Predictive Modeling 

for the US Non-Profit Sector

Quevedo, Francisco J. and Quevedo-Prince, Andrea K. (2019) "Predictive Modeling for the US Non-Profit Sector" Advanced Journal for Social Sciences, ISSN: 2581-3358 Volume 5, Issue 1, pp. 1-9, DOI: https://doi.org/10.21467/ajss.5.1.1-9.

August, 2011. Andrea & Francisco in the WSKF World Championship in Tokyo.


The Non-Profit Sector contributes almost $1 trillion to the US economy, representing 5.4% of GDP, and generating over 12 million jobs in 2017. Researchers suggest that a better understanding of the factors that affect fundraising would be of great interest to policy makers and fundraisers. However, the workings of the sector are subject of much debate. Some relate its size to the Theory of Government Failure, while others propose that government funding does have a positive effect on revenues. Some have suggested they swing with Gross Domestic Product (GDP), but others contradict this view and contend that macroeconomic variables do not affect short-run dynamics. Some research found that non-profit revenues react more to economic upswings than downturns, but nationwide organizations relate the ups-and-downs to certain events, as they influence public awareness. Predictive modeling overall has focused on big-donor analytics, aimed at identifying potential sponsors. Our research set out instead to define a working model for the US Non-Profit Sector. After an exhausting search, we located complete time series for an emblematic segment, the environmental cause, Factor Analysis allowed us to pinpoint the independent variables. We found that Non-Profit Revenues (NPR) depend largely on Public Awareness, as measured by TV coverage, and on Disposable Personal Income (DPI), specifically:

NPR = -4401.542 + 528.327(DPI) +23.121(TVCoverage) + Ɛ

We replicated prior research, which sought out relationships between macro-economic variables and NPR. That study had discarded the correlation between GDP and NPR as obvious, but did not explore DPI as the determining factor, and stuck to single variable searches, finding a correlation between the Standard & Poors index and lagged NPR figures, with a correlation coefficient of 0.636. Our model's Pearson's R came up to 0.935, with perfect significance levels. Confirmatory Factor Analysis reaffirmed the fit of our equation, with an R² of 0.87.

Keywords: Non-profit revenue, Fundraising, Fundraiser, Donor, Predictive modeling, Social cause, Environment

Other publications: