The name is absent



T2.

3.7 Results

In this section we present analysis and results by applying the proposed method to
the phage display data described in section 3.3.

The parameter values in our proposed priors are elicited by consulting with the
investigators. The values of the hyper-parameters are the same as the ones used in
the simulation study. The parameter
μi is interpreted as the expected counts if there
were no enrichment of the library of tripeptides at every stage and this is the case
for the first stage. We assume that most of the phage counts are small in the initial
state. Therefore, we set the expected value for the first stage counts
μi to 0.1 and its
variance to 0.03. We do not assume any knowledge of the means increment between
the first and the second stage (in terms of
βi) and between the first and the third
stage (in terms of
δi). We center these values around 6 allowing for a large variance
equal to 180.

We obtained a Monte Carlo posterior sample of size M = 5,000 storing the values
of the imputed parameters every ten iterations after a burn-in of 10,000 iterations.
Analogous to the simulation study, we performed convergence assessment for the
proposed parameter values to ensure that the MCMC algorithm converged well. We
found that the Markov chains mixed very well and converges rapidly.

Table 3.1 shows the 30 pairs with highest values of mi, i.e the pairs chosen accord-
ing to the optimal rule (3.35) with a threshold value of seven. Figure 3.5 depicts these
pairs. We notice that there are some pairs, such as, the tripeptide ARF in the tissue
fat, that present a small posterior probability of increasing means,
ρl, that would not
be selected according to the decision rule (3.31) but that are selected when using the
decision rule (3.35).

Using the optimal rule (3.35), with a threshold value of one, 219 tripeptide-tissue
pairs are selected. Figure 3.6 highlights these pairs. This criterion selects the pairs
clearly having high increasing counts across the three stages. Over some pairs with
nondecreasing counts, in agreement with its related utility function (3.34), the cri-



More intriguing information

1. The name is absent
2. Studying How E-Markets Evaluation Can Enhance Trust in Virtual Business Communities
3. Income Growth and Mobility of Rural Households in Kenya: Role of Education and Historical Patterns in Poverty Reduction
4. The name is absent
5. The name is absent
6. Om Økonomi, matematik og videnskabelighed - et bud på provokation
7. The name is absent
8. Structure and objectives of Austria's foreign direct investment in the four adjacent Central and Eastern European countries Hungary, the Czech Republic, Slovenia and Slovakia
9. LAND-USE EVALUATION OF KOCAELI UNIVERSITY MAIN CAMPUS AREA
10. Les freins culturels à l'adoption des IFRS en Europe : une analyse du cas français