Research Article Volume 7 Issue 6
Department of Statistics, Pondicherry University, India
Correspondence: Jambulingam Subramani, Department of Statistics, Pondicherry University, RV Nagar, Kalapet, Puducherry?605 014, India
Received: October 22, 2018 | Published: December 14, 2018
Citation: Subramani J. Two parameter modified ratio estimators with two auxiliary variables for the estimation of finite population mean. Biom Biostat Int J. 2018;7(6):559-568. DOI: 10.15406/bbij.2018.07.00259
The present paper deals with some two parameter modified ratio estimators for the estimation of finite population means with known skewness and correlation coefficient on two auxiliary variables. It has been shown that the proposed modified ratio estimators perform better than the simple random sampling without replacement (SRSWOR) sample mean and some of the existing ratio estimators for certain natural populations available in the literature.
Keywords: mean squared error, natural populations, percentage relative efficiency, simple random sampling, ams subject classification: 62DJO5
Let ( X ) be the study (auxiliary) variable taking values Yi ( Xi ) respectively on the unit Ui , i=1, 2, …, N wherein U={U1,U2, …,UN} be the finite population of size N . The information on auxiliary variables are effectively used to improve the efficiency of the simple random sampling without replacement (SRSWOR) estimator of the population mean. As the results, ratio, product and regression estimators are widely utilized in many situations, see for example Cochran1 and Murthy.2 Modified ratio estimators are developed to achieve further improvements on the ratio estimator with known parameters of the auxiliary variable, which include Sisodia & Dwivedi3 with known Co-efficient of Variation, Singh et.,4 with known Kurtosis, Yan & Tian5 with the known Skewness, Subramani and Kumarapandiyan6-9 with the known median and its linear combinations with the other known parameters. This paper deals with the two parameter modified ratio estimators with known correlation coefficient and skewness of two auxiliary variables ˉY .
Several modified estimators have been proposed by linking together ratio, product and regression estimators in order to obtain more efficient estimators with two auxiliary variables. For a more detailed discussion about the estimators with two auxiliary variables one may refer to Abu-Dayyeh et al.,10 Bandyopadhyay,11 Cochran,1 Kadilar & Cingi,12,13 Khare et al.,14 Murthy,2 Naik & Gupta,15 Olkin I,16 Perri,17,18 Rao and Mudholkar,19 Raj,20 Sahoo & Swain,21 Singh,4 Singh,22,23 Singh & Tailor,24 Srivenkataramana,25 Srivenkataramana & Tracy,26 Tailor et al.,27 Tracy et al.,28 and the references cited there in.
The notations described below are used in this paper:
N− Population size
n−Sample size
f=n/N, Sampling fraction
Y− Study variable
X1and X2 − Auxiliary variables
ˉX1,ˉX2, ˉY− Population means
ˉx1,ˉx2, ˉy− Sample means
β1(Xi)− Coefficient of Skewness of auxiliary variable Xi, i=1,2
R1=ˉYˉX1and R2=ˉYˉX¯2
Sx1 ,Sx2 , Sy−Population standard deviations
Sx1y −Population covariance between X1 and Y
Sx2y −Population covariance between X2 and Y
Sx1x2− Population covariance between X1 and X2
Cx,Cx1,Cx2,Cy− Coefficient of variations
ρxy− Coefficient of correlation between X and Y
ρyx1− Coefficient of correlation between Y and X1
ρyx2− Coefficient of correlation between Y and X2
ρx1x2− Coefficient of correlation between X1 and X1
B1=SxyS2x1, Regression coefficient of Y on X1
B2=SxyS2x2, Regression coefficient of Y on X2
MSE(.)− Mean squared error of the estimator
˜ˉYi− ith Existing modified ratio estimator of ˉY
In SRSWOR, the estimator of ˉY is ˉyr and its variance is
V(ˉyr)=(1−f)nS2y, where S2y=1(N−1)∑Ni=1(Yi−ˉY)2 (1)
Cochran [3] introduced the classical ratio estimator for estimating the population mean ˉY of the study variable Y using auxiliary variable X as given below:
ˆˉYR ¯y ˉxˉXˆR ˉX where ˆR ¯y ˉx y x (2)
The mean squared error of ˆˉYR to the first order of approximation is given below:MSE(ˆˉYR)(1−f)nˉY2(C2y+C2x−2xyCxCy) (3)
Singh [24] has suggested a ratio estimator with two auxiliary variables for estimating the population mean and is given below:ˆˉY1ˉy(ˉX1ˉx1)(ˉX2ˉx2) (4)
The mean squared error of ˆˉY1 to the first order of approximation is given below:MSE(ˆˉY1)(1−f)nˉY2(C2y+C2x1+C2x2−2yx1Cx1Cy−2yx2Cx2Cy+2x1x2Cx1Cx2) (5)
Using known correlation coefficient between auxiliary variables, Singh and Tailor19 have suggested the following modified ratio cum product estimator:ˆˉY2ˉy(ˉX1+x1x2ˉx1+x1x2)(ˉx2+x1x2ˉX2+x1x2) (6)
The mean squared error of ˆˉY2 to the first order of approximation is given below:MSE(ˆˉY2)1−fn ˉY2[C2y+*1C2x1(−2Kyx1)+*2C2x2(+2(Kyx2−*1Kx1x2))] (7)
where Kyx1yx1CyCx1, Kyx2yx2CyCx2,Kx1x2
x1x2Cx1Cx2,*1ˉX1ˉX1+x1x2 and *2ˉX2ˉX2+x1x2
Kadilar & Cingi6 have proposed a new ratio estimator using two auxiliary variables and isgiven below:ˆˉY3ˉy (ˉX1ˉx1)(ˉX2ˉx2)+b1(ˉX1−ˉx1)+b2(ˉX2−ˉx2) (8)
The mean squared error of ˆˉY3 to the first order of approximation is given below:MSE(ˆˉY3) ≅ 1−fnS2y+(R1+B1)2S2x1+(R2+B2)2S2x2−2(R1+B1)Syx1−2(R2+B2)Syx2+2(R1+B1)(R2+B2)Sx1x2 (9)
Perri13 has suggested some modified ratio cum product estimators using two auxiliary variables for estimating the population mean and are given below:ˆˉY4ˉy 21 ˉX1ˉX2, ˆˉY5ˉy ˉX11 ˉX22 and ˆˉY6ˉy 12 ˉX2ˉX1 (10)
where 1ˉx1+1(ˉX1−ˉx1) and 2ˉx2+2(ˉX2−ˉx2)The mean squared errors of ˆˉY4, ˆˉY5 and ˆˉY6 to the first order of approximation are given below:
MSE(ˆˉY4)1−fn[S2y+2x1+2x2−2(−yx2+x1x2)] (11)
MSE(ˆˉY5)1−fn[S2y+2x1+2x2−2(+yx2−x1x2)] (12)
MSE(ˆˉY6)1−fn[S2y+2x1+2x2+2(−yx2−x1x2)] (13)where x1x2R1R2Sx1x2(1−1)(1−2),x1R1Sx1(1−1), x2R2Sx2(1−2)
R1Syx1(1−1) and yx2R2Syx2(1−2)This paper is organized as follows: Section 2 introduces two parameter modified ratio estimators using the information of correlation coefficient and skewness of two auxiliary variables and the expressions for their bias and mean square error up to the first order of approximation have been derived. Section 3 is devoted to the analysis of the efficiencies of the proposed modified ratio estimators. In Section 4, an empirical analysis is carried out with some natural populations. Section 5 is ended with some concluding remarks.
