The entire field of statistics is based on around the idea that we can quantify, extrapolate from, and analyze various types of data. Based on data, we can draw conclusions and inferences with which we can adjust our actions and behaviors.

The great and most apt quote that has ever been uttered about statistics is

Lies, damned lies, and statistics.

Statistics done poorly are probably the easiest way to bullshit a story to convince yourself of whatever you want to convince yourself of. Throw a bunch of scenarios together, do some cross correlations and t-tests and viola, you have a P value that's less than .05, and now you have publishable results.

And this is where you come in.

How many of you guys out there are using your wife as your sole metric of whether or not you're becoming more attractive? How many of you are not approaching other women for reasons? How many of you are then using your wife's responses to gauge how you're doing and whether or not your SMV is actually improving - whether that's looks, confidence, personality, or otherwise?

I'd be willing to bet it's more than a handful.

Since so many of you seem to be numbers and spreadsheet people, let's talk about what you're actually doing when you're doing this.

You're drawing conclusions and inferences based on 1 single data point. You're asking a question about a population (Women's interpretation of your SMV) based on a single sample. Do you know what the margin of error on your data point is? It's 98%. That's so wide as to be totally and utterly meaningless.

If there were 10,000 women that you thought were your target audience, you would need to interact with 370 of them to draw a conclusion with a 5% margin of error on the 95% confidence interval.

What this means in practical terms is that in order to know how you're doing in an SMV sense, you'd need to interact with that many women to figure out what percent of them might actually find you attractive. This means that if you're one of the guys who is deciding to let his wife be the arbiter of whether or not his SMV is increasing, you're putting yourself in a position to be doomed by dubious statistical interpretation. I'd caution you against this, but you're probably going to do what you're going to do anyway.

Alternatively, if that is the route you want to take, you'll probably want to study up on Bayesian Statistics and figure out how to draw inferences from consecutive events. From those instances, you'll probably want to assess the changing probabilities of the frequency of said events. But I'll leave that as an exercise to the reader.