Questions about Levitt & Syverson = quasi experiment

6 important questions on Questions about Levitt & Syverson = quasi experiment

What is the main difference between L&S and List’s design?

List is a true experiment with multiple groups and random allocation. L&S is quasi experiment with multiple groups, but no random allocation.
In the quasi experiment of L&S there is a control group (the clients) and the experimental group (the realagent selling his own house)

Compare internal validity and external validity of both papers (L&S vs List)

-Internal validity of List’s experiment is higher than L&S, because there are alternative explanations in L&S.
-External validity of L&S is higher, because the experiment of List is conducted in the lab that makes it more difficult to compare the results to the real world.

Which characteristics of positivism do you recognize in the approach of Levitt and Syverson?

-Ontology à observable data
-Epistomology à
oLarge sample
oDeductive
oDetached stance
oNumbers (quantitative)
oStructures
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

What are the independent and the dependent variables?

-Independent variable: houses being agent owned or not
-Dependent variable: days on market + selling price

Why do they researchers expect a cause and effect relationship?

-Agents have more information
-Misalignment of incentives (it is not worth his time to go to the max, so more time does not pay out for the agents)

Which covariates (a.k.a. control variables) did they include in the analysis? Which third variables are discussed? And which factors cause an interaction effect?

No random allocation has implications for internal validity. L&S tried to minimize Threats to Validity by analysis.
L&S include the control variable à  basic features of housing, characteristics (rooms; fireplace) has effect on both variables (independent an dependent). Control variables are alternative explanations but there is data available
L&S discussed the following third variable à less risk aversion by the agents. L&S does not have any data on risk aversion. Third variables are alternative explanations but there is no data available
Interaction effect à influencing the strength of the relationship of the dependent and independent variables. For example internet.

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo