## Bad Hessian « Computational social science blog

Here is a new blog on computational social science. Extra kudos for the name and the logo.

## Replication Data for “A New Multinomial Accuracy Measure for Polling Bias”

Replication data for our forthcoming Political Analysis paper on our new, multinomial accuracy measure for bias in opinion surveys (e.g. pre-election polls) has just come online at the PA dataverse.

## Stata Software for Assessing Survey Bias

BinaryApe / Foter / CC BYIn a recent paper, we derive various multinomial measures of bias in public opinion surveys (e.g. pre-election polls). Put differently, with our methodology, you may calculate a scalar measure of survey bias in multi-party elections. Thanks to Kit Baum over at Boston College, our Stata add-on surveybias.ado is now available…

## Open Census Data and Open Geo Data in the UK

I’ve just realised that Her Majesty’s government has released the results of the 2011 (!) census at the level of individual output areas. Output areas are small, socially homogeneous cells with an average size of about 300 residents. In other words: The information is incredibly detailed, which is a bit worrying on one level (I…

## A Scalar Measure for Bias in (Multi-Party Pre-Election) Surveys

All surveys deviate from the true distributions of the variables, but some more so than others. This is particularly relevant in the context of election studies, where the true distribution of the vote is revealed on election night. Jocelyn Evans and I present a method for calculating a scalar measure that neatly summarises such bias for multi-party elections. We also present a Stata module that implements our new method.

## nlcom and the Delta Method

The delta method approximates the expectation of some function of a random variable by relying on a (truncated) Taylor series expansion. In plain words, that means that one can use the delta method to calculate confidence intervals and perform hypothesis tests on just about every linear or nonlinear transformation of a vector of parameter estimates. Stata’s procedure nlcom is a particularly versatile and powerful implementation of the delta method. If you can write down the formula of the transformation, nlcom will spit out the result. And that means that you can abuse Stata’s built in procedures to implement your own estimators.

## Statistical Songs Roundup

Today is clearly a day for statistical songs (are there any other days?), so here are some links to get you started. To kick of the stat song roundup, here are some … interesting insights into the culture that is biostatics, complete with some remarkably dreadful audio material. Obviously, youtube has a whole channel devoted…