Menu

Post image 1
Post image 2
Post image 3
Post image 4
Post image 5
Post image 6
1 / 6
0

Correlation vs. Causation: Measuring True Impact with Propensity Score Matching | Towards Data Science

Towards Data Science·Gustavo Santos·about 1 month ago
#92oaIx3a
Reading 0:00
15s threshold

task in Data Science, especially if we are performing an A/B Test to understand the effects of a given variable over those groups. The problem is that the world is just… well, real. I mean, it is very beautiful to think of a controlled environment where we can isolate just one variable and measure the effect of it. But what happens most of the time is that life just runs over everything, and the next thing you know, your boss is asking you to compare the effect of the latest campaign on customers’ expenses. But you never prepared the data for the experiment. All you have is the ongoing data before and after the campaign. Enter Propensity Score Matching In simple terms, Propensity Score Matching (PSM) is a statistical technique used to see if a specific action (a “treatment”) actually caused a result.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More