Bogor, West Java, Indonesia

Size: px
Start display at page:

Download "Bogor, West Java, Indonesia"

Transcription

1 2018 IJSRSET Volume 4 Issue 4 Print ISSN: Online ISSN : Themed Section : Engineering and Technology Assessment Method for Weighting and Aggregation in Constructing Composite Indicators of Mixed Data Arni Nurwida *, Aji Hamim Wigena, Budi Susetyo Department of Statistics, Faculty of Mathematics and Sciences Natural, Bogor Agricultural University (IPB), ABSTRACT Bogor, West Java, Indonesia Composite indicators is often encountered in various studies especially in social sector. Composite indicators constructed from several steps such as weighting and aggregation. The classical weighting method such as weighting based on factor analysis and regression analysis cannot handle a mixture of numeric and categorical variables. Furthermore, using dependent variable as the estimator in weighting based on regression analysis sometimes untrustworthy or manipulable by respondents. One approach to addressing this problem is by using a weighting method based on factor analysis of mixed data. Besides that, the classical aggreagtion method such as linear additive method cannot handle a mixture of compensatory and non-compensatory variables. One approach to addressing this problem is by using a geometric aggreagtion method. The accuracy of weighting method based on factor analysis of mixed data and geometric aggreagtion in constructing composite indicators of mixed data is important to be studied. The case study conducted in constructing household welfare status of Dramaga village, Bogor regency by comparing weighting method based on factor analysis of mixed data, weighting based on multiple correspondence analysis, geometric aggreagtion, and linear aggreagtion method. The weighting method based on factor analysis of mixed data and the geometric aggreagtion provided the most accurate results. Keywords: Composite Indicators, Factor Analysis of Mixed Data, Geometric Aggreagtion, Household Welfare I. INTRODUCTION categorical variables (mixed data). The classical weighting procedure such as based on principal Composite indicators is a technique to compile individual indicators into a single index on the basis of underlying model. The goal is to measure components or factor analysis, regression analysis, and multiple correspondence analysis developed to handle only numeric or categorical variables. multidimensional concepts which cannot be captured by a single indicator, e.g. competitiveness, Weighting based on regression analysis using industrialization, sustainability, single market dependent variable as the estimator of the integration, knowledge-based society, etc (OECD, phenomenon sometimes untrustworthy or 2008). Composite indicators constructed from several steps such as weighting and aggregation. Weighting is a procedure to weight individual indicators, they manipulable by respondents. Sari (2011) found household income used as dependent variable in estimating poverty in West Nusa Tenggara and describe different importance in expressing Maluku Province is manipulated. This is happened multidimensional phenomenon (Mazziota & Pareto, 2013). The main problem in weighting is the because the respondent manipulated during the survey, they knowed that the puspose of the survey is individual indicators came from numeric and to determine beneficiaries of government programs. IJSRSET Received : 03 April 2018 Accepted : 15 April 2018 March-April-2018 [(4) 4 : ] 1070

2 Also, Castano (2002) found weighting based on qualitative principal components that is not using dependent variable is more accurate than weighting based on least square regression that is using dependent variable. Therefore, weighting method based on factor analysis of mixed data can handle together both numeric and categorical variable and without dependent variable (Pages, 2004). Aggregation is a procedure to combine all variable components to form one composite indices (Mazziota & Pareto, 2013). The main problem in aggregation is the individual indicators came from compensatory and non-compensatory variables. The classical aggregation procedure such as linear additive methods developed to handle only compensatory variable (Tarabusi & Guarini, 2013). Therefore, geometric methods can handle together both compensatory and non-compensatory variables (OECD, 2008). This method is the combined method of compensatory and non-compensatory that called non-linear aggregation method. Statistics Indonesia (BPS) in TNP2K (2013) constructed Indonesian household welfare status by numeric and categorical variable using method based on regression analysis and household expenditure per capita as dependent variable. Therefore, this study want to examine weighting and aggreagtion methods in constructing individual indicators of mixed data in case of household welfare status in Dramaga village, Bogor regency, Indonesia by the social protection program data collection (PPLS) II. METHODS AND MATERIAL This study used social protection program data collection (PPLS) 2011 especially on Dramaga village, Bogor regency, Indonesia. Dramaga village has 775 households and 3155 household members. The variables that used are household welfare status criterions which consist of 15 numeric variables and 19 categorical variables as presented in Table 1. Table 1. research Variable Description Type Variable Description Type Age of household head Numeric Educational level of household head Categoric 1/Dependency ratio Numeric Working status of household head Categoric Net elementary and middle school Main occupational sector of Numeric enrolment ratio household head Categoric 1/Gross elementary and middle school enrolment ratio Numeric of residence mastery Categoric 1/Household size Numeric Wall material Categoric At least one of the household members graduated from middle school Numeric Roof material Categoric At least one of the household members graduated from high school Numeric Source of drinking water Categoric At least one of the household members graduated from college Numeric Way of getting drinking water Categoric 1/Number of school-aged child in elementary school Numeric Source of main lighting Categoric 1/Number of school-aged child in middle school Numeric Toilet facility Categoric 1/Number of school-aged child in high school Numeric Final stool disposal site Categoric Number of school-aged child in college Numeric Refrigerator ownership Categoric Proportion of household members working in the primary sector Numeric Motorcycle ownership Categoric Proportion of household members Main job position of household Numeric working in the secondary sector head Categoric Proportion of household members working in the tertiary sector Numeric Floor material Categoric Sex of household head Categoric Sector and main job position of h.h. Categoric Marital status of household head Categoric Working status of household head and residence mastery status Categoric 1071

3 Table 2. Research model Model Weighting Method based on Aggregation Method 1 Factor analysis of mixed data Linear 2 Factor analysis of mixed data Geometric 3 Multiple correspondence analysis Linear 4 Multiple correspondence analysis Geometric The steps in this study are as follows: 1. Data description 2. Constructing 4 models of Dramaga village household welfare status as presented in Table 2 3. Weighting individual indicators using the method based on factor analysis of mixed data: a. Weighting numeric variables using a technique described in OECD (2008). The first step is choosing a number of factor (F) that have cumulative variance larger than 60% and eigenvalue larger than 1. The next step refers to Nicoletti, Scarpetta, & Boylaud (2000) choosing the largest loading factor from the selected factors (F) for every numeric variable q. Then calculating the weight of numeric variable q as below: ( ) ( ) where is the weight of numeric variable q, largest loading factor,, is a factorial axis containing the factor of numeric variable q, is the largest loading ( ) is a variance of loading factor, and ( ) is total variance of loading factor, last step is converting and. to the value. The b. Weighting modalities of categorical variables using a technique of axis ordering consistency condition (AOC) by Asselin (2009). The first step is choosing a number of factor (F) that have eigenvalue larger than 1 as below: where is the eigenvalue of factor f,, is the discriminant value of categorical variable j and factor f,, is the number of households of modality,, is the loading factor f modality and categorical variable j, is total number of households. The next step is choosing the largest discriminant value from the selected factors (F) for every categorical variable j. Then calculating the weight of modalities below: of categorical variable j as where is the weight of modalities of categorical variable j, β is a factorial axis containing the largest discriminant value, is the loading factor β modalities and categorical variable j, is is the loading factor β the worst modalities and categorical variable j, and is the eigenvalue of factor β. 4. Weighting individual indicators using the method based on multiple correspondence analysis as belows: a. Converting numeric variables into categorical using the quantile methods with the number of modalities is 4 b. Calculating the weight of modalities of categorical variables using the same procedure on number 3.b 5. For weighting based on factor analysis of mixed data, constructing composite indicators for every household i using the linear aggreagtion method by summing the linear method for numeric 1072