In this Section, two parameter modified ratio estimators with known correlation coefficient and skewness and their linear combinations of two auxiliary variables have been proposed and are given below:
ˆˉYJS1ˉy(ˉX1+2ˉX2+x1x2ˉx1+2ˉx2+x1x2) (14)
ˆˉYJS2ˉy((ˉX1+1(X1))+2(ˉX2+1(X2))(ˉx1+1(X1))+2(ˉx2+1(X2))) (15)
ˆˉYJS3ˉy((1(X1)ˉX1+x1x2)+2(1(X2)ˉX2+x1x2)(1(X1)ˉx1+x1x2)+2(1(X2)ˉx2+x1x2)) (16)
ˆˉYJS4ˉy((x1x2ˉX1+1(X1))+2(x1x2ˉX2+1(X2))(x1x2ˉx1+1(X1))+2(x1x2ˉx2+1(X2))) (17)
In general the estimators proposed in (14) to (17) can be defined as given below:ˆˉYJSjˉy((ˉX1+T1)+2(ˉX2+T2)(ˉx1+T1)+2(ˉx2+T2)), j=1, 2, 3, 4
The mean squared errors of the proposed estimators are derived as given below:Let e0ˉy−ˉYˉY, e1ˉx1−ˉX1ˉX1 and e2ˉx2−ˉX2ˉX2. Further we can write ˉyˉY(1+e0)
ˉx1ˉX1(1+e1) and ˉx2ˉX2(1+e2) and from the definition of e0 and e1 we obtain:
E[e0]E[e1]=0
E[e20](1−f)nC2y, E[e21]1−fnC2x1and E[e22]1−fnC2x2
E(e0e11−fnyx1CyCx1, E(e0e21−fnyx2CyCx2 and E(e1e21−fnx1x2Cx1Cx2
The proposed estimators ˆˉYJSj can be written in terms of e0, e1 and e2 as given below:ˆˉYJSjˉY(1+e0)((ˉX1+T1)+2(ˉX2+T2)(ˉX1(1+e1)+T1)+2(ˉX2(1+e2)+T2))
⇒ˆˉYJSjˉY(1+e0)(ˉX1+2ˉX2+1T1+2T2ˉX1+2ˉX2+1T1+2T2+1ˉX1e1+2ˉX2e2)
⇒ˆˉYJSjˉY(1+e0)(11+'1e1+'2e2)), '1ˉX1(ˉX1+T1)+2(ˉX2+T2) and
ˉX2(ˉX1+T1)+2(ˉX2+T2)
⇒ˆˉYJSjˉY(1+e0)(1+'1e1+'2e2)−1
⇒ˆˉYJSjˉY(1+e0)(1−'1e1−'2e2+(e1+'2e2)2)
⇒ˆˉYJSjˉY(1+e0)(1−'1e1−'2e2+'1e21+'2e22+2'1e1e2)
Neglecting the terms of higher order, we haveˆˉYJSj−ˉYˉYe0−ˉY'1e1−ˉY'2e2+ˉY'1e1e2−ˉY'1e0e1−ˉY'2e0e2
Squaring and taking expectations on both sides, we haveMSE(ˆˉYJSjE(ˆˉYJSj−ˉY)2ˉY2E(e0−'1e1−'2e2)2
⇒MSE(ˆˉYJSj)= ˉY2E(e20+'1e21+'2e22−2'1e0e1−2'2e0e22+'1e1e2)
⇒MSE(ˆˉYJSj)ˉY2{E(e20)+'1E(e21)+'2E(e22)−2'1E(e0e1)−2'1E(e0e2+2'1E(e1e2)}
MSE(ˆˉYJSj)1−fnˉY2{C2y+'1C2x1+'2C2x2−2'1CyCx1−2'2CyCx2+2'1x1x2Cx1Cx2} (18)
In this Section the conditions for which the proposed estimators will have minimum mean squared error compared to SRSWOR sample mean and other existing estimators discussed in Section 2 for estimating the finite population mean have been derived algebraically.
From the expressions given in (18) and (1) the conditions for which the proposed estimator, is more efficient than the SRSWOR sample mean have been derived and are given below:
MSE(ˆˉYJSj)≤V(ˉyr) if '1C2x1+'2C2x2≤2(yx1CyCx1+'2CyCx2−'1x1x2Cx1Cx2) (19)
From the expressions given in (18) and (5) the conditions for which the proposed estimator ˆˉYJSj, j=1, 2, 3, 4 is more efficient than the existing ratio estimator ˆˉY1 have been derived and are given below:MSE(ˆˉYJSj)≤MSE(ˆˉY1) if (2−1)C2x1+('1−1)C2x2≤2{('1−1)yx1CyCx1+(−1)yx2CyCx2−('1−1)x1x2Cx1Cx2} (20)
From the expressions given in (18) and (7) the conditions for which the proposed estimator ˆˉYJSj, j=1, 2, 3, 4 is more efficient than the existing ratio estimator ˆˉY2 have been derived and are given below:MSE(ˆˉYJSj)≤MSE(ˆˉY2) if (2−*1)C2x1+('2−*2)C2x2≤2{('1−*1)yx1CyCx1+(+*2)yx2CyCx2−('1+*1)x1x2Cx1Cx2} (21)
