Abstract
New two-stage sampling methodologies are developed for both one-sided and two-sided comparisons between the means from treatment groups and a control. We suppose that we have k i ( ≥ 1) independent treatments with associated response variables \(X_{i1},...,X_{ik_{i}},\) i = 1,...,r( ≥ 2). We let X ijl denote the lth observation recorded independently and assume that their common distribution is \(N(\mu _{ij},\sigma _{i}^{2}),l=1,...,n_{i}(\geq 2),j=1,...,k_{i},i=1,...,r.\) Also, let X 0l denote the lth observation recorded independently from a control and we assume that their common distribution is \(N(\mu _{0},\sigma _{0}^{2}),l=1,...,n_{0}(\geq 2).\) The parameters μ ij ’s, σ i ’s, μ 0, and σ 0 are assumed finite, unknown, and σ i ’s unequal, j = 1,...,k i , i = 1,...,r. Denote the treatment-control difference Δ ij = μ ij − μ 0 and our goal is to make simultaneous one-sided and two-sided fixed-precision confidence statements regarding all Δ ij ’s, j = 1,...,k i , i = 1,...,r. Specifically, given two preassigned numbers d( > 0) and 0 < α < 1, we develop two sets of appropriate two-stage stopping variables N 0,N 1,...,N r via procedures \(\mathcal{P}_{\text{I}}^{ \mathbf{N}}\) and \(\mathcal{P}_{\text{II}}^{\mathbf{N}}\) respectively such that the simultaneous probability that \((\overline{X}_{ijN_{i}}-\overline{X} _{0n_{0}})-\Delta _{ij}\leq d\) under \(\mathcal{P}_{\text{I}}^{\mathbf{N}}\) and that \(\left| (\overline{X}_{ijN_{i}}-\overline{X}_{0N_{0}})-\Delta _{ij}\right| \leq d\) under \(\mathcal{P}_{\text{II}}^{\mathbf{N}}\) would both exceed or equal 1 − α for all j = 1,...,k i , i = 1,...,r. We note that the two-stage methodology for our one-sided problem covers more diverse applications than Dudewicz et al.’s (Biom Z 17:13–26, 1975) methodology did since we no longer assume k 1 = ... = k r = 1. With regard to our two-sided problem, no previous two-stage methodology was available in the literature. In this work, mathematical determinations of appropriate design constants with regard to either goal, the proposed methodologies, and the construction of the requisite tables are all new. This paper emphasizes practical implementations of the proposed methodologies.
Similar content being viewed by others
References
Aoshima M (2005) Statistical inference in two-stage sampling. Selected papers on differential equations and analysis. Am Math Soc Transl 215:125–145
Aoshima M, Mukhopadhyay N (1998) Fixed-width simultaneous confidence intervals for multinormal means in several intraclass correlation models. J Multivar Anal 66:46–63
Aoshima M, Kushida T (2005) Asymptotic second-order efficiency for two-stage multiple comparisons with components of a linear function of mean vectors. In: Balakrishnan N, Kannan N, Nagaraja N (eds) Advances in ranking and selection, multiple comparisons, and reliability: methodology and applications. Birkhauser, Boston, pp 191–211
Aoshima M, Takada Y (2000) Second-order properties of a two-stage procedure for comparing several treatments with a control. J Jpn Stat Soc 30:27–41
Aoshima M, Yata K (2010) Asymptotic second-order consistency for two-stage estimation methodologies and its applications. Ann Inst Stat Math 62:571–600
Bechhofer RE, Dunnett CW, Sobel M (1954) A two-sample multiple decision procedure for ranking means of normal populations with a common unknown variance. Biometrika 41:170–176
Bechhofer RE, Kiefer J, Sobel M (1968) Sequential identification and ranking procedures: with special reference to Koopman–Darmois populations. University of Chicago Press, Chicago
Bechhofer RE, Santner TJ, Goldsman DM (1995) Design and analysis of experiments for statistical selection, screening, and multiple comparisons. Wiley, New York
Chen HJ, Dudewicz EJ, Lee YJ (1976) Subset selection procedures for normal means under unequal sample sizes. Sankhya, Ser B 38:249–255
Dantzig GB (1940) On the non-existence of Student’s hypothesis having power functions independent of σ. Ann Math Stat 11:186–192
Dudewicz EJ (1971) Non-existence of a single-sample selection procedure whose P(CS) is independent of the variance. S Afr Stat J 5:37–39
Dudewicz EJ (1980) Ranking (ordering) and selection: an overview of how to select the best. Technometrics 22:113–119