4 variables (OECD, 2008) and for categorical variables (Asselin, 2009) as below: 6. For weighting based on factor analysis of mixed data, constructing composite indicators for every household i using the geometric aggreagtion method by summing the geometric method for numeric variables (OECD, 2008) and for categorical variables as below: 7. For weighting based on multiple correspondence analysis, constructing composite indicators for every household i using the linear and geometric aggreagtion for categorical variables only. 8. Constructing Dramaga village household welfare status as belows: a. Sorting the composite indicators from the smallest to largest b. Dividing the sorted composite indicators into 4 classes or status from status 1 to 4 using cuts off refers to BPS 9. Validating Dramaga village household welfare status compared with BPS using several test as belows: a. Mann-Whitney test b. Robust analysis ( ) c. Accuracy test d. Area Under the ROC Curve (AUC) 10. Choosing the best model which accepting in Mann-Whitney test, smallest, largest accuracy, and largest AUC 11. Explorating of Dramaga village household welfare status characteristics III. RESULTS AND DISCUSSION Dramaga village, Bogor regency in PPLS 2011 consists of 775 households and 3155 household members. The criterion variables of household welfare status in PPLS 2011 consist of numeric and categorical variables, and also complementary and noncomplementary variables. The complementary variables are at least one of the household members graduated from college with the proportion of household members working in primary sector, while the non-complementary variables are the age of the household head with the number of school-aged children in primary school. The PPLS 2011 contains households with the household welfare status of 1, 2, 3 and 4 with the number and percentage of households in every status presented in Table 3. The highest number of households is in status 3 (408 and 52.65%), followed by status 2 (224 and 28.90%), status 1 (108 and 13.94%), and status 4 (35 and 4.52%). Table 3. Number and percentage of the households Description Number of households households Weighting The weighting process in constructing household welfare status of Dramaga village conducted using two methods. The first method used weighting based on multiple correspondence analysis and the second method used weighting based on factor analysis of mixed data. Weighting based on Multiple Correspondence Analysis The weighting based on multiple correspondence analysis can only handle categorical variables, so that the numeric variables must be categorized first. Categorization of numeric variables using the quantile techniques with the number of modalities are 4 (Table 4). Weighting procedure conducted to all modalities of categorical variables. Table 4 presented that the value of J*50%*eigenvalue at least 1 is in the 1073

5 first 12 factors (1.01), so that the number of factor to be used is 12. Weighting variables used the loading factor and eigenvalue from the factor that gived the largest discriminant value. Table 5 present that the largest discriminant value of variable to are at factor 1, 8, 12, 8, 3, 1, 1, 5, 1, 4, 11, 10, 4, 6, 6, 8, 9, 9, 12, 5, 1, 8, 4, 1, 2, 2, 7, 1, 1, 12, 8, 3, 3, and 4, respectively, so that those are the factor of loading and eigenvalue to be used for weighting variables. The weight constructed from the gap between the loading factor and the loading factor from the worst-off modalities, then divided by the eigenvalue square root. The categorical weight based on multiple correspondence analysis presented in Table 6. Table 4. The value of J*50%*eigenvalue of the categorical variables on weighting based on multiple correspondence analysis Factors Description J*50%*Eigenvalue Table 5. Discriminant of the categorical variables on weighting based on multiple correspondence analysis Factors

6 Table 6. Weight of the variables on weighting based on multiple correspondence analysis Modalities Weight Modalities Weight Modalities Weight Tap water Bottled water No buying Buying No electricity PLN with No toilet Public Self-owned Others Holes River/lake/sea Female 0.00 Septic tank Male 1.67 No No married 0.00 Yes Married 1.25 No Elementary school 0.00 Yes Middle school 0.80 No working High school 0.21 Others College 6.48 Laborer/employee No working 0.00 Self-employed Working 0.12 Soil No working 0.00 No soil Tertiary 8.15 No working Secondary 9.02 Tertiary and others Primary 7.07 Tertiary and laborer/ emp Others 0.00 Tertiary and self-employed Free rental 3.55 Secondary and others Contract/lease 4.70 Secondary and laborer/emp Self-owned 3.04 Secondary and self- employed Others 0.00 Primary and others Wood 4.01 Primary and laborer/emp Wall 0.49 Primary and self-employed Others 0.00 No working and free rental Asbestos 1.12 No working and contract/lease Tiles 1.67 No working and self-owned Others 0.00 Working and others Unprotected wells 1.47 Working and free rental Protected wells 2.20 Working and contract/lease Drilling wells 1.74 Working and self-owned Weighting based on Factor Analysis of Mixed Data The weighting based on factor analysis of mixed data can handle a mixture of numeric and categorical variables. The first step is weighting the numeric variables. Table 7 presented that the percentage of cumulative variance at least 60% and the eigenvalue at least 1 is in the first 17 factors (60.91% and 1.23), so that the number of factor to be used is 17. Weighting numeric variables used the loading factor and the variance proportion from the factor that gived the largest loading factor value. Table 8 presented the largest loading factor of variable to are at factor 1 (Y = 0.42), 12 (Y = 0.23), 11 (Y = 0.14), 7 (Y = 0.16), 1 (Y = 0.31), 2 (Y = 0.34), 2 (Y = 0.25), 14 (Y = 0.19), 1 (Y = 0.21), 1 (Y = 0.08), 11 (Y = 1075

7 0.18), 11 (Y = 0.04), 2 (Y = 0.32), 1 (Y = 0.18), dan 3 (Y = 0.36), respectively. Then the largest loading factor weighted by the variance proportion and converted to a value with total 1 and range [0,1]. This conversion is the numeric weights that presented in Table 9. The next step is weighting the categorical variables. The categorical weighting procedure is the same as with categorical weighting based on multiple correspondence analysis. Table 10 presented that the value of J*50%*eigenvalue at least 1 is in the first 11 factors (1.23), so that the number of factor to be used is 11. Table 11 presented that the largest discriminant value of variable to are at factor 1, 1, 5, 5, 1, 1, 5, 2, 7, 4, 4, 4, 3, 3, 1, dan 1, respectively, so that those are the factor of loading and eigenvalue to be used for weighting variables. The categorical weight based on factor analysis of mixed data presented in Table 12. Table 7. Eigenvalue and cumulative variance of the numeric variables Description Factors Eigenvalue Cumulative Variance (%) Eigenvalue Cumulative Variance (%) Numeric Table 8. Loading factor of the numeric variables Factors Table 9. Weight of the numeric variables Numeric Weight Numeric Weight Numeric Weight

8 Table 10. The value of J*50%*eigenvalue of the categorical variables on weighting based on factor analysis of mixed data Factors Description J*50%*Eigenvalue Table 11. Discriminant of the categorical variables on weighting based on factor analysis of mixed data Factors Table 12. Weight of the variables on weighting based on factor analysis of mixed data Modalities Weight Modalities Weight Modalities Weight Female 0.00 Tiles No working 0.00 Male 9.46 Others 0.00 Others No married 0.00 Unprotected wells 1.61 Laborer/employee Married 9.16 Protected wells 3.09 Self-employed Elementary sc Drilling wells 0.91 Soil 0.00 Middle sch Tap water 1.84 No soil 6.07 High sch Bottled water 3.39 No working 0.00 College 3.96 No buying 0.00 Tertiary and others No working 0.00 Buying 5.15 Tertiary and laborer/emp Working No electricity 0.00 Tertiary and self-employed No working Secondary and others Tertiary PLN with e.m Secondary and laborer/emp Secondary No toilet 0.00 Secondary and self- emp Primary Public 1.87 Primary and others Others 0.00 Self-owned 2.79 Primary and laborer/emp Free rental Others 0.00 Primary and self-employed Contract/lease Holes 6.38 No working and free rental 0.00 Self-owned River/lake/sea 4.20 No working and contract/ls Others 0.00 Septic tank 6.53 No working and self-owned 4.02 Wood 5.86 No 0.00 Working and others Wall 4.67 Yes 2.60 Working and free rental Others 0.00 No 0.00 Working and contract/lease Asbestos Yes 3.67 Working and self-owned

9 Dramaga Village Household Welfare The household welfare status of Dramaga village obtained by ranking the household welfare index from the smallest to the largest and then dividing into 4 status from status 1 to status 4 with the cuts off refer to Dramaga village household welfare status in PPLS The number of households in every status presented in Table 16. Table 16. Number of the households in every status PPLS 2011 Weighting based on Multiple Correspondence Analysis Weighting based on Factor Analysis of Mixed Data Linear Aggregation Geometric Aggregation Linear Aggregation Geometric Aggregation Validation Test The validation test in constructing household welfare status of Dramaga village c7onducted using 4 tests (Table 17). The first test is Mann-Whitney test, the second test Weighting Method Weighting based on Multiple Correspondence Analysis Weighting based on Factor Analysis of Mixed Data Table 17. Mann-Whitney test to PPLS 2011 is the average of the absolute differences in households rank ( ), the third test is the classification accuracy test, and the last test is the value of the area under the ROC curve (AUC). Aggregation Method P-Value of Mann-Whitney Test Accuracy (%) AUC (%) Linear Geometric Linear Geometric The Mann-Whitney test conducted to prove that the computed Dramaga village household welfare status is the same as in PPLS 2011 statistically. Accepting means there are similarities between them. The p- value of Mann-Whitney test grether than α (=0.05) found in weighting method based on factor analysis of mixed data with geometric aggregation (1.00) and linear aggregation (1.00), and weighting based on multiple correspondence analysis with linear aggregation (1.00), it means that there are similarities with PPLS Meanwhile, the weighting method based on multiple correspondence analysis with geometric aggregation had the p-value (=0.02) less than α (=0.05), it means that there are not similarities with PPLS The average of the absolute differences in households rank ( ) closest to 0 found in weighting method based on factor analysis of mixed data with geometric aggregation (0.46). Then followed by weighting based on multiple correspondence analysis with linear aggregation (0.50), weighting based on multiple correspondence analysis with geometric aggregation (0.66), and weighting based on factor analysis of mixed data with linear aggregation (0.70). The highest of classification accuracy found in weighting method based on factor analysis of mixed data with geometric aggregation (57.68%). Then followed by weighting based on multiple correspondence analysis with linear aggregation (53.81%), weighting based on factor analysis of mixed data with linear aggregation (44.00%), and weighting based on multiple correspondence analysis with geometric aggregation (42.45%). The highest AUC value found in weighting method based on factor 1078

10 analysis of mixed data with geometric aggregation (78.27%). Then followed by weighting based on multiple correspondence analysis with linear aggregation (76.59%), weighting based on multiple correspondence analysis with geometric aggregation (67.86%), and weighting based on factor analysis of mixed data with linear aggregation (59.22%). Thus, it can be concluded that based on the three tests, the weighting method based on factor analysis of mixed data with geometric aggregation is the best model. Characteristics of The Dramaga Village Household Welfare based on The Best Model Characteristics of Dramaga village household welfare status based on the best method can be explained by Anova and Manova test (Table 19), correlation test of the numeric variables (Table 20), and characteristic test of the categorical variables (Table 21 and 22). Descriptive statistics of the Dramaga village household welfare index in every status presented in Table 18. Anova and Manova test conducted to prove that among Dramaga village household welfare status statistically significant different (Table 18). Rejecting means there are significantly different. Anova test computed to Dramaga village household welfare index, while Manova test to all variables. The p-value of Anova and Manova test less than α (=0.05), it means among the status significantly different. Table 19 presented that the high value of Dramaga village household welfare status associated with the high value of the numeric variables. Table 20 and 21 presented the characteristics of status 1, 2, 3, and 4 respectively, based on the categorical variables. The sex of the household head in status 1, 2, and 3 is male, while it is female in status 4. The marital status of the household head in status 1, 2, and 3 is married, while it is not married in status 4. The educational level of the household head in all status is elementary school level. The working status of the household head in all status is working. The main occupational sector of the status is tertiary. household head in all The status of residence mastery in all status is selfowned. The wall material in status 1, 2, and 4 is wall, while it is the others in status 3. The roof material in all status is tiles. The source of drinking water in all status is protected wells. The way of getting the drinking water in all status is not buying. The source of main lighting in all status is electric meter. The toilet facility in all status is self-owned. The final stool disposal site in status 1 and 2 is in septic tank, while it is in the river/lake/sea in status 3 and 4. The refrigerator and motorcycle ownership in all status is none. The main job position of the household head in all status is the others. The floor material in all status is not soil. Table 18. Descriptive statistics of Dramaga village household welfare index in every status Number of households Mean Standard Deviation Min Max Total Table 19. Anova and Manova test of Dramaga village household welfare status Anova Manova df 1 df 2 F P-Value df 1 df 2 Wilks F P-Value

11 Table 20. Correlation test between the numeric variables and Dramaga village household welfare status Numeric Correlation (%) Numeric Correlation (%) Numeric Correlation (%) Modalities Table 21. Characteristics of the categorical variables of status 1 and 2 Test Values Variable Modalities Test Values Variable 1 2 Male Male Married Married Elementary Elementary Working Working Tertiary Tertiary Self-owned Self-owned Wall Wall Tiles Tiles Protected Protected wells wells No buying No buying PLN with PLN with Self-owned Self-owned Septic tank Septic tank No No No No Others Others No soil No soil Tertiary, Others Working, Self-owned Tertiary, Others Working, Self-owned Modalities Table 22. Characteristics of the categorical variables of status 3 and 4 Test Values Variable Modalities Test Values Variable 3 4 Male Female Married Not married Elementary Elementary Working Working Tertiary Tertiary Self-owned Self-owned Wall Wall Others Tiles Protected Protected wells wells No buying No buying PLN with PLN with Self-owned Self-owned River/lake/sea River/lake/sea No No No No

12 Others Others No soil No soil Tertiary, Tertiary, Others Others Working, Working, Self-owned Self-owned Comparison of The Dramaga Village Household Welfare based on The Best Model and PPLS 2011 The comparison of the Dramaga village household welfare status based on the best model and PPLS 2011 can be explained by correlation test of the numeric variables (Table 23) and characteristic test of the categorical variables (Table 24 and 25). Table 23 showed that the correlation between numeric variables and Dramaga village household welfare status based on the best method is larger than PPLS 2011 with the test statistic is This means that the best model gave more accurate results than PPLS Table 24 and 25 showed that most of the characteristics of the best model and PPLS 2011 are similar even in status 1, 2, 3, and 4, especially in sex of the household head, marital status of the household head, educational level of the household head, working status of the household head, main occupational sector of the household head, wall material, roof material, source of drinking water, way of getting the drinking water, source of main lighting, toilet facility, motorcycle ownership, main job position of the household head, and floor material. The different characteristics between the best model and PPLS 2011 only in 3 variables, the first is the status of residence mastery especially in status 3, the best model is self-owned, while it is contract/lease in PPLS The second is final stool disposal site especially in status 1, the best model is septic tank, while it is river/lake/sea in PPLS The last is refrigerator ownership especially in status 4, the best model is no refrigerator, while it has refrigerator in PPLS Numeric Table 23. Comparison of the numeric variables correlation test Correlation (%) Numeric Correlation (%) Numeric Correlation (%) PPLS 2011 Best Model PPLS 2011 Best Model PPLS 2011 Best Model Table 24. Comparison of the categorical characteristics of status 1 and PPLS 2011 Best model PPLS 2011 Best model Male Male Male Male Married Married Married Married Elementary Elementary Elementary Elementary Working Working Working Working Tertiary Tertiary Tertiary Tertiary Self-owned Self-owned Self-owned Self-owned Wall Wall Wall Wall Tiles Tiles Tiles Tiles Protected wells Protected wells Protected wells Protected wells No buying No buying No buying No buying 1081

13 Self-owned Self-owned Self-owned Self-owned River/lake/sea Septic tank Septic tank River/lake/sea No No No No No No No No Others Others Others Others No soil No soil No soil No soil Tertiary, Others Tertiary, Others Tertiary, Others Tertiary, Others Working, Self-owned Working, Self-owned Working, Self-owned Working, Self-owned Table 25. Comparison of the categorical characteristics of status 3 and PPLS 2011 Best model PPLS 2011 Best model Male Male Female Female Married Married Not married Not married Elementary Elementary Elementary Elementary Working Working Working Working Tertiary Tertiary Tertiary Tertiary contract/lease Self-owned Self-owned Self-owned Wall Wall Wall Wall Tiles Others Tiles Tiles Protected wells Protected wells Protected wells Protected wells No buying No buying No buying No buying Self-owned Self-owned Self-owned Self-owned River/lake/sea River/lake/sea River/lake/sea River/lake/sea No No Yes No No No No No Others Others Others Others No soil No soil No soil No soil Tertiary, Others Tertiary, Others Tertiary, Others Tertiary, Others Working, Self-owned Working, Self-owned Working, Self-owned Working, Self-owned IV. CONCLUSION The algorithm of weighting method based on factor analysis of mixed data can handle a mixture of numeric and categorical variables, so it make easier to weight the mixed type variables of numeric and categorical. Constructing composite indicators of numeric and categorical variables using weighting method based on factor analysis of mixed data is more accurate than using weighting based on multiple correspondence analysis. The non-linear aggreagtion method developed to handle a mixture of compensatory and noncompensatory variables. Constructing composite indicators of compensatory and non-compensatory variables using geometric aggreagtion method is more accurate than using linear aggreagtion method in weighting method based on factor analysis of mixed data. The best model of constructing Dramaga village household welfare status by using weighting method based on factor analysis of mixed data and geometric aggreagtion method. The use of weighting method based on factor analysis of mixed data and geometric aggreagtion method gave more accurate results in individual classification. Constructing Dramaga village household welfare status using the best model gave the classification accuracy of 57.68% with the AUC of 78.27% and the absolute differences in households rank ( ) of The correlation between numeric variables and Dramaga village household welfare status based on the best method is larger than PPLS This proved that using weighting method based on factor analysis 1082