From the expressions given in (18) and (9) the conditions for which the proposed estimator ˆˉYJSj, j=1, 2, 3, 4 is more efficient than the existing ratio estimator have been derived and are given below:MSE(ˆˉYJSj)≤MSE(ˆˉY3) if 21(R'js−R21)S2x1+22(R'js−R22)S2x2+B1Syx1+B2Syx2≤2{R'js(Syx1+2Syx2)−[2R'js−(1R1+B1)(2R2+B2)]Sx1x2} (22)
From the expressions given in (18) and (11) the conditions for which the proposed estimator ˆˉYJSj, j=1, 2, 3, 4 is more efficient than the existing ratio estimator ˆˉY4 have been derived and are given below:MSE(ˆˉYJSj)≤MSE(ˆˉY4) if [R'js−(1−1)2R21]S2x1+[R'js−(1−2)2R22]S2x2≤2{Syx1[R'js−(1−1)R1]+Syx2[R'js+(1−2)R2]−Sx1x2[2R'js+R1R2(1−1)(1−2)]} (23)
From the expressions given in (18) and (12) the conditions for which the proposed estimator ˆˉYJSj, j=1, 2, 3, 4 is more efficient than the existing ratio estimator have been derived and are given below:MSE(ˆˉYJSj)≤MSE(ˆˉY5) if [R'js−(1−1)2R21]S2x1+[R'js−(1−2)2R22]S2x2≤2{Syx1[R'js−(1−1)R1]+Syx2[R'js−(1−2)R2]−Sx1x2[2R'js−R1R2(1−1)(1−2)]} (24)
From the expressions given in (18) and (13) the conditions for which the proposed estimator ˆˉYJSj, j=1, 2, 3, 4 is more efficient than the existing ratio estimator have been derived and are given below:MSE(ˆˉYJSj)≤MSE(ˆˉY6) if [R'js−(1−1)2R21]S2x1+[R'js−(1−2)2R22]S2x2≤2{Syx1[R'js+(1−1)R1]+Syx2[R'js−(1−2)R2]−Sx1x2[2R'js+R1R2(1−1)(1−2)]} (25)
where R'jsˉY(ˉX1+T1)+2(ˉX2+T2)
The performance of the proposed modified ratio estimators are assessed with that of the SRSWOR sample mean and the existing modified ratio estimators for certain natural populations. In this connection, we have considered two natural populations for the assessment of the performance of the proposed estimators with that of the existing estimators. The population 1 is taken from Singh & Chaudhary29 given in page 177 and population 2 is taken from taken from the Cingi & Kadilar30 given in page 117. The description of the study variable and auxiliary variable for the two populations are given below: (Table 1-4).
Popl. No. |
Study variable-Y |
Auxiliary variable- X1 |
Auxiliary variable- X2 |
1 |
Area under wheat in 1974 |
Area under wheat in1971 |
Area under wheat in1973 |
2 |
The population mean of the height of the fish |
The population mean of the length of the head |
The population mean of the length of the fin |
Table 1 Description of the study variable and auxiliary variable
Parameters |
Population 1 |
Population 2 |
N |
34 |
25 |
n |
20 |
10 |
ˉY |
856.41 |
75.28 |
ˉX1 |
208.88 |
14.3 |
ˉX2 |
199.44 |
6.82 |
ρyx1 |
0.45 |
0.99 |
ρyx2 |
0.45 |
0.89 |
ρx1x2 |
0.98 |
0.92 |
β11 |
0.87 |
1.24 |
β12 |
1.28 |
0.86 |
β21 |
2.91 |
4.26 |
β22 |
3.73 |
4.35 |
Sy |
733.14 |
17.27 |
Cy |
0.86 |
0.23 |
Sx1 |
150.51 |
3.17 |
Sx2 |
150.22 |
1.53 |
Cx1 |
0.72 |
0.22 |
Cx2 |
0.75 |
0.22 |
Table 2 Parameters and constants of the populations
Existing estimators |
Proposed estimators |
||||||||||
˜ˉYr |
37940.84 |
||||||||||
˜ˉY1 |
90847.02 |
