Reid Hoffman Quotes

Every time I think that political analysts and writers will finally recognize that most of them don't understand much about political polls, they prove me wrong. They don't know how to read them; they don't understand the importance of cross tabs within a given poll, and they don't know how to analyze them.

Everyone takes surveys. Whoever makes a statement about human behavior has engaged in a survey of some sort.

Sampling, statisticians have told us, is a much more effective way of getting a good census.

All of the studies we do in my group are quantified.

Bobby and I went through some old questionnaires about customer requirements for languages, then we compiled a new one and sent it out to a few dozen people we knew.

In order to create predictive algorithms, you need to have a training set. So, that training set is created through our quantitative surveys. Those surveys need to include either basic market research questions or basic political polling questions, which might be added to get your opinion on a brand or an issue or a candidate.

I think polling methodology is broken.

If you're a social scientist worth your salt, you never do a univariate analysis.

There's a lot of work to be done in the polling world, and a need to continue to rethink how we do what we do. We also need to be more open to the idea that any one input - in this case, polls - may not be the only way to hear what people are saying.

I'm a pollster by trade, so I'm into things that are actually quantifiable.

The problem is that when polls are wrong, they tend to be wrong in the same direction. If they miss in New Hampshire, for instance, they all miss on the same mistake.

Much of what I do in my job is think about whether relationships we see in data are causal, as opposed to just reflecting correlations. It's exactly these issues which come up in evaluating studies in public health.

I don't think the Gallup Poll technique is going to be very helpful in determining the goals of our educational system.

In the early days, I promoted the idea of spending time in libraries to gain facts that other investors didn't have. Not many people did that kind of research, so it worked.

The type of measure used placed constraints on which statistics can be used.

We saw that our customers required help beyond the data sets they had and that they could benefit from a wider opinion. So we built SurveyMonkey Audience, and we've now got 4 million users who signed up to take surveys. Our clients can choose the demographic they want to hear from, and we can provide that sample.

I am a data hound and so I usually end up working on whatever things I can find good data on. The rise of Internet commerce completely altered the amount of information you could gather on company behavior so I naturally drifted toward it.

There is a reasonable concern that posting raw data can be misleading for those who are not trained in its use and who do not have the broader perspective within which to place a particular piece of data that is raw.

If you believe these polls, you're making a mistake.

If your experiment needs statistics, you ought to have done a better experiment.

I really like the mission at SurveyMonkey, which is, we help people make better decisions. It's just a great thing.

For 'Power of 10,' you can look at the methodology at CBS.com, it's a company called Rasmussen Reports. We poll thousands and thousands of people for each question, a real cross section of the United States.

USA Today has come out with a new survey - apparently, three out of every four people make up 75% of the population.

If you aren't taking a representative sample, you won't get a representative snapshot.

Certainly, last year we did an episode about the census and sampling versus a direct statistic. You just said the word 'census,' and people fall asleep.