Abstract
This work considers point and interval estimation based on data from a life test under progressive type-I interval censoring with random removal. The asymptotic properties of the maximum likelihood estimators (MLEs) are established under appropriate regularity conditions. Asymptotic confidence intervals and \(\beta \)-content \(\gamma \)-level tolerance interval are obtained by using the asymptotic normality of MLEs. A simulation study is undertaken to assess the performance of the MLEs, confidence intervals and tolerance interval. Lastly, the minimum sample size required to achieve a desired \(\beta \)-content \(\gamma \)-level tolerance interval is determined.
Similar content being viewed by others
References
Aggarwala R (2001) Progressive interval censoring: some mathematical results with applications to inference. Commun Stat-Theory Methods 30(8–9):1921–1935
Ashour SK, Afify WM (2007) Statistical analysis of exponentiated Weibull family under \(\text{ T }\)ype-\(\text{ I }\) progressive interval censoring with random removals. J Appl Sci Res 3(12):1851–1863
Balakrishnan N, Aggarwala R (2000) Progressive censoring: theory, methods, and applications. Springer Science & Business Media, New York
Balakrishnan N, Beutner E, Cramer E (2010) Exact two sample non-parametric confidence, prediction, and tolerance intervals based on ordinary and progressively type-\(\text{ II }\) right censored data. Test 19(1):68–91
Berkson J, Gage RP (1950) Calculation of survival rates for cancer. Proc Staff Meet Mayo Clin 25:270–286
Budhiraja S, Pradhan B, Sengupta D (2017) Maximum likelihood estimators under progressive type-\(\text{ I }\) interval censoring. Stat Prob Lett 123:202–209
Catchpole EA, Morgan BJT (1997) Detecting parameter redundancy. Biometrika 84(1):187–196
Chen DG, Lio YL (2010) Parameter estimations for generalized exponential distibution under progressive type-\(\text{ I }\) interval censoring. Comput Stat Data Anal 54(6):1581–1591
Chen DG, Lio YL, Jiang N (2013) Lower confidence limits on the generalized exponential distribution percentiles under progressive type-\(\text{ I }\) interval censoring. Commun Stat-Simul Comput 42(9):2106–2117
Cheng C, Chen J, Li Z (2010) A new algorithm for maximum likelihood estimation with progressive \(\text{ T }\)ype-\(\text{ I }\) interval censored data. Commun Stat-Simul Comput 39(4):750–766
Childs A, Balakrishnan N (2000) Conditional inference procedures for the \(\text{ L }\)aplace distribution when the observed samples are progressively censored. Metrika 52(3):253–265
Cohen AC (1963) Progressively censored samples in life testing. Technometrics 5:327–339
Ding C, Yang C, Tse SK (2010) Accelerated life test sampling plans for the \(\text{ W }\)eibull distribution under \(\text{ T }\)ype-\(\text{ I }\) progressive interval censoring with random removals. J Stat Comput Simul 80(8):903–914
Faulkenberry GD, Weeks DL (1968) Sample size determination for tolerance limits. Technometrics 10(2):343–348
Fernández AJ (2010) Tolerance limits for k-out-of-n systems with exponentially distributed component lifetimes. IEEE Trans Reliab 59(2):331–337
Goodmann LA, Madansky A (1962) Parameter-free and non-parametric tolerance limits: the exponential case. Technometrics 4(1):75–95
Kumbhar RR, Shirke DT (2004) Tolerance limits for lifetime distribution of k-unit parallel system. J Stat Comput Simul 74(3):201–213
Lawless JF (2011) Statistical models and methods for lifetime data. Wiley, New York
Lehmann EL, Casella G (1998) Theory of point estimation, 2nd edn. Springer, New York
Lin YJ, Lio YL (2012) Bayesian inference under progressive type-\(\text{ I }\) interval censoring. J Appl Stat 39(8):1811–1824
Ng HKT, Wang Z (2009) Statistical estimation for the parameters of \(\text{ W }\)eibull distribution based on progressively type-\(\text{ I }\) interval censored sample. J Stat Comput Simul 79(2):145–159
Patel JK (1986) Tolerance limits- a review. Commun Stat-Theory Methods 15(9):2719–2762
Pradhan B (2007) Point and interval estimation for the lifetime distribution of a k-unit parallel system based on progressively type-\(\text{ II }\) censored data. Econ Qual Control 22(2):175–186
Rao, C.R.: Maximum likelihood estimation for the multinomial distribution. Sankhy\({\bar{a}}\)18(1/2), 139–148 (1957)
Shin H, Lee K (2012) Estimation in the exponential distribution under progressive type-\(\text{ I }\) interval censoring with semi-missing data. J Korean Data Inf Sci Soc 23(6):1271–1277
Shirke DT, Kumbhar RR, Kundu D (2005) Tolerance interval for exponentiated scale family of distributions. J Appl Stat 32(10):1067–1074
Singh, S., Tripathi. Y.M.: Estimating the parameters of an inverse Weibull distribution under progressive Type-I interval censoring. Stat Pap. doi:10.1007/s00362-016-0750-2 (2016)
Tsai TR, Lin CW (2010) Acceptance sampling plans under progressive interval censoring with likelihood ratio. Stat Pap 51(2):259–271
Volterman W, Balakrishnan N (2010) Exact non parametric confidence, prediction and tolerance interval based on multiple sample type-\(\text{ II }\) right censored data. J Stat Plann Inference 140(11):3306–3316
Wilks SS (1942) Statistical prediction with special reference to the problem of tolerance limits. Ann Math Stat 13(4):400–409
Wu SJ, Chang CT, Liao KJ, Huang SR (2008) Planning of progressive group-censoring life tests with cost considerations. J Appl Stat 35(11):1293–1304
Wu SJ, Huang SR (2010) Optimal progressive group-censoring plans for exponential distribution in presence of cost constraint. Stat Pap 51(2):431–443
Wu SJ, Lin Y, Chen ST (2008) Optimal step-stress test under type-\(\text{ I }\) progressive group censoring with random removals. J Stat Plann Inference 138(4):817–826
Xiang L, Tse SK (2005) Maximum likelihood estimation in survival studies under progressive interval censoring with random removals. J Biopharm Stat 15(6):981–991
Acknowledgements
The authors would like to thank two anonymous reviewers for their helpful comments and suggestions They are grateful to Professor Debasis Sengupta, Applies Statistics Unit, Indian Statistical Institute, Kolkata for his valuable suggestions and comments.
