They are saying iPhone demand is less responsive to price over time, but I disagree.

Income shifts the demand curve. Higher income exposes preference to more expensive phones, which makes it appear the consumer doenst care about price when in reality they have the same preference just scaled by income.

And it doesnt look sustainable, either, because the latest apple phones are price cut. There's additional factors like financing availability and competing products that make this not useful as a demand elasticity.

Am I right or they?


The way how they estimated elasticity is definitely not an accurate and unbiased way.

  1. You are correct that when you estimate elasticity it is important to control for income, but not only for that you should also have controls for prices of competing products and other relevant controls.

  2. Supply-Demand is an endogenous system and every observed price and quantity is result of an interaction of the two. In order to estimate elasticity some method that can model them simultaneously or allows for endogeneity is required. The author does not specify methodology used in the blog post but there is no indication that this was acknowledged.

  3. In order to make valid inferences from data when using parametric models you need at least 25-30 observations per independent regressor (see Newbold et al statistics for business and economics for example). The blog post tries to estimate the elasticities from 3-6 data points (depending on the model). That is woefully inadequate.

So in conclusion even though the blog you refer to does not share it's methodology, it seems to be acknowledging neither of the issues above so their estimates of elasticities are likely biased.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy