A method for estimating infant mortality rate for Nepal.Introduction Infant mortality rate infant mortality rate n. The ratio of the number of deaths in the first year of life to the number of live births occurring in the same population during the same period of time. (IMR IMR - Internet Monthly Report ) is an important indicator of social development of a nation. It is widely used for assessing socio-economic and health situation in developing countries (Chandra Sekhar 1972: 77; Jain and Visaria 1988). Measurement is a fundamental aspect of research in the area of infant mortality (hardware) infant mortality - It is common lore among hackers (and in the electronics industry at large) that the chances of sudden hardware failure drop off exponentially with a machine's time since first use (that is, until the relatively distant time at which enough mechanical . If vital registration is complete, IMR for each year can be calculated in the conventional manner directly from the system's data (Hill 1991:369). Unfortunately, complete vital registration system is practically non-existent in Nepal (Karki 1989). In the absence of complete vital registration system, indirect techniques proposed by Brass (1964), Trussell (1975), Feeney (1980), and Palloni and Heligman (1986) have been used for estimating IMR for Nepal using the census or survey data. The estimation of IMR by these techniques needs accurate birth history data to be collected from census or survey; reliable and adequate age patterns of child mortality for selecting an appropriate method and model life table; and lastly, many assumptions to be satisfied by the population under study. But the irony is that the birth and death data collected from the censuses or surveys of Nepal are highly inaccurate (Radhakrishna 1992:6-9; Pant 1996:18). Further, many assumptions underlying the models are unjustifiable in the population under study (Hill and Yazbek 1993:7). Moreover, there is no reliable age distribution of mortality for Nepal to use in deciding the right family that fits (CBS (Cell Broadcast Service) See cell broadcast. 1995:101). Apart from this, Nepal is a poor country where 42 percent of people still live below the poverty line, and almost hall of the total population are unable to read or write (UNDP UNDP United Nations Development Programme UNDP Unión Nacional para la Democracia y el Progreso (National Union for Democracy and Progress) 2002:2). Keeping in view the socio-economic and demographic realities of our own country, this paper presents a simple regression Noun 1. simple regression - the relation between selected values of x and observed values of y (from which the most probable value of y can be predicted for any value of x) regression toward the mean, statistical regression, regression model for estimating IMR from the minimum relevant parameter. Crude death rate (CDR (1) See CD-R and extension. (2) (Call Detail Reporting) See call accounting. (3) (Common Data Rate) A standard sampling rate for digital video for 480i and 576i systems. The rate is 13.5 MHz. See ITU-R BT. ) has been selected as the minimum relevant parameter needed for estimating IMR because it represents the 'end result' of development; can be easily obtained from either suitable models or various publications; and more importantly, it is strongly correlated with the level of IMR (Arriaga 1994). The model is applied to obtain the estimates of IMR for Nepal, and its validity is ascertained by comparing the estimated IMRs for Nepal with the other estimates available in the country; and by computing computing - computer relevant tests for diagnostic checking for model adequacy. Materials and Methods The proposed methodology of estimation is based on simple regression approach described elsewhere (Kumar 1981; Aryal and Gautam 2001; Singh 2003). The methodology of estimation developed here follows the usual path of establishing the relationships between the dependent variable, which in this case is the IMR and the independent variable, herein identified as CDR. Several empirical studies Empirical studies in social sciences are when the research ends are based on evidence and not just theory. This is done to comply with the scientific method that asserts the objective discovery of knowledge based on verifiable facts of evidence. show almost a linear relationship between IMR and CDR. Therefore, it was decided to fit a regression model of type: (1) Y = a + bX + e Where Y = IMR (per 1000 live births); X = CDR (per 1000 population); e is a