How scientists use statistical deception

... to fake influenza vaccine effectiveness

Note: As we approach the dreaded "FLU SEASON" which is now like the season of Rudolph the Red Nosed Reindeer in my house, 10 months a year, we are pleased to share this article from VacTruth.

By Tom Stavola

Statistical manipulation misinforms people by use of false measurements.

Vaccine scientists often conceal the true effectiveness of the influenza vaccine through risk calculations. Researchers use a calculation that essentially artificially inflates the effectiveness of influenza vaccines. Rather than use the statistical measure that more truthfully represents vaccine effectiveness, the researchers choose to use a statistical measure that makes vaccines appear more effective than they truly are.

Why is this important?

The published studies that report high effectiveness rates are then used by governmental agencies, your pediatrician, and mainstream media to attempt to increase influenza vaccine uptake rates. In other words – it is a tactic designed to convince you to get the flu vaccine every year.

To understand this specific deception technique, you will need to understand two risk concepts used to obscure findings: Relative Risk (RR) and Absolute Risk Reduction (ARR).

Relative Risk (RR) Explained

Relative Risk compares the chance of a bad outcome between two groups. Statistical definition: the proportion of bad outcomes in the experimental group (group #1) divided by the proportion of bad outcomes in the control group (group #2). Relative Risks under 1.0 indicate the tested medical intervention helped patients, while relative risks over 1.0 indicate the medical intervention hurt patients.

Absolute Risk Reduction (ARR) Explained

Absolute Risk Reduction measures the absolute difference in bad outcomes between two groups (group #1 and group #2). Statistical definition: the proportion of bad outcomes in the control group minus the proportion of bad outcomes in the experimental group (in this case, a larger number means the treatment was helpful, while a small number means the treatment didn’t do much to help, and a negative number means the treatment was hurtful).
Why RR and ARR are Different

Relative risk tells you how badly one group fared in comparison to another group, in relative terms. It’s akin to saying, “Johnny jumped half as high as Timmy” – but you never know how high each of them jumped. Absolute risk reduction – on the other hand – tells you the actual difference in outcomes between the two groups. This would be akin to saying, “Johnny jumped 8 feet high, but Timmy jumped 16 feet high.” One can see that the absolute risk reduction is a more helpful, informative statistical measure; whereas, it’s easier to hide the magnitude of the differences behind relative comparisons.

Again, why is this relevant to vaccines?

The general public is interested in one question: if I choose to get the influenza vaccine, will my chances of getting the flu decrease, and by how much? We are not interested in relative comparisons, we are interested in actual, true differences.

Let’s break down a practical example into 4 easy steps to demonstrate the disparity between relative risk (RR) and absolute risk (AR).

Step 1: Define the Two Groups

Good scientific practice is to separate people into groups as closely numbered as possible, and as well matched as possible, meaning, we attempt to compare groups of people in which all variables are the same (or very similar) except the one variable we’re testing. This way, we can tell that any significant difference between the two groups is due to the variable we’re testing, and not some other variable.

One of the groups will receive the treatment (let’s say vaccine), and another group will receive nothing. This is called the control group. Typically, gold standard medicine would dictate using a saline placebo on the control group (a placebo is a harmless substance that has no effect – used to make the control group think they’re getting the treatment).

In most vaccine experiments, researchers incorrectly use another vaccine or a vaccine ingredient as the placebo. This way, the differences between the two groups will be reduced (muted), and the researchers can report in their conclusions, something to the tune of, “vaccines didn’t increase the amount of adverse reactions significantly.”

So – back to our example.

Let’s assign 25 people to the control group (these people receive the “placebo” that is actually another vaccine or a vaccine ingredient), and 25 people to the vaccine exposed group (these will be the people who get the vaccine).  Read the rest of this article and take a good look at the graphics here.


By Tom Stavola
(Source:; August 14, 2018;
Back to INF

Loading please wait...