Publication bias and confounders in product reviews - TAS, Stereophile, Audiogon, etcetera


Folks-

Since I am a research professor at a major medical school in the U.S., I am used to identifying and using statistical measures of such bias in scientific research.

In Japan, I have read that a product reviewer who writes for magazines or websites are paid fees by manufacturers. I have noted that a similar thing may be happening here in the U.S., both reading TAS, Stereophile, etcetera, as well as noticing comments from individuals on this and other websites, many of whom are also dealers of these products.

As an example, I am somewhat of a computer nerd and have been downloading high-resolution audio files for almost a decade. That being said, I have been looking to buy a relatively high-end SACD player for my large collection of CDs and SACDs. I have noted the following:

1. There are few-to-no reviews of DCS players (e.g., Puccini SACD player, somewhat outdated but can be upgraded) and almost no published U.S. reviews of the Marantz SA-10 SACD player that was released about a year ago. In contrast, SACD/CD players including those from Esoteric, Hegel (CD only), Ayre, PS Audio, MBL, and other brands commonly appear in formal reviews, which are all favorable. Does this mean that products which have been reviewed but which are not well-liked by reviewers are not published?;

2.  Comments in this and other forums mention that one or another SACD player or other product "must not be that good because they appear often as used equipment for sale..." or something to that effect. This observation may be valid, but could easily be confounded by the number of such products that were, or are, available for sale. The greater the number of products, the greater the likelihood they will appear as used items for sale - it says nothing about the quality of the product. I like to call this the "Ferrari effect", as this manufacturer intentionally limits the number of cars of any model for sale, and the company often only sells to individuals of affluence and/or have purchased cars from them in the past, artificially inflating the value of these cars; 

3. Odd statements about the interesting MQA file format, part of a larger problem of a lack of objectivity in the audiophile community. Recently I read in a publication - "MQA is to conventional audio what quantum mechanics was to classical mechanics" - Really? Does this individual know anything about physics? Or am I taking this all too seriously?

I guess I am asking about the degree of bias in these reviews, to what extent are products reviews influenced by the manufacturers and dealers, and where is the objectivity in this domain?

Thanks for listening to my ranting...Gerry 
128x128Ag insider logo xs@2xgerryah930
Few to no reviews of DCS players?

not sure you’ve been doing decent research then, the Rossini and Vivaldi have been reviewed at length on every mag and the network box is now getting a bunch of reviews

https://www.dcsltd.co.uk/products/vivaldi-dac/reviews
https://www.dcsltd.co.uk/products/rossini-player/reviews
https://www.dcsltd.co.uk/products/network-bridge/reviews

I would argue that in fact DCS is more reviewed than the others you mention

DCS do however try to manage the second hand market in a Ferrari like manner and hence you find factory approved used items from them which come with after sales service and software upgrades as opposed to the private sale non supported ones, obviously the latter are cheaper but the buyer has the choice of which way to go

As to the reviewers they all have biases which are not hard to spot once you spend time reading and listening. With so many on line opinions it’s not too hard these days to find someone who’s ears you trust

Ps the Puccini was also reviewed by both the main mags as well
https://www.dcsltd.co.uk/products/puccini-player/reviews

I think your conclusions are a bit flawed.  I can agree that TAS and 6 Moons are a pay to play, Stereophile is not in that category.  John Atkinson, the Editor of Stereophile is a man of high integrity.  I have met him, talked personally with him and he really adheres to the values that Gordon Holt put down for Stereophile in its infancy.  I know of one reviewer, Myles Astor who is honest as the day is long and would never be biased towards a certain manufacturer.

The SA10 only came out a year ago, so it is possible that the mainstream magazines will review them.  There really haven't been too many cd/sacd players reviewed over the past couple of years as most people are going for music servers and streamers instead.

I guess I am asking about the degree of bias in these reviews, to what extent are products reviews influenced by the manufacturers and dealers, and where is the objectivity in this domain?

In a nutshell, yes, most product reviews aren't worth the paper they are printed on. I let all of my glossy magazine subscriptions lapse many years ago. The only information to be found in these "reviews", or "ads" whatever you want to call them are photos and specifications.

These magazines/websites are part of the marketing branch of high end audio. So yes, they would rather write no review at all than a negative review. They might bash one of the smaller, non-paying players once in a while just for appearances.

Make no mistake, all reviewers are HEAVILY biased towards the manufacturers. Their job is to push product, an extension of the marketing department if you will
Post removed 

There are two factors here.  The speed with which products get reviewed.  (Time of product launch to time of review publication.)  And whether a brand/product gets reviewed at all.

The frequency with which Musical Fidelity appeared in the pages of Stereophile a few years ago was a running joke in the audiophile community.

Meanwhile, try searching for reviews of PMC speakers in those same pages.

Partly it has to do with company policy, partly how well a foreign company is represented in the US and what kind of PR campaign they sponsor, partly on reviewers' individual preferences, partly on kismet, and probably 3 or 4 other factors as well.

In short, it's hard to read anything into the patchy coverage other than it's undeniably patchy.