||||||||||
˜ˉY2 |
40145.19 |
||||||||||
α1 |
α2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
˜ˉYJSI |
˜ˉYJS2 |
˜ˉYJS3 |
˜ˉYJS4 |
||
0 |
1 |
67310.24 |
64818.97 |
64818.97 |
64818.97 |
37438.58 |
37396.53 |
37468.86 |
37392.86 |
||
0.1 |
0.9 |
62385.73 |
60005.70 |
60005.90 |
60005.94 |
37182.02 |
37146.64 |
37206.57 |
37143.17 |
||
0.2 |
0.8 |
58048.59 |
56317.41 |
56317.77 |
56317.84 |
36952.76 |
36923.68 |
36971.88 |
36920.4 |
||
0.3 |
0.7 |
54298.80 |
53754.11 |
53754.56 |
53754.66 |
36750.06 |
36726.96 |
36764.05 |
36723.87 |
||
0.4 |
0.6 |
51136.38 |
52315.78 |
52316.28 |
52316.42 |
36573.22 |
36555.82 |
36582.32 |
36552.89 |
||
0.5 |
0.5 |
48561.32 |
52002.43 |
52002.92 |
52003.10 |
36421.56 |
36409.60 |
36425.98 |
36406.83 |
||
0.6 |
0.4 |
46573.62 |
52814.07 |
52814.49 |
52814.70 |
36294.41 |
36287.67 |
36294.34 |
36285.06 |
||
0.7 |
0.3 |
45173.28 |
54750.68 |
54750.99 |
54751.23 |
36191.12 |
36189.41 |
36186.71 |
36186.94 |
||
0.8 |
0.2 |
44360.30 |
57812.27 |
57812.42 |
57812.69 |
36111.05 |
36114.23 |
36102.43 |
36111.89 |
||
0.9 |
0.1 |
44134.68 |
61998.84 |
61998.77 |
61999.08 |
36053.59 |
36061.52 |
36040.88 |
36059.31 |
||
1 |
0 |
44496.43 |
67310.39 |
67310.05 |
67310.39 |
36018.14 |
36030.73 |
36001.41 |
36028.64 |
Table 3 Variance/Mean squared error of the existing and proposed estimators for the Population 1
Existing estimators |
Proposed estimators |
||||||||||
˜ˉYr |
17.9 |
||||||||||
˜ˉY1 |
17.58 |
||||||||||
˜ˉY2 |
17.58 |
||||||||||
α1 |
α2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
˜ˉYJSI |
˜ˉYJS2 |
˜ˉYJS3 |
˜ˉYJS4 |
||
35.07 |
34.61 |
34.61 |
34.61 |
3.83 |
3.83 |
3.85 |
3.83 |
||||
0.1 |
0.9 |
32.15 |
31.58 |
31.62 |
31.64 |
2.89 |
2.89 |
2.92 |
2.91 |
||
0.2 |
0.8 |
29.57 |
29.24 |
29.31 |
29.34 |
2.23 |
2.23 |
2.25 |
2.26 |
||
0.3 |
0.7 |
27.33 |
27.58 |
27.67 |
27.71 |
1.75 |
1.77 |
1.76 |
1.79 |
||
0.4 |
0.6 |
25.42 |
26.6 |
26.71 |
26.75 |
1.4 |
1.43 |
1.41 |
1.46 |
||
0.5 |
0.5 |
23.85 |
26.31 |
26.41 |
26.47 |
1.14 |
1.18 |
1.14 |
1.21 |
||
0.6 |
0.4 |
22.62 |
26.71 |
26.79 |
26.86 |
0.96 |
1 |
0.94 |
1.03 |
||
0.7 |
0.3 |
21.72 |
27.78 |
27.83 |
27.92 |
0.82 |
0.87 |
0.8 |
0.9 |
||
0.8 |
0.2 |
21.16 |
29.55 |
29.55 |
29.65 |
0.72 |
0.77 |
0.69 |
0.8 |
||
0.9 |
0.1 |
20.94 |
31.99 |
31.94 |
32.05 |
0.64 |
0.7 |
0.62 |
0.73 |
||
1 |
0 |
21.05 |
35.12 |
35 |
35.12 |
0.59 |
0.65 |
0.57 |
0.68 |
Table 4 Variance/Mean squared error of the existing and proposed estimators for the Population 2
The population parameters and constants computed for the above two populations are given below:
From the values of Table 5-12, it is observed that the proposed modified ratio estimators perform better than SRSWOR sample mean and the existing modified ratio estimators.30–35
α1 |
α2 |
SRSWOR |
Existing estimators |
|||||
ˉyr |
˜ˉY1 |
˜ˉY2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
||
0 |
1 |
101.34 |
242.66 |
107.23 |
179.79 |
173.13 |
173.13 |
173.13 |
0.1 |
0.9 |
102.04 |
244.33 |
107.97 |
167.78 |
161.38 |
161.38 |
161.38 |
0.2 |
