Ideas for the online revolution.

Estimating Median Household Income by Block

I'm trying to make a higher resolution map of median household income. The Census Bureau releases income data by census tract (around 4000 people) and also by block group. Relatively few people use block groups because the confidence interval is too high. Even when you pool five years of data from the American Community Survey the confidence interval for census tracts (which have about 3 times more people than block groups) is high (and can be too high to use).

Philadelphia Exterior Property Condition Map

I made a new map of Philadelphia Exterior Housing Condition using the Office of Property Assessment data (2015).

It is part of a series of high resolution maps I've made for Philadelphia using property level data.

It is interesting to see what parts of the city have new construction, rehabbing, and vacant and/or uninhabitable properties.

Bitcoin - large price increase

I've been following Bitcoin since June 2011. You might be interested in my Bitcoin trading thread. Recently the Bitcoin price has soared to $700 which is a two year high. Most notably in the past three weeks it went from $450 to $700.

Prediction: DC

My model has this upcoming DC Democratic Primary at around Clinton 88 / Sanders 12.

Predictions: CA, MT, ND, NM, and SD

Here are my predictions for the June 8 Democratic presidential primaries.

This is from my county-level model which includes past election results, age groups, sex, education, FB likes, Google searches, density, income, caucus/primary, whether 17 year olds can vote, and more.

Predictions: Kentucky and Oregon

Here are my predictions for today's Democratic primaries in Kentucky and Oregon.

In the national polls Sanders has been losing 0.5-1%/week versus Clinton. The Google Search Trends reflect this. Previously Sanders was getting around 65% of the combined Sanders + Clinton search trend, but now this has fallen to around 56%. For instance, in the past 7 days even though it is one of the few states which has an active campaign left -- Sanders has only got 53.5% of the searches in Kentucky.

West Virginia Prediction

For WV I'm predicting Sanders 55.3 %, Clinton 44.7% (percent of the shared Sanders + Clinton vote).

Indiana Prediction

My latest Indiana prediction for the Democratic Nomination is Sanders 52.6 %, Clinton 47.4 %.

Sanders is doing very well in the search trend.

The model includes the polling data, FB likes, Google search trends, past election results, and demographics (race, income, sex, age, education).

Other Models
Tyler Pendigo - Sanders 52.6 / Clinton 47.4
Benchmark Politics - Clinton 51.4 / Sanders 48.2 (Other: 0.4%) - so rebalanced - it is Clinton 51.6 / Sanders 48.4
Pollster Average - Clinton 54.1 / Sanders 45.9

PredictIt - Clinton 72% chance of winning.

Early Projections: West Virginia, Kentucky, and Oregon

Early projections for upcoming primaries. Later projections are likely to be more accurate as they can incorporate polling data. I'm not using polling data at this time.

Indiana: Sanders: 50.3 / Clinton 49.7. Sanders search trend is strong, probably due to advertising.

Kentucky: Clinton 57.0 / Sanders 43.0. Sanders is down 1% from my last projection.

Oregon: Sanders 62.2 / Clinton 38.8. Sanders is down 8% from my projection a month ago. It includes the start of the Sanders big rally in Oregon (and the Google Search trend boost).

Early Indiana Projection

My early model for Indiana is projecting: Sanders 50.6 / Clinton 49.4

This is Sanders down 2.8% from the previous 53.4% projection. It also is in disagreement with the polls, 538, and PredictIt - who all say Clinton will win.

Syndicate content