14 of mixed data and geometric aggreagtion method in constructing Dramaga village household welfare status gave more accurate results. The Dramaga village household welfare status based on the best model characterized by sex of the household head, marital status of the household head, wall material, and final stool disposal site. The sex of the household head in status 1, 2, and 3 is male, while it is female in status 4. The marital status of the household head in status 1, 2, and 3 is married, while it is not married in status 4. The wall material in status 1, 2, and 4 is wall, while it is the others in status 3. The final stool disposal site in status 1 and 2 is in septic tank, while it is in the river/lake/sea in status 3 and 4. [5]. Pages, J. (2004). Analyse Factorielle de Donnees Mixtes. Revue de Statistiquee, 52(4), [6]. Sari, W.J. (2011). Pembentukan Indikator Sasaran Dengan Proxy Means Test Berdasarkan Metode Princals, Depok: Universitas Indonesia [7]. Tarabusi, E.C., & Guarini, G. (2013). An Unbalance Adjustment Method for Development Indicators. Social Indicators Research, 112(1), [8]. Tim Nasional Percepatan Penanggulangan Kemiskinan TNP2K]. (2013). Pembangunan Basis Data Terpadu untuk Mendukung Program Perlindungan Sosial, Jakarta: Author Besides that, most of the characteristics of Dramaga village household welfare status based on the best model are similar with PPLS The different characteristics between the best model and PPLS 2011 are only in the status of residence mastery, the final stool disposal site, and the refrigerator ownership. V. REFERENCES [1]. Castano, E. (2002). Proxy Means Test Index for Targeting Social Programs: Two Methodologies and Empirical Evidence. Lecturas de Economia, 56(1), [2]. Mazziotta, M., & Pareto, A. (2013). Methods for Constructing Composite Indices: One for All or All for One?. Rivista Italiana di Economia Demografia e Statistica, 67(2), [3]. Nicoletti, G., Scarpetta, S., & Boylaud, O. (2000). Summary Indicators Of Product Market Regulation With An Extension To Employment Protection Legislation. ECO/WKP. 226(1), [4]. Organisation for Economic Co-Operation and Developement OECD]. (2008). Handbook on Constructing Composite Indicators Methodology and User Guide, Paris: Author 1083

Multilevel modeling and panel data analysis in educational research (Case study: National examination data senior high school in West Java)

Multilevel modeling and panel data analysis in educational research (Case study: National examination data senior high school in West Java) Multilevel modeling and panel data analysis in educational research (Case study: National examination data senior high school in West Java) Pepi Zulvia, Anang Kurnia, and Agus M. Soleh Citation: AIP Conference

More information

FINDING THE BEST INDICATORS TO IDENTIFY THE POOR

FINDING THE BEST INDICATORS TO IDENTIFY THE POOR FINDING THE BEST INDICATORS TO IDENTIFY THE POOR ADAMA BAH TNP2K WORKING PAPER 01 2013 September 2013 2 FINDING THE BEST INDICATORS TO IDENTIFY THE POOR ADAMA BAH TNP2K WORKING PAPER 01 2013 September

More information

Comparing Two Non-Compensatory Composite Indices to Measure Changes over Time: a Case Study

Comparing Two Non-Compensatory Composite Indices to Measure Changes over Time: a Case Study ANALYSES Comparing Two Non-Compensatory Composite Indices to Measure Changes over Time: a Case Study Matteo Mazziotta 1 Italian National Institute of Statistics, Rome, Italy Adriano Pareto 2 Italian National

More information

Apéndice 1: Figuras y Tablas del Marco Teórico

Apéndice 1: Figuras y Tablas del Marco Teórico Apéndice 1: Figuras y Tablas del Marco Teórico FIGURA A.1.1 Manufacture poles and manufacture regions Poles: Share of employment in manufacture at least 12% and population of 250,000 or more. Regions:

More information

Non-compensatory Composite Indices for Measuring Changes over Time: A Comparative Study

Non-compensatory Composite Indices for Measuring Changes over Time: A Comparative Study Non-compensatory Composite Indices for Measuring Changes over Time: A Comparative Study Matteo Mazziotta and Adriano Pareto Italian National Institute of Statistics Introduction In the recent years a large

More information

Ensemble Spatial Autoregressive Model on. the Poverty Data in Java

Ensemble Spatial Autoregressive Model on. the Poverty Data in Java Applied Mathematical Sciences, Vol. 9, 2015, no. 43, 2103-2110 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ams.2015.4121034 Ensemble Spatial Autoregressive Model on the Poverty Data in Java

More information

Lecture 28 Chi-Square Analysis

Lecture 28 Chi-Square Analysis Lecture 28 STAT 225 Introduction to Probability Models April 23, 2014 Whitney Huang Purdue University 28.1 χ 2 test for For a given contingency table, we want to test if two have a relationship or not

More information

CSAE WPS/2008-06 1998-2001 panel Mitch panel Mitch panel Mitch panel 1998-2001 panel 1998 1999 2001 Poverty 68.7% 74.1% 73.1% 70.6% 63.6% Extreme Poverty 28.6% 32.0% 34.5% 25.9% 25.4%

More information

Socio-Economic Atlas of Tajikistan. The World Bank THE STATE STATISTICAL COMMITTEE OF THE REPUBLIC OF TAJIKISTAN

Socio-Economic Atlas of Tajikistan. The World Bank THE STATE STATISTICAL COMMITTEE OF THE REPUBLIC OF TAJIKISTAN Socio-Economic Atlas of Tajikistan The World Bank THE STATE STATISTICAL COMMITTEE OF THE REPUBLIC OF TAJIKISTAN 1) Background Why there is a need for socio economic atlas? Need for a better understanding

More information

CRP 272 Introduction To Regression Analysis

CRP 272 Introduction To Regression Analysis CRP 272 Introduction To Regression Analysis 30 Relationships Among Two Variables: Interpretations One variable is used to explain another variable X Variable Independent Variable Explaining Variable Exogenous

More information

Measuring Poverty. Introduction

Measuring Poverty. Introduction Measuring Poverty Introduction To measure something, we need to provide answers to the following basic questions: 1. What are we going to measure? Poverty? So, what is poverty? 2. Who wants to measure

More information

Chapter Fifteen. Frequency Distribution, Cross-Tabulation, and Hypothesis Testing

Chapter Fifteen. Frequency Distribution, Cross-Tabulation, and Hypothesis Testing Chapter Fifteen Frequency Distribution, Cross-Tabulation, and Hypothesis Testing Copyright 2010 Pearson Education, Inc. publishing as Prentice Hall 15-1 Internet Usage Data Table 15.1 Respondent Sex Familiarity

More information

A Panel Data Analysis of The Role of Human Development Index in Poverty Reduction in Papua

A Panel Data Analysis of The Role of Human Development Index in Poverty Reduction in Papua A Panel Data Analysis of The Role of Human Development Index in Poverty Reduction in Papua 2010 2015 Faisal Arief* Statistics of Ternate City, Ternate, Indonesia faisal.arief@bps.go.id Erli Wijayanti Prastiwi

More information

EVALUATING THE TOURIST SATISFACTION IN FIVE FAMOUS ITALIAN CITIES

EVALUATING THE TOURIST SATISFACTION IN FIVE FAMOUS ITALIAN CITIES Rivista Italiana di Economia Demografia e Statistica Volume LXXIII n. 1 Gennaio-Marzo 219 EVALUATING THE TOURIST SATISFACTION IN FIVE FAMOUS ITALIAN CITIES Mariateresa Ciommi, Gennaro Punzo, Gaetano Musella

More information

Sources and Methods for the Analysis of International Data

Sources and Methods for the Analysis of International Data UNIVERSITA' DEGLI STUDI DI NAPOLI FEDERICO II Master s Degree in International Relations Sources and Methods for the Analysis of International Data F. Di Iorio Couse Outline Population and statistical

More information

ECONOMETRIC MODEL WITH QUALITATIVE VARIABLES

ECONOMETRIC MODEL WITH QUALITATIVE VARIABLES ECONOMETRIC MODEL WITH QUALITATIVE VARIABLES How to quantify qualitative variables to quantitative variables? Why do we need to do this? Econometric model needs quantitative variables to estimate its parameters

More information

DETERMINING POVERTY MAP USING SMALL AREA ESTIMATION METHOD

DETERMINING POVERTY MAP USING SMALL AREA ESTIMATION METHOD DETERMINING OVERTY MA USING SMALL AREA ESTIMATION METHOD Eko Yuliasih and Irwan Susanto T Bank UOB Buana Jakarta and Mathematics Dept. F MIA Sebelas Maret University yuliasih.eko@gmail.com Abstract. overty

More information

Using copulas to deal with endogeneity

Using copulas to deal with endogeneity An application to development economics Summer School in Development Economics Alba di Canazei, July 16 2013 Overview Endogeneity Copulas Estimation Simulations Telephone use in Uganda Motivation Endogeneity

More information

The System of Xiaokang Indicators: A Framework to Measure China's Progress

The System of Xiaokang Indicators: A Framework to Measure China's Progress Int. Statistical Inst.: Proc. 58th World Statistical Congress, 2011, Dublin (Session CPS020) p.6359 The System of Xiaokang Indicators: A Framework to Measure China's Progress Qingzhe Lv E-mail: lvqz@gj.stats.cn

More information

Poverty Outreach of Microfinance in Ecuador

Poverty Outreach of Microfinance in Ecuador Poverty Outreach of Microfinance in Ecuador An Application of the CGAP Poverty Assessment Tool on a Microcredit Program of INSOTEC in Santo Domingo de los Colorados Tonja van Gorp M.Sc. International Development

More information

Table 1. Answers to income and consumption adequacy questions Percentage of responses: less than adequate more than adequate adequate Total income 68.7% 30.6% 0.7% Food consumption 46.6% 51.4% 2.0% Clothing

More information

Research on the Influence Factors of Urban-Rural Income Disparity Based on the Data of Shandong Province

Research on the Influence Factors of Urban-Rural Income Disparity Based on the Data of Shandong Province International Journal of Managerial Studies and Research (IJMSR) Volume 4, Issue 7, July 2016, PP 22-27 ISSN 2349-0330 (Print) & ISSN 2349-0349 (Online) http://dx.doi.org/10.20431/2349-0349.0407003 www.arcjournals.org

More information

Demographic Data in ArcGIS. Harry J. Moore IV

Demographic Data in ArcGIS. Harry J. Moore IV Demographic Data in ArcGIS Harry J. Moore IV Outline What is demographic data? Esri Demographic data - Real world examples with GIS - Redistricting - Emergency Preparedness - Economic Development Next

More information

Turning a research question into a statistical question.

Turning a research question into a statistical question. Turning a research question into a statistical question. IGINAL QUESTION: Concept Concept Concept ABOUT ONE CONCEPT ABOUT RELATIONSHIPS BETWEEN CONCEPTS TYPE OF QUESTION: DESCRIBE what s going on? DECIDE

More information

Lecture 3: Multiple Regression. Prof. Sharyn O Halloran Sustainable Development U9611 Econometrics II

Lecture 3: Multiple Regression. Prof. Sharyn O Halloran Sustainable Development U9611 Econometrics II Lecture 3: Multiple Regression Prof. Sharyn O Halloran Sustainable Development Econometrics II Outline Basics of Multiple Regression Dummy Variables Interactive terms Curvilinear models Review Strategies

More information

TRAVEL PATTERNS IN INDIAN DISTRICTS: DOES POPULATION SIZE MATTER?

TRAVEL PATTERNS IN INDIAN DISTRICTS: DOES POPULATION SIZE MATTER? TRAVEL PATTERNS IN INDIAN DISTRICTS: DOES POPULATION SIZE MATTER? Deepty Jain Lecturer Department of Energy and Environment TERI University Delhi Dr. Geetam Tiwari Professor Department of Civil Engineering

More information

SMALL AREA ESTIMATION OF LITERACY RATES ON SUB- DISTRICT LEVEL IN DISTRICT OF DONGGALA WITH HIERARCHICAL BAYES METHOD

SMALL AREA ESTIMATION OF LITERACY RATES ON SUB- DISTRICT LEVEL IN DISTRICT OF DONGGALA WITH HIERARCHICAL BAYES METHOD Small Forum Area Statistika Estimation dan Of Komputasi Literacy : Rates Indonesian On Sub-District Journal of Statistics Level ISSN In : District 0853-8115 Of Donggala With Hierarchical Bayes Vol. 20

More information

Discriminant Analysis on Mixed Predictors

Discriminant Analysis on Mixed Predictors Chapter 1 Discriminant Analysis on Mixed Predictors R. Abdesselam Abstract The processing of mixed data - both quantitative and qualitative variables - cannot be carried out as explanatory variables through

More information

FIG Congress 2014 Engaging the Challenges, Enhancing the Relevance Kuala Lumpur, Malaysia, June 2014

FIG Congress 2014 Engaging the Challenges, Enhancing the Relevance Kuala Lumpur, Malaysia, June 2014 FIG Congress 2014 Engaging the Challenges, Enhancing the Relevance Kuala Lumpur, Malaysia, 16 21 June 2014 Disaster Risk Maps for Gender Empowerment in Disaster Management Lalitya Narieswari, Sri Lestari

More information

ANALYSIS OF POVERTY IN INDONESIA WITH SMALL AREA ESTIMATION : CASE IN DEMAK DISTRICT

ANALYSIS OF POVERTY IN INDONESIA WITH SMALL AREA ESTIMATION : CASE IN DEMAK DISTRICT ANALYSIS OF POVERTY IN INDONESIA WITH SMALL AREA ESTIMATION : CASE IN DEMAK DISTRICT Setia Iriyanto Faculty of Economics, University of Muhammadiyah Semarang Indonesia Email: setiairiyanto_se@yahoo.com

More information

VII APPROACHES IN SELECTING A CORE SET OF INDICATORS

VII APPROACHES IN SELECTING A CORE SET OF INDICATORS HANDBOOK ON RURAL HOUSEHOLDS LIVELIHOOD AND WELL-BEING VII APPROACHES IN SELECTING A CORE SET OF INDICATORS VII.1 Introduction In Chapters III to VI of this Handbook, and in associated annexes, numerous

More information

Sources of Inequality: Additive Decomposition of the Gini Coefficient.

Sources of Inequality: Additive Decomposition of the Gini Coefficient. Sources of Inequality: Additive Decomposition of the Gini Coefficient. Carlos Hurtado Econometrics Seminar Department of Economics University of Illinois at Urbana-Champaign hrtdmrt2@illinois.edu Feb 24th,

More information

Poverty statistics in Mongolia

Poverty statistics in Mongolia HIGH-LEVEL SEMINAR ON HARMONISATION OF POVERTY STATISTICS IN CIS COUNTRIES SOCHI (RUSSIAN FEDERATION) Poverty statistics in Mongolia Oyunchimeg Dandar Director Population and Social Statistics Department,

More information

Random Forests for Poverty Classification

Random Forests for Poverty Classification International Journal of Sciences: Basic and Applied Research (IJSBAR) ISSN 2307-4531 (Print & Online) http://gssrr.org/index.php?journal=journalofbasicandapplied ---------------------------------------------------------------------------------------------------------------------------

More information

THE EFFECT OF EXPLOITATION OF NATURAL RESOURCES TO ECONOMIC GROWTH AND HUMAN DEVELOPMENT INDEX IN SOUTH KALIMANTAN PROVINCE

THE EFFECT OF EXPLOITATION OF NATURAL RESOURCES TO ECONOMIC GROWTH AND HUMAN DEVELOPMENT INDEX IN SOUTH KALIMANTAN PROVINCE THE EFFECT OF EXPLOITATION OF NATURAL RESOURCES TO ECONOMIC GROWTH AND HUMAN DEVELOPMENT INDEX IN SOUTH KALIMANTAN PROVINCE Lydia Goenadhi & Nur Astri (Sekolah Tinggi Ilmu Ekonomi Indonesia Banjarmasin)

