Week 5: Maximum Likelihood Estimation and Heteroskedastic Regression

Schedule of the Week

Date	Time	Item	Place
Tue, Mar 10	13:30–14:30	Office hours (Thomas)	A5, 6, B 220
	15:30–17:00	Office hours (Domantas)	A5, 6, B 226
	15:30–17:00	Office hours (Lisa)	Zoom
Wed, Mar 11	8:30–10:00	Lecture	A5, 6, B244
	12:00	Homework 3 is assigned	Github
Thu, Mar 12	10:15–11:45	Lab (Domantas)	B6, 23-25, A 103
Fri, Mar 13	10:15–11:45	Lab (Lisa)	A5, 6, B143

Study Notes

Make sure you closely (re)-read the entire King’s UPM, chapter 4. For those of you who appreciate a slightly different take on MLE take a look at Eliason (1993). Please also read a short section in Long (1997) chapter 3.6.1 and 3.6.2 in order to get a sense of how to actually estimate standard errors using maximum likelihood. For an nice application on how to set-up a heteroskedastic regression model take a look at the “classic” Franklin (1991) paper (this paper will also be relevant for your third homework!). Alternatively, another interesting application of a heteroskedastic regression model is found in Golder and Lloyd (2014).

Readings


	King, Gary. 1989. Unifying Political Methodology. Ann Arbor: University of Michigan Press. Chapter 4.	Required
	Long, J. Scott. 1997. Regression Models for Categorical and Limited Dependent Variables. Thousand Oaks, CA: Sage. Chapter 3.6.1 - 3.6.2.	Required
	Eliason, Scott R. 1993. Maximum Likelihood Estimation: Logic and Practice. Newbury Park: Sage. Chapter 1-4.	Required
	Franklin, Charles H. 1991. “Eschewing Obfuscation? Campaigns and the Perception of Senate Incumbents”. American Political Science Review 85(4): 1193–1214.
	Golder, Matt, and Gabriella Lloyd. 2014. “Re-Evaluating the Relationship between Electoral Rules and Ideological Congruence”. European Journal of Political Research 53(1): 200–212.

Last updated on 26 Feb 2026