Analysis coaching for HR practitioners and I/O psychology graduates. Learn to work through any HR dataset: what's in it, what it's telling you, and whether it holds up.
Usually it's a spreadsheet and "can you take a look at this?" No hypothesis. Sometimes no idea what half the columns mean.
Before any chart or test, you have to work out what's in the file, what's broken, and what's worth asking.
That's most of the job. So that's where we start.
rows & columns → how big is the dataset?data types → is salary stored as a number?missing values → drop, fill or flag?outliers → typo or real?relationships → does pay move with level?You've done the stats. Not on a messy HR file with a deadline.
You ran the engagement survey. Now you're the one who has to make sense of it.
Someone will ask if the programme worked. You want a better answer than attendance.
You're changing careers and need the analysis side to hold up.
The kind that come up in a leadership meeting.
Production says one thing, IT says another. Is the gap real, or just two very different-sized teams?
Same people, scores before and after. Did anything actually change?
A thousand survey responses. Work out which few matter.
Pay is set by job, level and location. If men and women are spread differently across those, the averages show a gap even when people in the same role are paid the same.
A regression pulls those apart. It's the check you run before anyone quotes the number.
Check what you've got: types, gaps, outliers, how the columns relate. Build new fields like tenure bands. Come back with three things worth looking into.
Turn Likert answers into percent agreeable, work out eNPS, and check the questions hang together before you report on them. Overall picture first, then cut by team.
Pick the right t-test for the question, and ANOVA when there are more than two groups. Read the means next to the p-value, and know when a significant result doesn't matter.
When groups differ in level, job or location, a straight comparison can mislead. Regression shows what's actually driving the difference.
This isn't a course. There are no videos to get through, and nothing that marks you right or wrong.
You do the analysis and bring it back. We go through it with you, line by line.
Homework starts on our datasets and moves toward the analysis you actually do at work.
We work out where you are, what you need to answer, and which tools you'll use.
Live, one on one. We work through the concept together.
A question to work through on your own before the next session.
We go through your work together: what works and what to fix.
Stuck? Message us. No need to wait for the next session.
"I worked with Aaron and Abhinav to upskill my data analysis abilities, specifically in Python. I was able to build the right skills fast with the project-based format and dedicated live feedback sessions."
"I was particularly impressed by how they assigned practice problems, allowing me to apply what I had learned and receive valuable feedback."
"The training I received from Abhinav and Aaron in analytics and R was outstanding. They helped me understand how to use the tools as well as how to broadcast my analysis efficiently."
"They helped me understand the parts of data work that used to feel confusing, like cleaning datasets, building visuals, and getting comfortable with Python. They explain things in a way that feels down-to-earth."
"Aaron and Abhinav helped me … build a solid foundation in Excel and data analysis. Their expertise in statistics and various programming tools was evident and incredibly beneficial."
"DataSkillUp takes a thoughtful approach to supporting individuals in their learning journey. I would absolutely recommend connecting with [Aaron] and Abhinav if you're looking to build confidence in analytics, whatever your background or starting point."
Sessions booked at whatever cadence your calendar allows.