Eylem Seç
Essays in Persuasion, Sampling, and Experimentation
Başlık:
Essays in Persuasion, Sampling, and Experimentation
Yazar:
Bardhi, Arjada, author.
ISBN:
9780438117396
Yazar Ek Girişi:
Fiziksel Tanımlama:
1 electronic resource (273 pages)
Genel Not:
Source: Dissertation Abstracts International, Volume: 79-11(E), Section: A.
Advisors: Asher Wolinsky; Bruno H. Strulovici Committee members: Georgy Egorov; Yingni Guo.
Özet:
This dissertation studies the optimal design of experiments concerning a multidimensional payoff state both in decision problems of a single agent and in environments involving multiple interdependent agents, such as hierarchical organizations and voting bodies.
The first chapter takes its motivation from the observation that most decisions-- from a job seeker appraising a job offer to a policymaker assessing a novel social program-- involve the consideration of numerous attributes of an object of interest. It studies the optimal evaluation of a complex project of uncertain quality by sampling a limited number of its attributes. The project is described by a unit mass of correlated attributes, of which only one is observed initially. Optimal sampling and adoption is characterized for both single-agent and principal-agent evaluation. In the former, sampling is guided by the initial attribute but it is unaffected by its realization. Sequential and simultaneous sampling are equivalent. The optimal sample balances the variability of sampled attributes with their usefulness in inferring neighboring attributes. Under principal-agent evaluation, the realization of the initial attribute informs sampling so as to better influence adoption. Sampling hinges on (i) its informativeness for the principal, and (ii) the variation of the agent's posterior belief explained by the principal's posterior belief. Optimal sampling is not necessarily a compromise between the players' ideal samples. I identify conditions under which mild disagreement leads to excessively risky or conservative sampling. Yet, drastic disagreement always induces compromise.
The second chapter, which is joint work with Yingni Guo, analyzes the problem of a fully committed sender who seeks to sway a collective adoption decision through designing experiments. Voters have correlated payoff states and heterogeneous thresholds of doubt. We characterize the sender-optimal policy under unanimity rule for two persuasion modes. Under general persuasion, evidence presented to each voter depends on all voters' states. The sender makes the most demanding voters indifferent between decisions, while the more lenient voters strictly benefit from persuasion. Under individual persuasion, evidence presented to each voter depends only on her state. The sender designates a subgroup of rubber-stampers, another of fully informed voters, and a third of partially informed voters. The most demanding voters are strategically accorded high-quality information.
The third chapter returns to the problem of attribute discovery by allowing for a larger class of distributions and attribute weights. An object considered for adoption is characterized by finitely many attributes, which follow an arbitrary jointly normal distribution. The analysis takes a network-theoretic approach to characterize the optimal sample of attributes by making use of the representation of the distribution as a Gaussian Markov Random Field. The main contribution of the analysis lies in the construction of a novel centrality measure within this correlation graph---inference centrality ---that captures the success of a sample in leading to the correct adoption decision. Inference centrality has a number of novel properties compared to other standard centrality notions: it is naturally defined over both single nodes and subsets of nodes, it considers all paths in the graph, and path discounting reflects the particular nature of the inference problem. I show that the inference centrality of a sample depends on (i) the inference value of each sampled attribute for unsampled attributes, (ii) the marginal precision of each sampled attribute, and (iii) the intra-connectedness of the sample. I then use the concept of inference centrality to characterize the optimal sample in two multi-player settings of separate sampling and adoption decisionmaking.
Notlar:
School code: 0163
Tüzel Kişi Ek Girişi:
Mevcut:*
Yer Numarası | Demirbaş Numarası | Shelf Location | Lokasyon / Statüsü / İade Tarihi |
---|---|---|---|
XX(693900.1) | 693900-1001 | Proquest E-Tez Koleksiyonu | Arıyor... |
On Order
Liste seç
Bunu varsayılan liste yap.
Öğeler başarıyla eklendi
Öğeler eklenirken hata oldu. Lütfen tekrar deneyiniz.
:
Select An Item
Data usage warning: You will receive one text message for each title you selected.
Standard text messaging rates apply.