More information

International Journal of Advances in Management, Economics and Entrepreneurship. Available online at: RESEARCH ARTICLE

International Journal of Advances in Management, Economics and Entrepreneurship. Available online at:   RESEARCH ARTICLE International Journal of Advances in Management, Economics and Entrepreneurship Available online at: www.ijamee.info RESEARCH ARTICLE A Factor Analysis of Determinants of Human Development in Rural Odisha

More information

CHI SQUARE ANALYSIS 8/18/2011 HYPOTHESIS TESTS SO FAR PARAMETRIC VS. NON-PARAMETRIC

CHI SQUARE ANALYSIS 8/18/2011 HYPOTHESIS TESTS SO FAR PARAMETRIC VS. NON-PARAMETRIC CHI SQUARE ANALYSIS I N T R O D U C T I O N T O N O N - P A R A M E T R I C A N A L Y S E S HYPOTHESIS TESTS SO FAR We ve discussed One-sample t-test Dependent Sample t-tests Independent Samples t-tests

More information

Market access and rural poverty in Tanzania

Market access and rural poverty in Tanzania Market access and rural poverty in Tanzania Nicholas Minot International Food Policy Research Institute 2033 K St. NW Washington, D.C., U.S.A. Phone: +1 202 862-8199 Email: n.minot@cgiar.org Contributed

More information

Urban dependence on ecosystem services: a spatially explicit analysis of a megacity riverside settlement

Urban dependence on ecosystem services: a spatially explicit analysis of a megacity riverside settlement Urban dependence on ecosystem services: a spatially explicit analysis of a megacity riverside settlement Derek Vollmer PhD Candidate (Prof. Dr. Adrienne Grêt-Regamey, advisor) ETH Zürich/Future Cities

More information

Robust Multidimensional Poverty Comparisons

Robust Multidimensional Poverty Comparisons Robust Multidimensional Poverty Comparisons by Jean-Yves Duclos Department of Economics and CIRPÉE, Université Laval, Canada, David Sahn Food and Nutrition Policy Program, Cornell University and Stephen

More information

Didacticiel Études de cas. Parametric hypothesis testing for comparison of two or more populations. Independent and dependent samples.

Didacticiel Études de cas. Parametric hypothesis testing for comparison of two or more populations. Independent and dependent samples. 1 Subject Parametric hypothesis testing for comparison of two or more populations. Independent and dependent samples. The tests for comparison of population try to determine if K (K 2) samples come from

More information

CONSTRUCTING THE POVERTY AND OPPORTUNITIES/PUBLIC SERVICES MAPS INFORMATION MANAGEMENT. Background: Brazil Without Extreme Poverty Plan

CONSTRUCTING THE POVERTY AND OPPORTUNITIES/PUBLIC SERVICES MAPS INFORMATION MANAGEMENT. Background: Brazil Without Extreme Poverty Plan INFORMATION MANAGEMENT CONSTRUCTING THE POVERTY AND OPPORTUNITIES/PUBLIC SERVICES MAPS Background: Brazil Without Extreme Poverty Plan The Brazil Without Extreme Poverty Plan (BSM), designed to overcome

More information

HOW THE COMMUTERS MOVE: A STATISTICAL ANALYSIS BASED ON ITALIAN CENSUS DATA

HOW THE COMMUTERS MOVE: A STATISTICAL ANALYSIS BASED ON ITALIAN CENSUS DATA Rivista Italiana di Economia Demografia e Statistica Volume LXIX n. 4 Ottobre-Dicembre 2015 HOW THE COMMUTERS MOVE: A STATISTICAL ANALYSIS BASED ON ITALIAN CENSUS DATA Gabriella Schoier, Adriana Monte

More information

Parametric versus Nonparametric Statistics-when to use them and which is more powerful? Dr Mahmoud Alhussami

Parametric versus Nonparametric Statistics-when to use them and which is more powerful? Dr Mahmoud Alhussami Parametric versus Nonparametric Statistics-when to use them and which is more powerful? Dr Mahmoud Alhussami Parametric Assumptions The observations must be independent. Dependent variable should be continuous

More information

Politician Family Networks and Electoral Outcomes: Evidence from the Philippines. Online Appendix. Cesi Cruz, Julien Labonne, and Pablo Querubin

Politician Family Networks and Electoral Outcomes: Evidence from the Philippines. Online Appendix. Cesi Cruz, Julien Labonne, and Pablo Querubin Politician Family Networks and Electoral Outcomes: Evidence from the Philippines Online Appendix Cesi Cruz, Julien Labonne, and Pablo Querubin 1 A.1 Additional Figures 8 4 6 2 Vote Share (residuals) 4

More information

PRIMA. Planning for Retailing in Metropolitan Areas

PRIMA. Planning for Retailing in Metropolitan Areas PRIMA Planning for Retailing in Metropolitan Areas Metropolitan Dimension to sustainable retailing futures Metropolitan strategies Retailing in city and town centres will be a primary component of any

More information

Making sense of Econometrics: Basics

Making sense of Econometrics: Basics Making sense of Econometrics: Basics Lecture 4: Qualitative influences and Heteroskedasticity Egypt Scholars Economic Society November 1, 2014 Assignment & feedback enter classroom at http://b.socrative.com/login/student/

More information

Applied Econometrics (MSc.) Lecture 3 Instrumental Variables

Applied Econometrics (MSc.) Lecture 3 Instrumental Variables Applied Econometrics (MSc.) Lecture 3 Instrumental Variables Estimation - Theory Department of Economics University of Gothenburg December 4, 2014 1/28 Why IV estimation? So far, in OLS, we assumed independence.

More information

Group comparison test for independent samples

Group comparison test for independent samples Group comparison test for independent samples The purpose of the Analysis of Variance (ANOVA) is to test for significant differences between means. Supposing that: samples come from normal populations

More information

Chapter 14. Multiple Regression Models. Multiple Regression Models. Multiple Regression Models

Chapter 14. Multiple Regression Models. Multiple Regression Models. Multiple Regression Models Chapter 14 Multiple Regression Models 1 Multiple Regression Models A general additive multiple regression model, which relates a dependent variable y to k predictor variables,,, is given by the model equation

More information

Dwelling Price Ranking vs. Socio-Economic Ranking: Possibility of Imputation

Dwelling Price Ranking vs. Socio-Economic Ranking: Possibility of Imputation Dwelling Price Ranking vs. Socio-Economic Ranking: Possibility of Imputation Larisa Fleishman Yury Gubman Aviad Tur-Sinai Israeli Central Bureau of Statistics The main goals 1. To examine if dwelling prices

More information

Mining Approximate Top-K Subspace Anomalies in Multi-Dimensional Time-Series Data

Mining Approximate Top-K Subspace Anomalies in Multi-Dimensional Time-Series Data Mining Approximate Top-K Subspace Anomalies in Multi-Dimensional -Series Data Xiaolei Li, Jiawei Han University of Illinois at Urbana-Champaign VLDB 2007 1 Series Data Many applications produce time series

More information

Seaport Status, Access, and Regional Development in Indonesia

Seaport Status, Access, and Regional Development in Indonesia Seaport Status, Access, and Regional Development in Indonesia Muhammad Halley Yudhistira Yusuf Sofiyandi Institute for Economic and Social Research (LPEM), Faculty of Economics and Business, University

More information

Households or locations? Cities, catchment areas and prosperity in India

Households or locations? Cities, catchment areas and prosperity in India Households or locations? Cities, catchment areas and prosperity in India Yue Li and Martin Rama World Bank July 13, 2015 Motivation and approach (Some) cities are drivers of prosperity in India Because

More information

Online Appendices, Not for Publication

Online Appendices, Not for Publication Online Appendices, Not for Publication Appendix A. Network definitions In this section, we provide basic definitions and interpretations for the different network characteristics that we consider. At the

More information

The Influence of Geographical Factors On Poverty Alleviation Program

The Influence of Geographical Factors On Poverty Alleviation Program The Influence of Geographical Factors On Poverty Alleviation Program Lynda Refnitasari, Doddy Aditya Iskandar, and Retno Widodo Dwi Pramono Abstract Poverty is one of the problems that must be tackled

