Space Travel, Random walk, Forecasting
Improvement in a variety of technologies can often be successful modeled using a general version of Moore’s law (i.e. exponential improvements over time). Another successful approach is Wright’s law, which models increases in technological capability as a function of an effort variable such as production. While these methods are useful, they do not provide prediction distributions, which would enable a better understanding of forecast quality
Farmer and Lafond (2016) developed a forecasting method which produces forecast distributions and is applicable to many kinds of technology. A fundamental assumption of their method is that technological progress can be modeled as a random walk with drift.
We demonstrate a class of technology, space exploration, in which random walk with drift does not occur. This shows the need for alternative approaches suitable in such technological domains.
Howell, Michael; Berleant, Daniel; Aboudja, Hyacinthe; Segall, Richard; and Tsai, Peng-Hung
"Is technological progress a random walk? Examining data from space travel,"
Journal of the Arkansas Academy of Science: Vol. 75
, Article 14.
Available at: https://scholarworks.uark.edu/jaas/vol75/iss1/14