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
Here we provide the proofs of the lemmas and results stated in the main article.
For the sake of convenience, we drop index i in the proof as items are independent and identical. Let \(\delta _{1,j}\) and \(\delta _{2,j}\) represent the indicator functions that an item fails in jth interval, and is censored at \(T_j\) respectively. Note that \(\sum _{l=j+1}^k (\delta _{1,l}+\delta _{1,l})=1\) indicates that an item is at risk at \(T_j\), thus \(P\left( \sum _{l=j+1}^k (\delta _{1,l}+\delta _{1,l})=1\right) =\prod _{l=0}^{j}(1-p_l)(1-q_l)\), where \(p_0=q_0=0\). In all the subsequent expressions we use \(F(T_j)\) instead of \(F(T_j;\varvec{\theta })\) for \(j=1,2,\ldots ,k\).
Proof of Lemma 1 (i)
By differentiating the contribution of an item in log-likelihood function (6) with respect to parameter \(\theta _u\) for \(u=1,2,\ldots ,m\), we have,
By using (2) and (3), we have \(\displaystyle \mathrm {E}[\delta _{1,j}]=\prod \nolimits _{l=0}^{j-1} (1-p_l)(1-q_l)q_j\) and \(\displaystyle \mathrm {E}[\delta _{2,j}]=\prod \nolimits _{l=0}^{j-1} (1-p_l)(1-q_l)(1-q_j)p_j\), where \(p_0=q_0=0\). Then we get, for \(u=1,2,\ldots ,m,\)
The last two expressions hold, since \(\prod _{l=0}^{j-1}(1-q_l)=1-F(T_{j-1})\) and \(p_k=1\). This implies . Hence Lemma 1 (i) holds. \(\square \)
Proof of Lemma 1 (ii)
On differentiating equation with respect to \(p_j\) for \(j=1,2,\ldots ,k-1\), we have
Now \(\displaystyle \mathrm {E}\left[ \sum _{l=j+1}^k (\delta _{1,l}+\delta _{1,l})\right] =P\left( \sum _{l=j+1}^k (\delta _{1,l}+\delta _{1,l})=1\right) =\prod _{l=0}^{j}(1-p_l)(1-q_l)\), for \(j=1,\ldots ,k-1\). So,
Hence . \(\square \)
Proof of Lemma 2 (i)
We have, for \(v=1,2,\ldots ,m\),
where \(T_0=0\). By using (2) and (3) and following arguments similar to the ones used for proving Lemma 1 (i), we have,
Thus for \(u,v=1,2,\ldots ,m\), we have
Next by using (15), we have
Since out of the 2k indicator variables, \(\delta _{1,1},\delta _{1,2},\ldots , \delta _{1,k}, \delta _{2,1}, \delta _{2,2},\ldots ,\delta _{2,k}\), exactly one can take value 1 and others are zero, we observe that when \(j\ne s\), \(\displaystyle P\left( \delta _{1,j}\delta _{1,s}=1\right) = P\left( \delta _{2,j}\delta _{2,s}=1\right) =0.\) Also \(P\left( \delta _{1,j}\delta _{2,s}=1\right) =0\) for all j and s. As a result, we have, for \(j\ne s\),
and when \(j=s\), we get
Thus by using (18) and (19), we get
Thus, using Eqs. (17) and (20), part (i) of Lemma 2 is proved.
Proof of Lemma 2 (ii)
On differentiating (15) with respect to \(p_s\) for \(s=1,2,\ldots ,k-1\), we have . Hence for \(u=1,2,\ldots ,m\) and \(s=1,2,\ldots ,k-1\), we get that
Next we consider the LHS of part (ii) of Lemma 2. For \(s=1,2,\ldots ,k-1\), we have
Hence by using (21) and (22), we prove that Lemma 2 (ii) holds.