random error term; and a and b are parameters to be estimated. The next step is to estimate the value of the parameters. For this purpose, the regression model is fitted in by using the following set of data extracted from the United Nations (1999). The table gives the following values of constants needed for estimating the parameters: [summation summation n. the final argument of an attorney at the close of a trial in which he/she attempts to convince the judge and/or jury of the virtues of the client's case. (See: closing argument) of]X = 195.90 [summation of][chi square chi square (kī), n a nonparametric statistic used with discrete data in the form of frequency count (nominal data) or percentages or proportions that can be reduced to frequencies. ] = 4163.81 [summation of]Y = 1849.00 [summation of]XY = 31598.20 [summation of][Y.sup.2] = 239821 n = 10 Using these data, simple regression approach gives the following estimated regression model for computing IMR for Nepal: (2) Y[GAMMA] = 3.01 + 7.4470 X n = 10, R2 = 99.8763%, S.E. (Y[GAMMA])= 1.7009 Where Y[GAMMA] = Estimated IMR (per 1000 live births); X = CDR (per 1000 population). Diagnostic Checking for Model Adequacy And Discussions A model that fails in diagnostic checking for model adequacy will always remain suspect and little faith can be put in the results (Kerlinger 1998). Therefore, it is essential that the model fitted for estimation purposes should satisfy the important tests of model adequacy. In this study, diagnostic checking for model adequacy is done by applying the model in Nepal's context; comparing the estimated IMRs for Nepal with the other estimates available for the country from different sources (Singh 1979; CBS 1987a, 1995; UNICEF UNICEF (y  `nĭsĕf'), the United Nations Children's Fund, an affiliated agency of the United Nations. 2001); and by
computing relevant tests for model adequacy described elsewhere. The
comparison of the estimated IMRs for Nepal with the other estimates
available for the country is presented by the figures in the following
table and figure:
Table 2 : Comparison of the Estimated IMRs for Nepal with other Estimates Estimates of other sources Present Study Years CDR IMR IMR * 1954 (i) 36.70 255.00 276.05 1961 (ii) 25.72 171.23 194.55 1976 (iii) 22.20 134.00 168.33 1981 (ii) 17.35 131.00 132.21 1991 (iv) 13.30 97.00 102.02 1999 (v) 10.00 75.00 77.48 Notes: (i) Refers to the estimates of Baidyanathan and Gaige (1973), PP. 278-290. (ii) Refers to the estimates of Singh, M.L. (1979, P. 172. (iii) Refers to the estimates of CBS (1987a), P. 99. (iv) Refers to the estimates of CBS (1995), P. 96. (v) Refers to the estimates of UNICEF (2001), P. 80 * Refers to the estimates of the present study. Source: CBS (1987a, 1995); Singh, M.L. (1979); UNICEF (2001). Notes: i Refers to the estimates of Baidyanathan anal Gaige (1973), PP. 278-290. ii Refers to the estimates of Singh, M.L. (1979, P. 172. iii Refers to the estimates of CBS (1987a), P. 99. iv Refers to the estimates of CBS (1995), P. 96. v Refers to the estimates of UNICEF (2001), P. 80 * Refers to the estimates of the present study. Source: CBS (1987a, 1995); Singh, M.L. (1979); UNICEF (2001). [FIGURE 1 OMITTED] This figure clearly shows declining trends of IMRs over the periods as is usually expected. More importantly, it shows close agreement between the estimated IMRs and the other estimates available for the country from different sources over a wide range of periods. However, it also shows a weak agreement between the estimated IMRs and other estimates especially, before 1981. This may be attributed to the limitations of data sources. In summary, the model seems to provide better estimates for more recent periods than the distant past. Diagnostic checking for model adequacy can also be done by computing major relevant tests described elsewhere. The following table presents the results of major relevant tests computed for diagnostic checking for model adequacy: The coefficient of determination Coefficient of determination A measure of the goodness of fit of the relationship between the dependent and independent variables in a regression analysis; for instance, the percentage of variation in the return of an asset explained by the market portfolio return. Also known as R-square. ([R.sup.2]) is computed for testing the goodness of fit Goodness of fit means how well a statistical model fits a set of observations. Measures of goodness of fit typically summarize the discrepancy between observed values and the values