SQL Analysis Project: Identifying Outliers and Department Statistics

[@simonoganga9535]

Wow, this is an amazing tutorial packed with a lot of content to boost SQL learning. Thank you so much for this.

[@JW-pu1uk]

Coming back to this to let you know what a phenomenal tutorial this is!

[@absentdata]

Awesome. I am glad that you are enjoying it. I enjoyed making it!!

[@ericaleverson9430]

Thanks for sharing. I will use this as a project at work.

[@diamondsandlipgloss]

I'm unable to import the excel file. my errror message says I do not have a configuration string or file set up. I googled the error msgs and apparently the Salary column cannot have "dbNull". Is this working in 2024 for everyone else?

[@Adeyeye_seyison]

Thanks a million sir, For the value adding contents...

[@theresaparker3384]

I really liked this video. I thought you explained difficult concepts i. An easy to understand format and in a brief manner. Kudos! I loved seeing the statistics in SQL! I havent noticed many content creators covering statistics using SQL like you did. Would love to see more projects like this!!

[@absentdata]

I love the feedback. I would love to provide more of these types of videos. Its important to understand not only the techniques but also analysis. Please share them with anyone you think it will help

[@theresaparker3384]

@Absent Data I agree! I would be intrigued to see an expanded video that also includes a data visualization piece. I am curious how you would visually present this to an audience (like a box/whisker plot) that is not technical like executive leadership. Just a thought!

[@zanderrita2526]

Wow thank you for sharing sir

[@tboykelvin1865]

Thank uuu

[@nahavasa]

Thanks very much sir. I'll definitely do this project later. Can I use this project to my portfolios?

[@absentdata]

Of course!

[@camomile4085]

WITH cte1 AS ( SELECT *, AVG(salary) OVER (PARTITION BY department) AS salary_avg, STDDEV_SAMP(salary) OVER (PARTITION BY department) AS std_dev FROM employee_salaries WHERE Salary >= 10000 ), cte2 AS ( SELECT *, (salary - salary_avg)/std_dev AS z_scores FROM cte1 ), cte3 AS ( SELECT cte2.department, cte2.salary_avg, cte2.std_dev, ROUND(cte2.std_dev/cte2.salary_avg*100,2) AS Coefficient_of_variation, SUM(CASE WHEN ABS(z_scores) > 1.96 THEN 1 ELSE 0 END) AS Ouliers_count FROM cte2 GROUP BY cte2.department, cte2.salary_avg, cte2.std_dev ) SELECT * FROM cte3 ORDER BY Coefficient_of_variation DESC ;

[@carolinecarr56]

Can we also get the database to we can follow along??

[@absentdata]

Added the dataset to the description.

[@simonoganga9535]

How can someone reach you Sir(email, linkedin, etc)? Your teaching is AMAZING

[@absentdata]

You can reach me on Linkedin. My contact is in the profile.

[@tboykelvin1865]

Thank uuu