Proof of Lemma 2 (ii)
From Eq. (16), it is obvious that
and , for \(j \ne s\).
Next we consider its LHS,
By using (16), we have
Note that by using (18) and (19), we have, \(\mathrm {E}\left[ \delta _{1,j} \delta _{2,s} \right] =0\) for all j and s, and \(\mathrm {E}\left[ \delta _{2,j} \delta _{2,s} \right] =\mathrm {E}\left[ \delta _{2,j}\right] \) for \(j=s\) and 0 otherwise. Also we have
We also note that an item at risk at \(T_j\), must be at risk at \(T_s\). Thus it is easy to deduce that
and
By using (23) and (24), for \(j>s\), we have
Similarly for \(j<s\),
Lastly, for \(j=s\)
Hence we have
Hence the proof of Lemma 2 is complete. \(\square \)
Proof of Result 1
Let \(\nabla _{\varvec{\theta }}F(T_j)=\left( \frac{\partial F(T_j)}{\partial \theta _1}, \frac{\partial F(T_j)}{\partial \theta _2}, \ldots , \frac{\partial F(T_j)}{\partial \theta _m}\right) ^T\) for \(j=1,2,\ldots ,k\). By using Lemma 2 and the assumption that items are independent and identically distributed, we have
where \(\mathrm {E}[N_j]=n \prod _{l=0}^{j-1}(1-p_l)(1-q_l)\) and \(p_0=q_0=0\).
Similarly for \(j,s=1,2,\ldots ,k-1\), we have
where , for \(j=1,2,\ldots ,k-1\).
Hence Result 1 is proved.
Next we prove the lemmas 3 to 5 necessary to establish the consistency and asymptotic properties of the MLE of \(\varvec{\theta }\).
Proof of Lemma 3
By (1), we have \(\mathrm {E}[N_j]=n\prod _{l=0}^{j-1}(1-p_l)(1-q_l)\). Thus, \( \mathrm {E}\left[ \frac{N_j}{n}\right] =\prod _{l=0}^{j-1}(1-p_l)(1-q_l) =b_j\), say. It is clear that \(b_j < \infty \). Now, it is enough to show that the variance of \(N_j/n\) tends to zero as \(n \rightarrow \infty \). We have
Thus, \( \text{ Var }\left( \frac{N_j}{n}\right) \rightarrow 0\), when \(n \rightarrow \infty \). Hence the proof.
Proof of Lemma 4 (i)
From Result 1, the \((u,v)^{th}\) element of is given by
For \(u=1,2,\ldots ,m\), we define
Then
Also, for fixed n, \(\mathrm {E} [N_j] <n\). Lastly, for all \( \varvec{\theta } \in \Theta \), by using regularity condition V(a), we have \(0<\frac{1}{q_j(1-q_j)}<\infty \) and number of inspections k is finite. Hence, .
Proof of Lemma 4 (ii)
Note that is the variance-covariance matrix of the score vector \(\varvec{\theta }\), it is a symmetric and non-negative definite. Consider a vector \({\mathbf {a}}(\varvec{\theta })\ne 0\). Then we have
Note that \(0<q_j<1\) and \(\mathrm {E} [N_j]>0\) for \(j=1,2,\ldots ,k\). Also, by the regularity condition V(b), \({\mathbf {a}}(\varvec{\theta })^T \nabla _{\varvec{\theta }}\left( F(T_j)-F(T_{j-1})\right) \ne 0\) and \({\mathbf {a}}(\varvec{\theta })^T\nabla _{\varvec{\theta }}F(T_j) \ne 0\). This implies for \({\mathbf {a}}(\varvec{\theta })\ne 0\). Hence is a positive definite matrix for all \(\varvec{\theta } \in \Theta _0\).
Proof of Lemma 5
For \(u,v,w=1,2,\ldots ,m\), we define
By using Eqs. (25)–(27), (28) and (29), it can be easily shown that
Now
where
Proof of Lemma 6 (i)
We show that for \(j,j'=1,2,\ldots ,k-1\). Note that for \(j\ne j'\) and when \(j'=j\). Hence each element of the Fisher Information matrix is finite for all \(\left( \varvec{\theta }, \varvec{p}\right) \in \Theta ^*\).
Proof of Lemma 6 (ii)
We prove that is a positive definite matrix. A diagonal matrix is positive definite if and only if all its element are positive. The jth component of is for \(j=1,2,\ldots ,k-1\). Hence is positive definite.
Proof of Lemma 7
Given that the regularity condition (VI) holds, we define
By using and equation (30), we have
Now
where
Hence the proof of the lemma is complete. \(\square \)
Rights and permissions
About this article
Cite this article
Budhiraja, S., Pradhan, B. Point and interval estimation under progressive type-I interval censoring with random removal. Stat Papers 61, 445–477 (2020). https://doi.org/10.1007/s00362-017-0948-y
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00362-017-0948-y