China
Africa
Explore chapters and articles related to this topic
An empirical model of low-cost carrier entry
Published in Budd Lucy, Ison Stephen, Low Cost Carriers, 2017
Once exogeneity of denkt and sdrkt (and related terms) is rejected, one needs an instrumental variables estimator for binary dependent variables. Moreover, GMM estimation would be required in case of rejection of the hypothesis of homoskedasticity of εkt. In order to test for this, a likelihood-ratio test of heteroskedasticity in the discrete-choice framework was performed after a maximum-likelihood heteroskedastic probit estimation. This test requires the specification of an indicator vector of suspected explanatory variables that could affect the unobservables, which, in this case, was set equal to [sdrkt−1, denkt−1, kmk].34 The null hypothesis of homoskedasticity was not rejected at 10% level of significance – the χ2 statistic with 3 degrees of freedom was 1.57 (P-value of 0.6671).
Linear Neighbor Network Coding
Published in Zihuai Lin, Design of Network Coding Schemes in Wireless Networks, 2022
The next step is to get μ1(t) and μ2(t). Bj is a L×1 indicator vector, with the lth entry set to one if Nj broadcasts the XORed packet in the lth state, and zero otherwise. Let Aj be a L×1 indicator vector, with the lth entry set to one if Nj broadcasts its original packet in the lth state and zero otherwise.
Spectral Clustering
Published in Charu C. Aggarwal, Chandan K. Reddy, Data Clustering, 2018
For a subset A of vertices V, its indicator vector is denoted by 1A=(f1,…,fn)T, where fi = 1 if vertex vi belongs to A and fi = 0 otherwise.
Automatic estimation of unknown chemical components in a mixed material by XPS analysis using a genetic algorithm
Published in Science and Technology of Advanced Materials: Methods, 2022
Ryo Murakami, Hideki Yoshikawa, Kenji Nagata, Hiroshi Shinotsuka, Hiromi Tanaka, Takeshi Iizuka, Hayaru Shouno
where is the upper value of the number of unknown peaks, and the unknown peak parameter set is , where is the indicator vector. This means that the number of unknown peaks is the sum of the indicator vector . Here, , and are the area intensity, peak position, and Lorentz natural width of an unknown peak, respectively.
Data integration for multiple alkali metals in predicting coordination energies based on Bayesian inference
Published in Science and Technology of Advanced Materials: Methods, 2022
Koki Obinata, Tomofumi Nakayama, Atsushi Ishikawa, Keitaro Sodeyama, Kenji Nagata, Yasuhiko Igarashi, Masato Okada
is a likelihood for the entire model set. We use to express the summation over all combinations of the indicator vector. For the prior distribution of the model specified by the indicator vector, , we set the Bernoulli distribution for each element of the indicator vector as
Multi-Keyword ranked search based on mapping set matching in cloud ciphertext storage system
Published in Connection Science, 2021
Tingting Xiao, Dezhi Han, Junhui He, Kuan-Ching Li, Rodrigo Fernandes de Mello
KeyGen: The data owner randomly generates the secret key using the probabilistic key function and sends the generated security key to the user, where are random invertible matrices, n is the size of keyword set, is an indicator vector and v is a positive integer whose value can be artificially set.Index building: The data owner extracts keywords from the plaintext document dataset and gets the keyword set . Next, the document index vector will be generated by the data owner for the document in the plaintext document dataset. If is contained in , the data owner sets the TF values of to the corresponding bit; otherwise, it is set as 0. Each of the document index vectors is traversed in turn, as shown in Figure 3. If the value of the x-th bit of the document index vector is non-zero, the corresponding keyword number for x is put into ; the next position of the document index vector is traversed, if otherwise. The mapping set of the numbers corresponding to keywords contained in plaintext document dataset can be generated by Algorithm 1. Identify different documents with document identifiers , , and then send to the private cloud server. The document index vector is extended to (n + 2) dimension by the data owner, who is supposed to set the (n + 1)-th bit and the (n + 2)-th bit to a random number and 1 separately. Afterward, the extended document index vector can be expressed as . At last, is split into by the data owner.