just stop being petty guys

Thank you for inquiring. It forced me to verify the point.

I will have to recant my statement as I have mis-interpreted the talking point.

The correct statement is 32% of paternity test found fraud. Thus the sample is bias towards men who already have suspicion that their child may not be theirs. Thus we cannot conclude it to represent the whole population.

Roughly 300,000 paternity test are done yearly in the USA.

There's roughly 3,700,000 births per year in the USA.

The number of paternity test isn't the problem, because 300,000 test is significant enough to make the confidence interval small. But the sampling data is not random, thus it's not possible to determine how much of this can represent.

From wikipedia

Research published in 2016 indicated that one in 50 British fathers is unknowingly raising a child who is the biological child of another man, and that misattributed paternity is rarer than commonly believed.[4]

A 2005 scientific review of international published studies of paternal discrepancy found a range in incidence, around the world, from 0.8% to 30% (median 3.7%).[5] However, as many of the studies were conducted between the 1950s and the 1980s, numbers may be unreliable due to the inaccuracies of genetic testing methods and procedures used at the time. Studies ranging in date from 1991 to 1999 quote the following incidence rates: 11.8% (Mexico), 4.0% (Canada), 2.8% (France), 1.4% and 1.6% (UK), and 0.8% (Switzerland).[5] These numbers suggest that the widely quoted and unsubstantiated figure of 10% of non-paternal events is an overestimate. However, in studies that solely looked at couples who obtained paternity testing because paternity was being disputed, there are higher levels: an incidence of 17% to 33% (median of 26.9%). Most at risk were those born to younger parents, to unmarried couples and those of lower socio-economic status, or from certain cultural groups.[6]

A 2008 study in the United Kingdom found that biological fathers were misidentified in 0.2% (1 in 500) of the cases processed by the Child Support Agency. Of that 0.2%, those resolved with DNA paternity testing between 2004 and 2008 showed that between 10 and 19% of mothers had misidentified the biological father; data about why mothers identified the wrong biological father was not available

This is probably more correct as the study is more likely to be random sampling.

So I will now use 2% as the incident rate as the population as a whole.