A Relationship Model Between the Perceived Economic Value of Computer Operating Systems and Their Usability: All Variables Evaluated by Copilot AI

This article proposes and implements a relationship model between the perceived economic value of computer operating systems (OSs) and their usability where all the model variables are evaluated by the generative artificial intelligence (AI) robot Copilot of Microsoft. In the underlying study, the perceived economic value of a particular OS was estimated by a proxy variable, namely, the OS’s total cost of ownership (TCO) whereas the usability of the OS was gauged by eight usability variables corresponding to the eight major usability dimensions (1) Effectiveness, (2) Efficiency, (3) Learnability, (4) Memorability, (5) Safety, (6) Utility, (7) Ergonomics, and (8) Accessibility. All these variables were evaluated on a scale of 1 (the lowest or worst, as appropriate) to 10 (the highest or best, as appropriate) by the robot Copilot based on global users’ textual comments on the TCO and the above eight dimensions of the OS as appear all around the web. A total of 18 OSs were covered in the modeling, they being the popular versions of the three leading OS families of Microsoft Windows, Apple macOS, and Linux. Multiple regression of the TCO on the eight usability variables was performed, followed by individual simple regression of the TCO on each of the eight usability variables in a bid to avert multicollinearity’s effect. On the one hand, the multiple regression rendered a model with a coefficient of determination R² = .853 and an F-statistic = 8.290 (df = 7, 10; p = 0.002 < 0.01) and (2) Efficiency being the only usability variable statistically significantly (p < 0.05) but negatively impinging on the TCO. On the other hand, the individual simple regression models revealed that in an individual manner, (2) Efficiency (R² = 0.562; F = 20.542 (df = 1, 16; p = .000)), (5) Safety (R² = .547; F = 19.335 (df = 1, 16; p = .000)), (6) Utility (R² = .392; F = 10.331 (df = 1, 16; p = .005)), and (7) Ergonomics (R² = .253; F = 5.431 (df = 1, 16; p = .033)) all statistically significantly but negatively impacted the TCO. Deducing from these models, the better an OS in these four usability dimensions, the lower its economic value as perceived by the market was. In other words, the market of OSs did not seem to have priced in usability or seemed to have even priced in them in a direction at odds with intuition and logic. These confounding results may be ascribable to multicollinearity and probably imperfection of the current generative AI technology, on which this study heavily hinged. After all, the multiple regression model predicts and explains the TCO and thus the perceived economic value very well.