0.8 |
102.67 |
245.85 |
108.64 |
157.09 |
152.4 |
152.4 |
152.4 |
0.3 |
0.7 |
103.24 |
247.2 |
109.24 |
147.75 |
146.27 |
146.27 |
146.27 |
0.4 |
0.6 |
103.74 |
248.4 |
109.77 |
139.82 |
143.04 |
143.05 |
143.05 |
0.5 |
0.5 |
104.17 |
249.43 |
110.22 |
133.33 |
142.78 |
142.78 |
142.78 |
0.6 |
0.4 |
104.54 |
250.31 |
110.61 |
128.32 |
145.52 |
145.52 |
145.52 |
0.7 |
0.3 |
104.83 |
251.02 |
110.93 |
124.82 |
151.28 |
151.28 |
151.28 |
0.8 |
0.2 |
105.07 |
251.58 |
111.17 |
122.84 |
160.1 |
160.1 |
160.1 |
0.9 |
0.1 |
105.23 |
251.98 |
111.35 |
122.41 |
171.96 |
171.96 |
171.96 |
1 |
0 |
105.34 |
252.23 |
111.46 |
123.54 |
186.88 |
186.88 |
186.88 |
Table 5 PRE of the proposed estimator ˜ˉYJS1 for the Population 1
α1 |
α2 |
SRSWOR |
Existing estimators |
|||||
ˉyr |
˜ˉY1 |
˜ˉY2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
||
0 |
1 |
101.46 |
242.93 |
107.35 |
179.99 |
173.33 |
173.33 |
173.33 |
0.1 |
0.9 |
102.14 |
244.56 |
108.07 |
167.94 |
161.54 |
161.54 |
161.54 |
0.2 |
0.8 |
102.75 |
246.04 |
108.72 |
157.21 |
152.52 |
152.52 |
152.52 |
0.3 |
0.7 |
103.31 |
247.36 |
109.31 |
147.84 |
146.36 |
146.36 |
146.36 |
0.4 |
0.6 |
103.79 |
248.52 |
109.82 |
139.89 |
143.11 |
143.11 |
143.11 |
0.5 |
0.5 |
104.21 |
249.51 |
110.26 |
133.38 |
142.83 |
142.83 |
142.83 |
0.6 |
0.4 |
104.56 |
250.35 |
110.63 |
128.35 |
145.54 |
145.54 |
145.54 |
0.7 |
0.3 |
104.84 |
251.03 |
110.93 |
124.82 |
151.29 |
151.29 |
151.29 |
0.8 |
0.2 |
105.06 |
251.55 |
111.16 |
122.83 |
160.08 |
160.08 |
160.08 |
0.9 |
0.1 |
105.21 |
251.92 |
111.32 |
122.39 |
171.93 |
171.93 |
171.93 |
1 |
0 |
105.3 |
252.14 |
111.42 |
123.5 |
186.81 |
186.81 |
186.81 |
Table 6 PRE of the proposed estimator˜ˉYJS2 for the Population 1
α1 |
α2 |
SRSWOR |
Existing estimators |
|||||
ˉyr |
˜ˉY1 |
˜ˉY2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
||
0 |
1 |
101.26 |
242.46 |
107.14 |
179.64 |
172.99 |
172.99 |
172.99 |
0.1 |
0.9 |
101.97 |
244.17 |
107.9 |
167.67 |
161.28 |
161.28 |
161.28 |
0.2 |
0.8 |
102.62 |
245.72 |
108.58 |
157.01 |
152.32 |
152.33 |
152.33 |
0.3 |
0.7 |
103.2 |
247.11 |
109.2 |
147.7 |
146.21 |
146.22 |
146.22 |
0.4 |
0.6 |
103.71 |
248.34 |
109.74 |
139.78 |
143.01 |
143.01 |
143.01 |
0.5 |
0.5 |
104.16 |
249.4 |
110.21 |
133.32 |
142.76 |
142.76 |
142.76 |
0.6 |
0.4 |
104.54 |
250.31 |
110.61 |
128.32 |
145.52 |
145.52 |
145.52 |
0.7 |
0.3 |
104.85 |
251.05 |
110.94 |
124.83 |
151.3 |
151.3 |
151.3 |
0.8 |
0.2 |
105.09 |
251.64 |
111.2 |
122.87 |
160.13 |
160.13 |
160.14 |
0.9 |
0.1 |
105.27 |
252.07 |
111.39 |
122.46 |
172.02 |
172.02 |
172.02 |
1 |
0 |
105.39 |
252.34 |
111.51 |
123.6 |
186.97 |
186.97 |
186.97 |
Table 7 PRE of the proposed estimator˜ˉYJS1 for the Population 1
α1 |
α2 |
SRSWOR |
Existing estimators |
|||||
ˉyr |
˜ˉY1 |
˜ˉY2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
||
0 |
1 |
101.47 |
242.95 |
107.36 |
180.01 |
173.35 |
173.35 |
173.35 |
0.1 |
0.9 |
102.15 |
244.59 |
108.08 |
167.96 |
161.55 |
161.55 |
161.55 |
0.2 |
0.8 |
102.76 |
246.06 |
108.73 |
157.23 |
