Comparing correlation in the FiveThirtyEight and Economist election forecasts

FiveThirtyEight and The Economist take similar inputs but output different forecasts. Adam Pearce was curious about how the state-by-state correlations differed between the two models:

Outside of the CA-DC-VT-WA and LA-MS-ND-KY clusters, where the 538 correlation dips below 0, the models are mostly aligned. Glancing over the outliers, it looks like the Economist might not have an equivalent to 538’s regional regression that groups states in the same geographic region together; the Economist has HI at 0.2 correlation with WA & OR while 538 has it around 0.7.

Tags: , , ,

Using the FiveThirtyEight model, see how the election odds shift with different scenarios

With each model update, FiveThirtyEight runs 40,000 simulations, or what-ifs, to calculate the odds for who will win the election. Their new interactive lets you experiment with all of the what-ifs to see how the odds shift when a candidate wins a state.

It answers the question, “If ______ wins in ______ and in ______, etc., what are the chances of him winning the whole thing?”

So if Trump wins a very red state or Biden wins a very blue state, the overall odds don’t change that much. But if a very red goes blue, or a very blue goes red, then the odds swing dramatically.

There’s a good lesson on conditional probability somewhere in there.

Tags: , ,

Tips for not letting polls and forecasts occupy your mind for two weeks

For FiveThirtyEight, Nate Silver provides tips to stay less stressed staring into the darkness known at election forecasts:

This is perhaps the single piece of advice we give most often at FiveThirtyEight, but it’s especially important in the final couple weeks of a campaign. After a lull this weekend, there are likely to be a lot of polls the rest of the way out. On any given day, it will be possible to take the two or three best polls for Biden and tell a story of his holding or expanding his lead, or the two or three best polls for Trump and make a claim that the race is tightening.

Resist buying too much into those narratives.

Good luck.

Tags: , ,

NBA playoff win probabilities, animated over time

FiveThirtyEight publishes win probabilities for NBA games throughout the season. During the playoffs, they show chances of winning each round, and with each game, the probabilities shift. Adam Pearce animated these shifts, from the start of the playoffs up to now.

Nice. The visualization. Not so much the Lakers.

Tags: , ,

How to vote in each state

Each state is handling mail-in voting in a certain way with varying timelines and rules. FiveThirtyEight provides a straightforward state-by-state guide so you can see what your state is doing.

I like the color-coded grid map doubling as quick navigation. You get the overview and a jump to the state of interest.

Tags: , ,

FiveThirtyEight launches 2020 election forecast

The election is coming. FiveThirtyEight just launched their forecast with a look at the numbers from several angles. Maps, histograms, beeswarms, and line charts, oh my. There is also a character named Fivey Fox, which is like Microsoft’s old Clippy providing hints and tips to interpret the results.

One thing you’ll notice, and I think newsrooms have been working towards this, there’s a lot of uncertainty built into the views. It’s clear there are multiple hypothetical outcomes and there’s minimal use of percentages, opting for fuzzier sounding odds.

Remember when election forecasting went the opposite direction? They tried to build more concrete conclusions than talking heads. Now pundits frequently talk about the numbers (maybe misinterpreted at times), and the forecasts focus on all possible outcomes instead of what’s most likely to happen.

Tags: , , ,

Where unemployment benefits are higher than lost wages

Economists at the University of Chicago analyzed unemployment benefits from the CARES act and compared them against median salaries for different occupations and by state. FiveThirtyEight highlighted the differences:

The researchers uncovered other kinds of inequality, too. In some professions, like janitorial work, people who are employed by essential businesses are continuing to show up to their jobs under hazardous conditions. But in doing so, they may be eligible for less money than janitors who have been laid off or furloughed by a nonessential business. In an ideal world, Ganong said, the people who have kept working at hospitals or grocery stores would be receiving some kind of hazard pay. “But that’s generally not the reality, which means there’s a weakness in the current system,” he said. “We’re giving more money to certain workers to stay home than to other workers who are putting themselves at risk by going to work.”

I don’t know the right answers to any of this, but it underscores the difficulties of making decisions based on averages. The system is built for simplicity and basic values. How do we adjust or rebuild the system for real-world variation and distributions?

Tags: , ,

Comparing Covid-19 models

FiveThirtyEight compared six Covid-19 models for a sense of where we might be headed. With different assumptions and varying math, the trajectories vary, but they at least provide clues so that policymakers can make educated decisions.

If you’re interested in the data behind these models, check out the COVID-19 Forecast Hub maintained by the Reich Lab at the University of Massachusetts Amherst. They helped with the FiveThirtyEight comparisons and are also the source for the official CDC forecast page.

Tags: , ,

Challenges of making a reliable Covid-19 model

Fatalities from Covid-19 range from the hundreds of thousands to the millions. Nobody knows for sure. These predictions are based on statistical models, which are based on data, which aren’t consistent and reliable yet. FiveThirtyEight, whose bread and butter is models and forecasts, breaks down the challenges of making a model and why they haven’t provided any.

Tags: , ,

Super Tuesday simulator

With Super Tuesday on the way, there’s still a lot of uncertainty for what’s going to happen. FiveThirtyEight has their forecast, but even with results expressed as odds and probabilities, the outcome almost seems static and concrete. So FiveThirtyEight has a different way of poking at their forecast. Pick the winners in each state, note how the conditional probabilities change as you go, and see what might happen in the rest of the primary given your picks.

Tags: , , , ,