expected under the model in question. Such measures can be used in statistical hypothesis testing, e. . For the given set of data, the computed value of coefficient of determination [R.sup.2] (= 98.88%) is very high which indicates goodness of fit as 99.88% of the variation in IMR among the periods appears to be explained by the variation in the CDRs. Similarly, the smaller value of computed S.E. (Y[GAMMA]) [= 1.70] indicates the higher reliability of the model. The goodness of fit of a regression model is mostly affected by the estimated values of parameters. Similarly, the estimated parameters may be considered significant as they satisfied the 't' test. For instance, the parameter b[GAMMA] may be considered significant as the calculated value of |t| statistic statistic, n a value or number that describes a series of quantitative observations or measures; a value calculated from a sample. statistic a numerical value calculated from a number of observations in order to summarize them. for b[GAMMA] is 103.358 which is greater than the tabulated values [t.sup.*] (=1.306) and [t.sup.**] (= 1.860) for n - 2 (= 8) degrees of freedom.. This is also true for the other remaining parameters except for a[GAMMA] at 5 percent level of significance. Another way to test the significance of the regression model is to compute To perform mathematical operations or general computer processing. For an explanation of "The 3 C's," or how the computer processes data, see computer. the 'F' test. The calculated value of 'F ratio' (= 6060.69) is evidently greater than the tabulated values F* (= 5.32) and [F.sup.**] (= 11.30) for (1, 8) degrees of freedom and therefore, the regression model may be considered significant. The presence of autocorrelation Autocorrelation The correlation of a variable with itself over successive time intervals. Sometimes called serial correlation. is a serious problem and therefore, D-W test is computed for detection of autocorrelation. The results of D-W test clearly show absence of autocorrelation in the residuals because the first order autocorrelation coefficient [rho] (= 0.233) is very small, and the condition: [d.sub.u] < d < 4 - [d.sub.u] is well satisfied. For instance, [d.sub.u*] (= 1.32) < d (= 1.44) < 4 - [d.sub.u*] (= 2.68); and [d.sub.u**] (= 1.001) < d (= 1.44) < 4 - [d.sub.u**] (= 2.999) are satisfied. Conclusions The advantages of the indirect techniques in mortality estimation cannot be overemphasized in developing countries like Nepal. The proposed model is very simple and easy to apply; does not need census or survey data and model life tables for estimation of IMR; and gives approximately reliable estimates for Nepal. The results indicate that the model is effective in providing approximately reliable estimates of IMR for Nepal during the last few decades. The model seems to provide comparatively better estimates for more recent periods than for the distant past. However, the model seems to be affected by accuracy of data and age structure of the population under study. Conclusively con·clu·sive adj. Serving to put an end to doubt, question, or uncertainty; decisive. See Synonyms at decisive. con·clu  sive·ly adv. , the
model may be considered suitable for estimating IMR for Nepal for few
more decades.
Table 1 : Estimates of CDR and IMR for Nepal used
for Fitting the Equation (1)
Years X (= CDR) Y (= IMR)
1950-1955 27.9 210
1955-1960 26.7 200
1960-1965 25.0 189
1965-1970 22.8 175
1970-1975 21.1 160
1975-1980 18.4 142
1980-1985 16.2 125
1985-1990 14.1 109
1990-1995 12.8 96
1995-2000 10.9 83
Source: United Nations (1999), p. 305.
Table 3: Tests Computed for Diagnostic Checking
for Model Adequacy
Tests for Model Adequacy Results (@)
1. Tests for Goodness of fit:
i. Based on coefficient [R.sup.2](%) 99.6900
of determination: r -0.9984
n 8
2. S.E. of Estimates: S.E. (Y[??]) 3.0188
S.E. (a[??]) 4.4288
S.E. (b[??]) 0.0817
3. Tests of significance:
i. Based on 't' test: For a[??]: |t| 205.843
For b[??]: |t| 5808.738
For r: |t| 43.249
Tabulated t * 2.447
Tabulated t ** 1.943
ii. Based on ANOVA TSS 22801.968750
and 'F' Ratio: SSR 22731.509070
SSE 70.459680
Calculated 'F Ratio' 1935.70
Tabulated F * 5.99
Tabulated F ** 13.70
iii. Based on P.E. (r): P.E. (r) 0.0011
4. D-W test for Autocorrelation: d statistic 1.191
[rho] 0.392
[d.sub.u] * 1.332
[d.sub.L] * 0.763
[d.sub.u] ** 1.003
[d.sub.L] ** 0.497
Notes:
* Refers to 5% level of significance.
** Refers to 1% level of significance.
(@) Refers to the results of tests computed for the proposed
model (2).
