program Evaluation https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445296971805-Q2PE725YQOEVT67LCGTZ/measurement+error+in+in+pos.gif Program Evaluation https://www.lecy.info/urban-policy daily 0.75 2019-03-08 https://www.lecy.info/projects daily 0.75 2024-10-03 https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1440361106417-5PVGRF508RDDDIFA1BB3/image-asset.jpeg Projects https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1483384292366-1YLBJEKDUWFEV26BFICP/image-asset.png Projects https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1440373299020-51M92HL4HDBGDTCPH1D8/image-asset.png Projects https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1440355383142-95GU201IDW66KRP6YP35/image-asset.png Projects https://www.lecy.info/r-meetup daily 0.75 2016-04-15 https://www.lecy.info/reg daily 0.75 2016-01-22 https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445295667847-YR71M68YGGUBM20KL8BX/image-asset.gif Regression Simulations Demonstration of 95% confidence intervals. Approximately 95 out of 100 samples will result in confidence intervals that contain the true slope. Note, if a confidence interval contains zero, the slope is not statistically significant at the 0.05 level. https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445297152740-X96V20MWLTN1LFGU0GQU/increase+sample+size Regression Simulations If we have a small sample size, but a large effect size, we still have good statistical power. There is a trade-off between the size of the program effect, and how much data we need to detect it. https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445295683822-IR5UDBNRVMI9F9B3AN2B/image-asset.gif Regression Simulations If we want to increase the statistical power to ensure that we have more confidence in our results (achieve statistical significance) we can increase the sample size from 10 to 25. Notice how much smaller the confidence intervals become. https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445297080363-ATYX0R2EV9P4N33CGKXB/image-asset.gif Regression Simulations https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445296971805-Q2PE725YQOEVT67LCGTZ/measurement+error+in+in+pos.gif Regression Simulations https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1445296950584-BSPUN5G4ZF79MND0UWBZ/image-asset.gif Regression Simulations https://www.lecy.info/data-for-good daily 0.75 2019-05-08 https://images.squarespace-cdn.com/content/v1/55d9f3fbe4b001723c108c17/1545934260339-6RAGNQBPWE7J84NO75EN/how-to-benefit-from-big-data.png Data for Good https://www.lecy.info/home-montauk daily 0.75 2025-05-09 https://images.squarespace-cdn.com/content/v1/5052176b84aeb45fa5cfcc83/1349577199654-C8A6HP2M4MLEBJXQ06MF/wilderness.png Welcome - Transient