91–100 of 144 posts
Earlier quoted context omitted.
"if I were to round a 21.4% to 20%" Right, but you'd round 21.4% to 21%, not to 20%.
Or ideally keep 21.4% and include the 95% CI. There’s nothing misleading about the extra precision when the CI is included.
Earlier quoted context omitted.
You are confusing confidence intervals (used to say that you are confident the increase is positive at all) with error margin (the false precision in the 3rd significant figure).
That does not bode well for the rest of the methodology...
//> we finally have an absolute number of sales measured, but no way of knowing - representing all sales within a period or just cherry picked?
//> for the rest of the population, did it reduced sales?
//> was there any randomised test or not, because in the latter case there could be other biases we're unaware of
//> the increase is compared to what exactly?
//> any WHY is purely speculative as what was measured was WHAT people did. Internal motivation is in this case unproven, there is just a potential correlation.
//> confuses me to hell people taking about error margins and confidence intervals for something measured directly.
"People said they were 14.2% more likely to buy this chocolate bar when they were shown the version with a cost breakdown." What people say they would do and what they actually do are 2 very different things. The conversion rate of actual behavior needs to be tested for this to mean something useful.
Earlier quoted context omitted.
Thank you so much! I agree that the figures can vary for many reasons and we shouldn't expect them to be exactly the same (some things we don't end up controlling for). At the same time, if we take the experiment of the soup for example: They measured 9,227 sales of it so the 21.1% increase is quite robust and I'd expect the error margin to be much lower than 5% either way - so in some ways the precision is warranted…
"if I were to round a 21.4% to 20%" Right, but you'd round 21.4% to 21%, not to 20%.
"People said they were 14.2% more likely to buy this chocolate bar when they were shown the version with a cost breakdown." What people say they would do and what they actually do are 2 very different things. The conversion rate of actual behavior needs to be tested for this to mean something useful.
Author of the summary here: You are right regarding the chocolate bar experiment. That's why the researchers ran multiple experiments, some of which measured actual behavior: - People were 16.1% more likely to bid for a gift card for an Everlane backpack (vs a J.Crew one) when they saw cost information about it - Sales of chicken noodle soup bowls ($4.95) in Harvard’s campus canteen increased 21.1% when costs were di…
You're also lacking cases where the markup is high, 500-2000% is common among a wide range of products, from Fashion to SaaS.
Edit: I'd also add, in the case of food products, if all vendors adopted the transparency strategy, once consumers see typical margins in that industry are in the 5-10% range, suddenly that not-unreasonably-priced organic chocolate bar looks like a high margin item...
Earlier quoted context omitted.
Yes, but will you be the one to explain that cost accounting to each buyer? "Yes Maaam, we'll spend $200 of the money you're about to give us on a fancy campus with hammocks to try to attract good engineers. Oh, and the massive billboard outside that made you walk into the shop in the first place."
TBH, I've consistently found that "average people" have a better intuitive understanding of costs/profit than the average engineer. That may sound strange, at least it does to me, but I've noticed it for as long as I've been in this profession.
They did quite well, which probably had a lot to do with coming across as honest. Certainly more honest than the kind of vendor where you have to ask some guy with a really fancy watch for a quote - I've met a couple of those.
Earlier quoted context omitted.
"21.1% more likely" is how articles phrase a 21.1% increase in observed frequency. "Sales increased 21.1%" is equivalent as long as the unit price remained the same.
The article is very confusing on this front. > People said they were 14.2% more likely to buy this chocolate bar when they were shown the version with a cost breakdown Surely that cannot be correct. Possibly 14.2% of the people who were asked said that they would be "somewhat" more likely to buy X with more data stuck to its label (does any data improve sales? Did they A/B the label by adding random info?). This is v…
Earlier quoted context omitted.
Author of the summary here: You are right regarding the chocolate bar experiment. That's why the researchers ran multiple experiments, some of which measured actual behavior: - People were 16.1% more likely to bid for a gift card for an Everlane backpack (vs a J.Crew one) when they saw cost information about it - Sales of chicken noodle soup bowls ($4.95) in Harvard’s campus canteen increased 21.1% when costs were di…
It's kind of lazy of you to disclose the Backpack and Chicken Soup cases in a declarative way. You present no references, no drill-down on whether all other effects were equal in these cases. For example, did chicken soup sales continue for an extended period of time and were not driven by other factors such as "a cold going around" or low temperatures? Trust is certainly a factor in consumer behavior, but it nowhere…