More information

Evaluating Community Analyst for Use in School Demography Studies

Evaluating Community Analyst for Use in School Demography Studies Portland State University PDXScholar Publications, Reports and Presentations Population Research Center 7-2013 Evaluating Community Analyst for Use in School Demography Studies Richard Lycan Portland State

More information

Summary prepared by Amie Gaye: UNDP Human Development Report Office

Summary prepared by Amie Gaye: UNDP Human Development Report Office Contribution to Beyond Gross Domestic Product (GDP) Name of the indicator/method: The Human Development Index (HDI) Summary prepared by Amie Gaye: UNDP Human Development Report Office Date: August, 2011

More information

Projection of Geospatial Human Resources In Indonesia Until 2025

Projection of Geospatial Human Resources In Indonesia Until 2025 Projection of Geospatial Human Resources In Indonesia Until 2025 Fahmi AMHAR, SUPRAJAKA, SUMARYONO Budi SUSETYO, Iksal YANUARSYAH, Indonesia Key words: capacity building;cpd; education; professional practice;

More information

MULTIDIMENSIONAL POVERTY MEASUREMENT: DEPENDENCE BETWEEN WELL-BEING DIMENSIONS USING COPULA FUNCTION

MULTIDIMENSIONAL POVERTY MEASUREMENT: DEPENDENCE BETWEEN WELL-BEING DIMENSIONS USING COPULA FUNCTION Rivista Italiana di Economia Demografia e Statistica Volume LXXII n. 3 Luglio-Settembre 2018 MULTIDIMENSIONAL POVERTY MEASUREMENT: DEPENDENCE BETWEEN WELL-BEING DIMENSIONS USING COPULA FUNCTION Kateryna

More information

Administrative Data Research Facility Linked HMDA and ACS Database

Administrative Data Research Facility Linked HMDA and ACS Database University of Pennsylvania ScholarlyCommons 2017 ADRF Network Research Conference Presentations ADRF Network Research Conference Presentations 11-2017 Administrative Data Research Facility Linked HMDA

More information

COMPOSITE INDICATORS AND SPATIAL CORRELATIONS OF ITALIAN MUNICIPALITIES SOCIO-ECONOMIC MEASURES 1

COMPOSITE INDICATORS AND SPATIAL CORRELATIONS OF ITALIAN MUNICIPALITIES SOCIO-ECONOMIC MEASURES 1 Rivista Italiana di Economia Demografia e Statistica Volume LXXII n. 3 Luglio-Settembre 2018 COMPOSITE INDICATORS AND SPATIAL CORRELATIONS OF ITALIAN MUNICIPALITIES SOCIO-ECONOMIC MEASURES 1 Antonella

More information

5. Let W follow a normal distribution with mean of μ and the variance of 1. Then, the pdf of W is

5. Let W follow a normal distribution with mean of μ and the variance of 1. Then, the pdf of W is Practice Final Exam Last Name:, First Name:. Please write LEGIBLY. Answer all questions on this exam in the space provided (you may use the back of any page if you need more space). Show all work but do

More information

NC Births, ANOVA & F-tests

NC Births, ANOVA & F-tests Math 158, Spring 2018 Jo Hardin Multiple Regression II R code Decomposition of Sums of Squares (and F-tests) NC Births, ANOVA & F-tests A description of the data is given at http://pages.pomona.edu/~jsh04747/courses/math58/

More information

Analysis of Post-Local Government Proliferation Practice on Socioeconomic Change in Nias

Analysis of Post-Local Government Proliferation Practice on Socioeconomic Change in Nias International Journal of Progressive Sciences and Technologies (IJPSAT) ISSN: 2509-0119. 2018International Journals of Sciences and High Technologies http://ijpsat.ijsht-journals.org Vol. 9 No. 2 July

More information

THE ROYAL STATISTICAL SOCIETY HIGHER CERTIFICATE

THE ROYAL STATISTICAL SOCIETY HIGHER CERTIFICATE THE ROYAL STATISTICAL SOCIETY 004 EXAMINATIONS SOLUTIONS HIGHER CERTIFICATE PAPER II STATISTICAL METHODS The Society provides these solutions to assist candidates preparing for the examinations in future

More information

A PRIMER ON LINEAR REGRESSION

A PRIMER ON LINEAR REGRESSION A PRIMER ON LINEAR REGRESSION Marc F. Bellemare Introduction This set of lecture notes was written so as to allow you to understand the classical linear regression model, which is one of the most common

More information

Does city structure cause unemployment?

Does city structure cause unemployment? The World Bank Urban Research Symposium, December 15-17, 2003 Does city structure cause unemployment? The case study of Cape Town Presented by Harris Selod (INRA and CREST, France) Co-authored with Sandrine

More information

Opportunities and challenges of HCMC in the process of development

Opportunities and challenges of HCMC in the process of development Opportunities and challenges of HCMC in the process of development Lê Văn Thành HIDS HCMC, Sept. 16-17, 2009 Contents The city starting point Achievement and difficulties Development perspective and goals

More information

STAT 3900/4950 MIDTERM TWO Name: Spring, 2015 (print: first last ) Covered topics: Two-way ANOVA, ANCOVA, SLR, MLR and correlation analysis

STAT 3900/4950 MIDTERM TWO Name: Spring, 2015 (print: first last ) Covered topics: Two-way ANOVA, ANCOVA, SLR, MLR and correlation analysis STAT 3900/4950 MIDTERM TWO Name: Spring, 205 (print: first last ) Covered topics: Two-way ANOVA, ANCOVA, SLR, MLR and correlation analysis Instructions: You may use your books, notes, and SPSS/SAS. NO

More information

Understanding China Census Data with GIS By Shuming Bao and Susan Haynie China Data Center, University of Michigan

Understanding China Census Data with GIS By Shuming Bao and Susan Haynie China Data Center, University of Michigan Understanding China Census Data with GIS By Shuming Bao and Susan Haynie China Data Center, University of Michigan The Census data for China provides comprehensive demographic and business information

More information

Answer Key: Problem Set 5

Answer Key: Problem Set 5 : Problem Set 5. Let nopc be a dummy variable equal to one if the student does not own a PC, and zero otherwise. i. If nopc is used instead of PC in the model of: colgpa = β + δ PC + β hsgpa + β ACT +

More information

The World Bank Decentralized Community Driven Services Project (P117764)

The World Bank Decentralized Community Driven Services Project (P117764) Public Disclosure Authorized AFRICA Benin Social Protection Global Practice IBRD/IDA Adaptable Program Loan FY 2012 Seq No: 6 ARCHIVED on 12-Jun-2015 ISR19748 Implementing Agencies: Public Disclosure Authorized

More information

Tribhuvan University Institute of Science and Technology 2065

Tribhuvan University Institute of Science and Technology 2065 1CSc. Stat. 108-2065 Tribhuvan University Institute of Science and Technology 2065 Bachelor Level/First Year/ First Semester/ Science Full Marks: 60 Computer Science and Information Technology (Stat. 108)

More information

Data Matrix User Guide

Data Matrix User Guide Data Matrix User Guide 1. Introduction The 2017 Data Matrix is designed to support the 2017 iteration of the Regional Skills Assessments (RSAs) in Scotland. The RSAs align with the Regional Outcome Agreement

More information

Towards an International Data Set for MST

Towards an International Data Set for MST Towards an International Data Set for MST Carl Obst, UNWTO Consultant 15 October, 2018 Background and context The key role of the Measuring the Sustainability of Tourism (MST) project is to support more

More information

Lecture (chapter 13): Association between variables measured at the interval-ratio level

Lecture (chapter 13): Association between variables measured at the interval-ratio level Lecture (chapter 13): Association between variables measured at the interval-ratio level Ernesto F. L. Amaral April 9 11, 2018 Advanced Methods of Social Research (SOCI 420) Source: Healey, Joseph F. 2015.

More information

A course in statistical modelling. session 09: Modelling count variables

A course in statistical modelling. session 09: Modelling count variables A Course in Statistical Modelling SEED PGR methodology training December 08, 2015: 12 2pm session 09: Modelling count variables Graeme.Hutcheson@manchester.ac.uk blackboard: RSCH80000 SEED PGR Research

More information

Notes On: Do Television and Radio Destroy Social Capital? Evidence from Indonesian Village (Olken 2009)

Notes On: Do Television and Radio Destroy Social Capital? Evidence from Indonesian Village (Olken 2009) Notes On: Do Television and Radio Destroy Social Capital? Evidence from Indonesian Village (Olken 2009) Increasing interest in phenomenon social capital variety of social interactions, networks, and groups

More information

Chapter 9: The Regression Model with Qualitative Information: Binary Variables (Dummies)

Chapter 9: The Regression Model with Qualitative Information: Binary Variables (Dummies) Chapter 9: The Regression Model with Qualitative Information: Binary Variables (Dummies) Statistics and Introduction to Econometrics M. Angeles Carnero Departamento de Fundamentos del Análisis Económico

More information

CHAPTER 7. + ˆ δ. (1 nopc) + ˆ β1. =.157, so the new intercept is = The coefficient on nopc is.157.