Acknowledgement The author wishes to thank Dr. Mrigendra La! Singh, the Professor of Statistics at Central Department of Statistics, Tribhuvan University Tribhuvan University is the largest and the oldest university of Nepal. It is situated in Kirtipur. The university was established in 1959 as the first university of the country. , Kirtipur, Kathmandu, Nepal for his valuable suggestions while planning the study. Any remaining errors are entirely the responsibility of the author. References Arriaga, E.E. and Associates. 1994. Population Analysis with Microcomputers, Volume 1: Presentation of Techniques. Washington D.C.: United States United States, officially United States of America, republic (2005 est. pop. 295,734,000), 3,539,227 sq mi (9,166,598 sq km), North America. The United States is the world's third largest country in population and the fourth largest country in area. Bureau of the Census Noun 1. Bureau of the Census - the bureau of the Commerce Department responsible for taking the census; provides demographic information and analyses about the population of the United States Census Bureau . Aryal, J.P. and Gautam, A. 2001. Quantitative Techniques, New Hira Book Enterprises. Baidyanathan, K.E, and Gaige, F.H. 1973. "Estimates of Abridged Life Tables, Corrected Sex-Age Distribution and Birth and Death Rates for Nepal, 1954," Demography demography (dĭmŏg`rəfē), science of human population. Demography represents a fundamental approach to the understanding of human society. India, 2(2):278-290. Brass, W. 1964. "Uses of Census and Survey Data for Estimation of Vital Rates Vital rates refer to how fast vital statistics change in a population (usually measure per 1000 individuals). There are 2 categories within vital rates: crude rates and refined rates. ," Paper Presented at the African Seminar on Vital Statistics, Addis Ababa Addis Ababa (ăd`ĭs ăb`əbə) [Amharic,=new flower], city (1994 pop. 2,112,737), capital of Ethiopia. It is situated at c.8,000 ft (2,440 m) on a well-watered plateau surrounded by hills and mountains. . CBS. 1987a. Population Monograph of Nepal. Kathmandu: Central Bureau of Statistics. CBS. 1995. Population Monograph of Nepal. Kathmandu: Central Bureau of Statistics. Chandra Sekhar, S. (1972). Infant Mortality, Population Growth and Family Planning family planning Use of measures designed to regulate the number and spacing of children within a family, largely to curb population growth and ensure each family’s access to limited resources. in India. London: George Allene and Unwine Ltd. G.C., Radhakrishna. 1992/93. "Population Data Quality," Tathyank Gatibidhi (Four Monthly Statistical Bulletin), Kathmandu: Central Bureau of Statistics, Kathmandu, 13 (2):6-9. Hill, K. 1991. "Approaches to the Measurement of Childhood Mortality: A Comparative Review," Population Index, 57(3):368-382. Hill, K. and Yazbeck, A. (1993). Trends in Child Mortality, 1960-1990: Estimates for 83 Developing Countries. New York New York, state, United States New York, Middle Atlantic state of the United States. It is bordered by Vermont, Massachusetts, Connecticut, and the Atlantic Ocean (E), New Jersey and Pennsylvania (S), Lakes Erie and Ontario and the Canadian province of : United Nations Children's Fund United Nations Children's Fund (UNICEF), an affiliated agency of the United Nations. It was established in 1946 as the United Nations International Children's Emergency Fund. . Jain, A.K. and Visaria, P. (eds.). 1988. Infant Mortality in India: Differentials and Determinants. New Delhi New Delhi (dĕl`ē), city (1991 pop. 294,149), capital of India and of Delhi state, N central India, on the right bank of the Yamuna River. : Sage Publications This article or section needs sources or references that appear in reliable, third-party publications. Alone, primary sources and sources affiliated with the subject of this article are not sufficient for an accurate encyclopedia article. . Karki, Y.B. 1989. "Vital Registration System in Nepal." A paper presented at National Seminar on Social Statistics, Central Bureau of Statistics, 20-23 June, Kathmandu. Kerlinger, F.N. 1998. Foundations of Behavioural Adj. 1. behavioural - of or relating to behavior; "behavioral sciences" behavioral Research. Delhi: Surjeet Publications. Kumar, R. 1981. "Use of Regression Models in Determining Accurate Vital Statistics in Developing Countries: A Methodology," Demography India, 10:216-233. Palloni, A., and Heligman, L. 1986. "Re-estimation of Structural Parameters to Obtain Estimates of Mortality in Developing Countries." Population Bulletin of the United Nations, 18:10-33. Pant, P.D. 1996. "The Quality of the Reported Age of Mother, Date of Birth and Death of Children in the 1976 NFS (Network File System) The file sharing protocol in a Unix network. This de facto Unix standard, which is widely known as a "distributed file system," was developed by Sun. See file sharing protocol and WebNFS. NFS - Network File System and the 1986 NFFS NFFS Nonfederal Financial Support (Public Broadcasting) NFFS Nonferrous Founder's Society Data," Nepal Population Journal, 5(4): 1-8. Singh, M.L. 1979. "Population Dynamics Population dynamics is the study of marginal and long-term changes in the numbers, individual weights and age composition of individuals in one or several populations, and biological and environmental processes influencing those changes. of Nepal: An Analytic Study." Unpublished Ph.D. Thesis, Tribhuvan University, Kathmandu. Singh, M.L. 2003. Understanding Research Methodology (Third Edition). Kathmandu. Trussell, T.J. 1975. "A Re-estimation of the Multiply Factors for the Brass Technique for Determining Childhood Survivorship Rates survivorship rate proportion of the population that are still alive at successive annual ages. ," Population Studies, 29(1):97-108. UNDP. 2002. "Poverty Reduction and Governance," Human Development Report 2001. Kathmandu. UNICEF. 2001. The State of World's Children. New York: Oxford University Press. |
|
||||||||||||||||||
Printer friendly
Cite/link
Email
Feedback
Reader Opinion