Status: First draft for comment
First of all, Value Prospecting is not intended to be ‘work’ it should be designed as a rewarding social interaction in itself – ‘meaningful fun’.
I would like to think that repose and reflection are a natural part of the rhythms of life. There is a Judeo-Christian tradition in the west that one day in seven is a day of rest…
It is a theme in this project that there may be a many contributing aspects (5 ‘whys’) behind every action or activity.
The ‘day of rest’ may have arisen in part to mitigate for the exploitation of people under the control of those who derive power and status from the work done (by serfs) for them.
The ‘day of rest’ approach (or an equivalent) allows time and energy to be directed towards family and society.
The practice also enforces a period of reflection. It could be argued that 14% of every person’s week has been excluded from the normal preoccupations of a working day, giving space for an alternative agenda based around universal values.
Conventional Moslem communities spend a similar if not greater amount of time, energy and thought focusing on non material values:- Five Daily Prayers (Salah), Friday Prayer (Jumu’ah), Recitation of the Quran, Charitable Acts (Zakat and Sadaqah), Fasting and Nightly prayers during Ramadan (Sawm, Tarawih)
So, how much time would the application I propose require, if we wanted to represent everyone and their values reasonably well? How many people do we need to be involved to assess impacts for actions that are common to millions of others?
Polling, public opinion, and sample sizes have been studied and theories and conventions exist to relate statistical significance and cohort/sample sizes See the Conjointly website for an example.
The sample sizes for questions affecting lots of people are surprisingly small, well within the 14% of time allocated by a weekly ‘day of rest’. In addition, this is a project related to social values, a project which aims to integrate global (and intergenerational) impacts with local and personal actions. It follows that many if not most of the core social values will be shared by large numbers of people.
For what it is worth to answer a question in a population of 1,000,000 with a 95% confidence interval and a 3% error margin requires a little under 1100 people (i.e. 0.11%) to respond. Approximately 1 in a thousand has to care enough to express themselves. This seems to me achievable, especially on important issues.
This may seem like an abstract and inaccessible (or incredible) way of thinking about sample size, but all I am saying is that “A reasonably representative and comprehensive registration of citizens values is a realistic objective”, and that “There are enough people interested in human and societal values, issues and prospects to achieve a representative register of citizens values in the spare time of volunteers”.
APPENDIX A
QUESTION TO CHATGPT “What is the sample size required for statistical significance in a poll”
See also Conjointly website for an example
ANSWER (ChatGPT)
The required sample size for statistical significance in a poll depends on several factors, including the desired level of confidence, margin of error, and the variability of the population being sampled. The formula for calculating the sample size in a simple random sample is:
n=(Z^2*p*(1-p))/E^2
where:
- n is the required sample size,
- Z is the Z-score corresponding to the desired confidence level,
- p is the estimated proportion of the population with the characteristic of interest,
- E is the desired margin of error.
The Z-score depends on the chosen confidence level, and common values include 1.96 for a 95% confidence level.
The margin of error is the maximum amount by which the sample estimate is expected to differ from the true population value.
The estimated proportion (p) is often set at 0.5 when there is no prior knowledge about the proportion in the population, which maximizes the required sample size, providing a conservative estimate.
Keep in mind that the formula assumes a simple random sample and certain conditions. If your sampling method is more complex or if your population has specific characteristics, you might need to adjust the formula accordingly.