Dudewicz EJ, Dalal SR (1975) Allocation of observations in ranking and selection with unequal variances. Sankhya, Ser B 37:28–78
Dudewicz EJ, Ramberg JS, Chen HJ (1975) New tables for multiple comparisons with a control (unknown variances). Biom Z 17:13–26
Dunn OJ (1958) Estimation of the means of dependent variables. Ann Math Stat 29:1095–1111
Dunnett CW, Sobel M (1955) Approximations to the probability integral and certain percentage points of a multivariate analogue of Student’s t-distribution. Biometrika 42:258–260
Ghosh M, Mukhopadhyay N, Sen PK (1997) Sequential estimation. Wiley, New York
Gibbons JD, Olkin I, Sobel M (1977) Selecting and ordering populations: a new statistical methodology. Wiley, New York. Reprinted 1999, SIAM, Philadelphia
Gupta SS, Panchapakesan S (1979) Multiple decision procedures: theory and methodology of selecting and ranking populations. Wiley, New York. Reprinted 2002, SIAM, Philadelphia
Mukhopadhyay N (1979) Some comments on two-stage selection procedures. Commun Stat, Theory Methods 8:671–683
Mukhopadhyay N (1993) Nonlinear renewal theory and beyond: reviewing the roles in selection and ranking. In: Hoppe FM (ed) Multiple comparisons, selection, and applications in biometry. Marcel Dekker, New York, pp 293–313
Mukhopadhyay N (1995) Two-stage and multi-stage estimation. In: Balakrishnan N, Basu AP (eds) Exponential distribution: theory, methods and application, chapter 26. Gordon and Breach, Amsterdam, pp 429–452
Mukhopadhyay N (1999a) Second-order properties of a two-stage fixed-size confidence region for the mean vector of a multivariate normal distribution. J Multivar Anal 68:250–263
Mukhopadhyay N (1999b) Higher than second-order approximations via two-stage sampling. Sankhya, Ser A 61:254–269
Mukhopadhyay N (2005) A new approach to determine the pilot sample size in two-stage sampling. In: Chen P, Hsu L, Panchapakesan S (eds) Special Milton Sobel memorial issue. Commun Stat, Theory Methods 34:1275–1295
Mukhopadhyay N (2006) A personal tribute to Milton Sobel: selecting the best treatment. Seq Anal (Milton Sobel memorial issue-part I) 25:119–143
Mukhopadhyay N, Aoshima M (1998) Multivariate multistage methodologies for simultaneous all pairwise comparisons. Metrika 47:185–201
Mukhopadhyay N, Datta S, Chattopadhyay S (2004) Applied sequential methodologies, edited volume. Marcel Dekker, New York
Mukhopadhyay N, de Silva BM (2009) Sequential methods and their applications. CRC Press, Boca Raton
Mukhopadhyay N, Duggan WT (1997) Can a two-stage procedure enjoy second-order properties? Sankhya, Ser A 59:435–448
Mukhopadhyay N, Solanky TKS (1994) Multistage selection and ranking procedures: second-order asymptotics. Marcel Dekker, New York
Mukhopadhyay N, Solanky TKS (1998) Multistage methodology for fixed-width simultaneous confidence intervals for all pairwise comparisons. J Stat Plan Inference 73:163–176
Mukhopadhyay N, Solanky TKS (2002) Multistage methodologies for comparing several treatments with a control. J Stat Plan Inference 100:209–220
Rinott Y (1978) On two-stage selection procedures and related probability-inequalities. Commun Stat, Theory Methods 7:799–811
Slepian D (1962) The one-sided barrier problem for Gaussian noise. Bell Syst Tech J 41:463–501
Stein C (1945) A two sample test for a linear hypothesis whose power is independent of the variance. Ann Math Stat 16:243–258
Stein C (1949) Some problems in sequential estimation (abstract). Econometrica 17:77–78
Tong YL (1980) Probability inequalities in multivariate distributions. Academic, New York
Tong YL (1990) The multivariate normal distribution. Springer, New York
Wilcox RR (1985) On comparing effects to a standard when the variances are unknown and unequal. J Educ Stat 10:45–54
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mukhopadhyay, N., Solanky, T.K.S. On Two-Stage Comparisons with a Control Under Heteroscedastic Normal Distributions. Methodol Comput Appl Probab 14, 501–522 (2012). https://doi.org/10.1007/s11009-011-9241-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-011-9241-z
Keywords
- Dunn’s inequality
- Fixed-size confidence intervals
- One-sided confidence intervals
- Real data illustration
- Simulations
- Simultaneous confidence intervals
- Slepian’s inequality
- Statistical tables
- Treatments vs. control
- Two-sided confidence intervals
- Two-stage sampling