CHAPTER 7. + ˆ δ. (1 nopc) + ˆ β1. =.157, so the new intercept is = The coefficient on nopc is.157. CHAPTER 7 SOLUTIONS TO PROBLEMS 7. (i) The coefficient on male is 87.75, so a man is estimated to sleep almost one and one-half hours more per week than a comparable woman. Further, t male = 87.75/34.33

More information

Fertility Transitions and Wealth in Comparative Perspective. Sarah Staveteig. Demographic and Health Surveys, Futures Institute PRELIMINARY DRAFT

Fertility Transitions and Wealth in Comparative Perspective. Sarah Staveteig. Demographic and Health Surveys, Futures Institute PRELIMINARY DRAFT Fertility Transitions and Wealth in Comparative Perspective Sarah Staveteig Demographic and Health Surveys, Futures Institute PRELIMINARY DRAFT April 2014 PAA 2014 Session 23: Fertility Transitions Sarah

More information

In matrix algebra notation, a linear model is written as

In matrix algebra notation, a linear model is written as DM3 Calculation of health disparity Indices Using Data Mining and the SAS Bridge to ESRI Mussie Tesfamicael, University of Louisville, Louisville, KY Abstract Socioeconomic indices are strongly believed

More information

DIFFERENT INFLUENCES OF SOCIOECONOMIC FACTORS ON THE HUNTING AND FISHING LICENSE SALES IN COOK COUNTY, IL

DIFFERENT INFLUENCES OF SOCIOECONOMIC FACTORS ON THE HUNTING AND FISHING LICENSE SALES IN COOK COUNTY, IL DIFFERENT INFLUENCES OF SOCIOECONOMIC FACTORS ON THE HUNTING AND FISHING LICENSE SALES IN COOK COUNTY, IL Xiaohan Zhang and Craig Miller Illinois Natural History Survey University of Illinois at Urbana

More information

Statistics and Data Analysis

Statistics and Data Analysis Statistics and Data Analysis Professor William Greene Phone: 212.998.0876 Office: KMC 7-90 Home page: http://people.stern.nyu.edu/wgreene Email: wgreene@stern.nyu.edu Course web page: http://people.stern.nyu.edu/wgreene/statistics/outline.htm

More information

Trip Generation Model Development for Albany

Trip Generation Model Development for Albany Trip Generation Model Development for Albany Hui (Clare) Yu Department for Planning and Infrastructure Email: hui.yu@dpi.wa.gov.au and Peter Lawrence Department for Planning and Infrastructure Email: lawrence.peter@dpi.wa.gov.au

More information

Robust geographically weighted regression with least absolute deviation method in case of poverty in Java Island

Robust geographically weighted regression with least absolute deviation method in case of poverty in Java Island Robust geographically weighted regression with least absolute deviation method in case of poverty in Java Island Rawyanil Afifah, Yudhie Andriyana, and I. G. N. Mindra Jaya Citation: AIP Conference Proceedings

More information

Sensitivity checks for the local average treatment effect

Sensitivity checks for the local average treatment effect Sensitivity checks for the local average treatment effect Martin Huber March 13, 2014 University of St. Gallen, Dept. of Economics Abstract: The nonparametric identification of the local average treatment

More information

More on Roy Model of Self-Selection

More on Roy Model of Self-Selection V. J. Hotz Rev. May 26, 2007 More on Roy Model of Self-Selection Results drawn on Heckman and Sedlacek JPE, 1985 and Heckman and Honoré, Econometrica, 1986. Two-sector model in which: Agents are income

More information

BUILDING SOUND AND COMPARABLE METRICS FOR SDGS: THE CONTRIBUTION OF THE OECD DATA AND TOOLS FOR CITIES AND REGIONS

BUILDING SOUND AND COMPARABLE METRICS FOR SDGS: THE CONTRIBUTION OF THE OECD DATA AND TOOLS FOR CITIES AND REGIONS BUILDING SOUND AND COMPARABLE METRICS FOR SDGS: THE CONTRIBUTION OF THE OECD DATA AND TOOLS FOR CITIES AND REGIONS STATISTICAL CAPACITY BUILDING FOR MONITORING OF SUSTAINABLE DEVELOPMENT GOALS Lukas Kleine-Rueschkamp

More information

Robustness of location estimators under t- distributions: a literature review

Robustness of location estimators under t- distributions: a literature review IOP Conference Series: Earth and Environmental Science PAPER OPEN ACCESS Robustness of location estimators under t- distributions: a literature review o cite this article: C Sumarni et al 07 IOP Conf.

More information

Might using the Internet while travelling affect car ownership plans of Millennials? Dr. David McArthur and Dr. Jinhyun Hong

Might using the Internet while travelling affect car ownership plans of Millennials? Dr. David McArthur and Dr. Jinhyun Hong Might using the Internet while travelling affect car ownership plans of Millennials? Dr. David McArthur and Dr. Jinhyun Hong Introduction Travel habits among Millennials (people born between 1980 and 2000)

More information

IOP Conference Series: Earth and Environmental Science. Related content PAPER OPEN ACCESS

IOP Conference Series: Earth and Environmental Science. Related content PAPER OPEN ACCESS IOP Conference Series: Earth and Environmental Science PAPER OPEN ACCESS Implications of Pearl, Gold, Silver (PGS) craft industrial cluster towards settlements region in Karang Pule Village, Sekarbela

More information

In Class Review Exercises Vartanian: SW 540

In Class Review Exercises Vartanian: SW 540 In Class Review Exercises Vartanian: SW 540 1. Given the following output from an OLS model looking at income, what is the slope and intercept for those who are black and those who are not black? b SE

More information

Surrey Pay Offer non-schools 1 July 2017 to 30 June 2018 ADDITIONAL INFORMATION REQUESTED

Surrey Pay Offer non-schools 1 July 2017 to 30 June 2018 ADDITIONAL INFORMATION REQUESTED Surrey Offer non-schools 1 July 2017 to 30 June 2018 ADDITIONAL INFORMATION REQUESTED Contents Table 1: Headcount across pay models for non-schools Table 2: 2016 pay bands for job family and leadership

More information

The Changing Nature of Gender Selection into Employment: Europe over the Great Recession

The Changing Nature of Gender Selection into Employment: Europe over the Great Recession The Changing Nature of Gender Selection into Employment: Europe over the Great Recession Juan J. Dolado 1 Cecilia Garcia-Peñalosa 2 Linas Tarasonis 2 1 European University Institute 2 Aix-Marseille School

More information

Topic 9: Canonical Correlation

Topic 9: Canonical Correlation Topic 9: Canonical Correlation Ying Li Stockholm University October 22, 2012 1/19 Basic Concepts Objectives In canonical correlation analysis, we examine the linear relationship between a set of X variables

More information

ES103 Introduction to Econometrics

ES103 Introduction to Econometrics Anita Staneva May 16, ES103 2015Introduction to Econometrics.. Lecture 1 ES103 Introduction to Econometrics Lecture 1: Basic Data Handling and Anita Staneva Egypt Scholars Economic Society Outline Introduction

More information

Econometrics I Lecture 7: Dummy Variables

Econometrics I Lecture 7: Dummy Variables Econometrics I Lecture 7: Dummy Variables Mohammad Vesal Graduate School of Management and Economics Sharif University of Technology 44716 Fall 1397 1 / 27 Introduction Dummy variable: d i is a dummy variable

More information

Normalized Equation and Decomposition Analysis: Computation and Inference

Normalized Equation and Decomposition Analysis: Computation and Inference DISCUSSION PAPER SERIES IZA DP No. 1822 Normalized Equation and Decomposition Analysis: Computation and Inference Myeong-Su Yun October 2005 Forschungsinstitut zur Zukunft der Arbeit Institute for the

More information