152.54 |
152.54 |
152.54 |
0.3 |
0.7 |
103.31 |
247.38 |
109.32 |
147.86 |
146.37 |
146.37 |
146.38 |
0.4 |
0.6 |
103.8 |
248.54 |
109.83 |
139.9 |
143.12 |
143.12 |
143.13 |
0.5 |
0.5 |
104.21 |
249.53 |
110.27 |
133.39 |
142.84 |
142.84 |
142.84 |
0.6 |
0.4 |
104.56 |
250.37 |
110.64 |
128.35 |
145.55 |
145.55 |
145.55 |
0.7 |
0.3 |
104.85 |
251.05 |
110.94 |
124.83 |
151.3 |
151.3 |
151.3 |
0.8 |
0.2 |
105.06 |
251.57 |
111.17 |
122.84 |
160.09 |
160.09 |
160.09 |
0.9 |
0.1 |
105.22 |
251.94 |
111.33 |
122.39 |
171.94 |
171.94 |
171.94 |
1 |
0 |
105.31 |
252.15 |
111.43 |
123.5 |
186.82 |
186.82 |
186.82 |
Table 8 PRE of the proposed estimator˜ˉYJS4 for the Population 1
α1 |
α2 |
SRSWOR |
Existing estimators |
|||||
ˉyr |
˜ˉY1 |
˜ˉY2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
||
0 |
1 |
467.36 |
459.01 |
459.01 |
915.67 |
903.66 |
903.66 |
903.66 |
0.1 |
0.9 |
619.38 |
608.3 |
608.3 |
1112.46 |
1092.73 |
1094.12 |
1094.81 |
0.2 |
0.8 |
802.69 |
788.34 |
788.34 |
1326.01 |
1311.21 |
1314.35 |
1315.7 |
0.3 |
0.7 |
1022.86 |
1004.57 |
1004.57 |
1561.71 |
1576 |
1581.14 |
1583.43 |
0.4 |
0.6 |
1278.57 |
1255.71 |
1255.71 |
1815.71 |
1900 |
1907.86 |
1910.71 |
0.5 |
0.5 |
1570.18 |
1542.11 |
1542.11 |
2092.11 |
2307.89 |
2316.67 |
2321.93 |
0.6 |
0.4 |
1864.58 |
1831.25 |
1831.25 |
2356.25 |
2782.29 |
2790.63 |
2797.92 |
0.7 |
0.3 |
2182.93 |
2143.9 |
2143.9 |
2648.78 |
3387.8 |
3393.9 |
3404.88 |
0.8 |
0.2 |
2486.11 |
2441.67 |
2441.67 |
2938.89 |
4104.17 |
4104.17 |
4118.06 |
0.9 |
0.1 |
2796.88 |
2746.88 |
2746.88 |
3271.88 |
4998.44 |
4990.63 |
5007.81 |
1 |
0 |
3033.9 |
2979.66 |
2979.66 |
3567.8 |
5952.54 |
5932.2 |
5952.54 |
Table 9 PRE of the proposed estimator˜ˉYJS1 for the Population 2
α1 |
α2 |
SRSWOR |
Existing estimators |
|||||
ˉyr |
˜ˉY1 |
˜ˉY2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
||
0 |
1 |
467.36 |
459.01 |
459.01 |
915.67 |
903.66 |
903.66 |
903.66 |
0.1 |
0.9 |
619.38 |
608.3 |
608.3 |
1112.46 |
1092.73 |
1094.12 |
1094.81 |
0.2 |
0.8 |
802.69 |
788.34 |
788.34 |
1326.01 |
1311.21 |
1314.35 |
1315.7 |
0.3 |
0.7 |
1011.3 |
993.22 |
993.22 |
1544.07 |
1558.19 |
1563.28 |
1565.54 |
0.4 |
0.6 |
1251.75 |
1229.37 |
1229.37 |
1777.62 |
1860.14 |
1867.83 |
1870.63 |
0.5 |
0.5 |
1516.95 |
1489.83 |
1489.83 |
2021.19 |
2229.66 |
2238.14 |
2243.22 |
0.6 |
0.4 |
1790 |
1758 |
1758 |
2262 |
2671 |
2679 |
2686 |
0.7 |
0.3 |
2057.47 |
2020.69 |
2020.69 |
2496.55 |
3193.1 |
3198.85 |
3209.2 |
0.8 |
0.2 |
2324.68 |
2283.12 |
2283.12 |
2748.05 |
3837.66 |
3837.66 |
3850.65 |
0.9 |
0.1 |
467.36 |
459.01 |
459.01 |
915.67 |
903.66 |
903.66 |
903.66 |
1 |
0 |
619.38 |
608.3 |
608.3 |
1112.46 |
1092.73 |
1094.12 |
1094.81 |
Table 10 PRE of the proposed estimator˜ˉYJS2 for the Population 2
α1 |
α2 |
SRSWOR |
Existing estimators |
|||||
ˉyr |
˜ˉY1 |
˜ˉY2 |
˜ˉY3 |
˜ˉY4 |
˜ˉY5 |
˜ˉY6 |
||
0 |
1 |
464.94 |
456.62 |
456.62 |
910.91 |
898.96 |
898.96 |
898.96 |
0.1 |
0.9 |
613.01 |
602.05 |
602.05 |
1101.03 |
1081.51 |
1082.88 |
1083.56 |
0.2 |
0.8 |
795.56 |
781.33 |
781.33 |
1314.22 |
1299.56 |
1302.67 |
1304 |
0.3 |
0.7 |
1017.05 |
998.86 |
998.86 |
1552.84 |
1567.05 |
1572.16 |
1574.43 |
0.4 |
0.6 |
1269.5 |
1246.81 |
1246.81 |
1802.84 |
1886.52 |
1894.33 |
1897.16 |
0.5 |
0.5 |
1570.18 |
1542.11 |
1542.11 |
2092.11 |
2307.89 |
2316.67 |
2321.93 |
0.6 |
0.4 |
1904.26 |
1870.21 |
1870.21 |
2406.38 |
2841.49 |
2850 |
2857.45 |
0.7 |
0.3 |
2237.5 |
2197.5 |
2197.5 |
2715 |
3472.5 |
3478.75 |
3490 |
0.8 |
0.2 |
2594.2 |
2547.83 |
2547.83 |
3066.67 |
4282.61 |
4282.61 |
4297.1 |
0.9 |
0.1 |
464.94 |
456.62 |
456.62 |
910.91 |
898.96 |
898.96 |
898.96 |
1 |
0 |
613.01 |
602.05 |
602.05 |
1101.03 |
1081.51 |
1082.88 |
1083.56 |
Table 11 PRE of the proposed estimator˜ˉYJS3 for the Population 2
|
|
SRSWOR |
Existing estimators |
|||||
|
|
|
|
|
|
|
||
0 |
1 |
467.36 |
459.01 |
459.01 |
915.67 |
903.66 |
903.66 |
903.66 |
0.1 |
0.9 |
615.12 |
604.12 |
604.12 |
1104.81 |
1085.22 |
1086.6 |
1087.29 |
0.2 |
0.8 |
792.04 |
777.88 |
777.88 |
1308.41 |
1293.81 |
1296.9 |
1298.23 |
0.3 |
0.7 |
1000 |
982.12 |
982.12 |
1526.82 |
1540.78 |
1545.81 |
1548.04 |
0.4 |
0.6 |
1226.03 |
1204.11 |
1204.11 |
1741.1 |
1821.92 |
1829.45 |
1832.19 |
0.5 |
0.5 |
1479.34 |
1452.89 |
1452.89 |
1971.07 |
2174.38 |
2182.64 |
2187.6 |
0.6 |
0.4 |
1737.86 |
1706.8 |
1706.8 |
2196.12 |
2593.2 |
2600.97 |
2607.77 |
0.7 |
0.3 |
1988.89 |
1953.33 |
1953.33 |
2413.33 |
3086.67 |
3092.22 |
3102.22 |
0.8 |
0.2 |
2237.5 |
2197.5 |
2197.5 |
2645 |
3693.75 |
3693.75 |
3706.25 |
0.9 |
0.1 |
467.36 |
459.01 |
459.01 |
915.67 |
903.66 |
903.66 |
903.66 |
1 |
0 |
615.12 |
604.12 |
604.12 |
1104.81 |
1085.22 |
1086.6 |
1087.29 |
Table 12 PRE of the proposed estimator˜ˉYJS4 for the Population 2
In this paper, two parameter modified ratio estimators using the linear combination of the correlation coefficient and skewness of auxiliary variables has been suggested. The mean squared error of the proposed estimators are derived and compared with that of the SRSWOR sample mean, the classical ratio estimator and the existing modified ratio estimators. Further we have derived the conditions for which the proposed estimators are more efficient than the existing estimators. We have also assessed the performance of the proposed estimators with that of the existing estimators for certain natural populations. It is observed that the mean squared error of the proposed estimators is less than the mean squared error of the existing estimators for two populations. Further it has been shown that the efficiency of the proposed estimators with respect to existing estimators are in general ranging from 101.26 to 5007.81. Hence we strongly recommend that the proposed modified ratio estimators may be preferred over the existing estimators for practical applications.
None.
Author declares that there is no conflict of interest.
©2018 Subramani. This is an open access article distributed under the terms of the, which permits unrestricted use, distribution, and build upon your work non-commercially.
2 7