Mobility and Entrepreneurship in Ecuador: A Pseudo-Panel Approach

Please download to get full document.

View again

of 32
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Similar Documents
Information Report
Category:

Education

Published:

Views: 10 | Pages: 32

Extension: PDF | Download: 0

Share
Description
El Banco Interamericano de Desarrollo (BID) publicó el working paper Mobility and Entrepreneurship: A Pseudo Panel Approach, de autoría del profesor de ESPAE, Xavier Ordeñana.Este estudio quiere indagar si ¿Es el emprendimiento exitoso en la mejora de la movilidad social en Ecuador? Para ello se construyó un pseudo panel para analizar el efecto dinámico de la actividad empresarial en los ingresos de los hogares ecuatorianos durante el período 2002-2010. Utilizando tres escenarios de estimación, nos encontramos con un significativo nivel de movilidad incondicional y un efecto importante de la actividad empresarial (movilidad condicional). También se encontró que las mujeres experimentan mayor movilidad que los hombres.
Transcript
  • 1. IDB WORKING PAPER SERIES No. IDB-WP-319Mobility andEntrepreneurshipin Ecuador:A Pseudo-Panel ApproachXavier OrdeñanaRamón VillaJuly 2012 Inter-American Development Bank Department of Research and Chief Economist
  • 2. Mobility and Entrepreneurship in Ecuador: A Pseudo-Panel Approach Xavier Ordeñana* Ramón Villa** * Graduate School of Management, Escuela Superior Politécnica del Litoral ** Centro de Investigaciones Económicas, Escuela Superior Politécnica del Litoral Inter-American Development Bank 2012
  • 3. Cataloging-in-Publication data provided by theInter-American Development BankFelipe Herrera LibraryOrdeñana, Xavier. Mobility and entrepreneurship in Ecuador: a pseudo-panel approach / Xavier Ordeñana, Ramón Villa. p. cm. (IDB working paper series ; 319) Includes bibliographical references. 1. Entrepreneurship—Ecuador. 2. Social mobility—Latin America. I. Villa, Ramón. II. Inter-AmericanDevelopment Bank. Research Dept. III. Title. IV. Series.http://www.iadb.orgDocuments published in the IDB working paper series are of the highest academic and editorial quality.All have been peer reviewed by recognized experts in their field and professionally edited. Theinformation and opinions presented in these publications are entirely those of the author(s), and noendorsement by the Inter-American Development Bank, its Board of Executive Directors, or the countriesthey represent is expressed or implied.This paper may be reproduced with prior written consent of the author.Corresponding author: Xavier Ordeñana (email: xordenan@espol.edu.ec)
  • 4. Abstract 1 Does entrepreneurship contribute to improving social mobility in Ecuador? This paper constructs a pseudo-panel to analyze the dynamic effect of entrepreneurship on Ecuadorian household incomes during the period 2002-2010. Using three estimation scenarios, the paper finds a significant level of unconditional mobility and an important effect of entrepreneurship (conditional mobility). JEL Classification: J16, L26, M13 Keywords: Mobility, Pseudo-panel, Entrepreneurship, Ecuador1 This paper is part of the research project “Strengthening Mobility and Entrepreneurship: A Case for The MiddleClasses” financed by the Inter-American Development Bank (IDB) Research Department. The authors thank HugoÑopo, Virginia Lasio, Gustavo Solorzano, and the participants in the Discussion Seminars for helpful comments. 1
  • 5. 1. IntroductionThere seems to be a consensus among policymakers in Latin America that promotingentrepreneurship is a way to achieve economic development. Different programs around theregion, such as Emprende Ecuador and Start-Up Chile, exemplify this idea. However, theeconomic effect of policies that promote entrepreneurship at the country level is still unclear. In countries like Ecuador, where this study is focused, about one in five people isengaged in entrepreneurial activities, according to the Global Entrepreneurship Monitor EcuadorReport 2010. However, most entrepreneurial activity is highly ineffective at creating jobs; infact, 98 percent of entrepreneurs created fewer than five jobs. Shane (2009) suggests that theseactivities are not contributing to economic growth and thus should not be promoted by thegovernment. However, Amorós and Cristi (2010) find a positive effect on poverty reduction,which remains an important issue in Latin America, particularly in Ecuador. This paper focuses on the effect of entrepreneurship on one economic variable: socialmobility. Is there evidence that entrepreneurship increases a person’s relative income? In order todetermine whether such a correlation exists, we studied the evolution of household income overtime, using panel data. Unfortunately, in Ecuador, attempts to build rotating panels have onlyrecently begun to be undertaken, and we encountered several problems when attempting toconstruct a database using this information. We found many statistical inconsistencies, and onlyshort time spans are available for the construction of the data series. Techniques have beendeveloped to remedy these limitations, and several authors have established that panel data arenot necessary for many commonly estimated dynamic models (Heckman and Rob, 1985; Deaton,1985; and Moffitt, 1990). The pseudo-panel approach, first introduced by Deaton (1985), consists of categorizing“similar” individuals in a number of cohorts, which can be constructed over time, and thentreating the average values of the variables in the cohort as synthetic observations in a pseudo-panel. In Cuesta et al. (2011), a pseudo-panel approach is used to study the differences inmobility across the Latin American region. They find a high level of unconditional mobility andsignificant differences across countries. Canelas (2010) also uses this technique to measurepoverty, inequality, and mobility in Ecuador and finds a decrease in poverty but persistentinequality between 2000 and 2009. 2
  • 6. The rest of the paper is organized as follows: Section 2 presents the data treatment andthe construction of the pseudo-panel. Section 3 presents the models of mobility: unconditionaland conditional. Section 4 presents the results and the analysis, and Section 5 concludes.2. Database Treatment and DocumentationThe main objective of this paper is to describe the linkages between entrepreneurship andmobility. In this section, we first analyze the intragenerational mobility experienced byEcuadorians (unconditional mobility) and approach the potential role of entrepreneurship inimproving mobility (conditional mobility). Given that individual data panels are nonexistent inEcuador, the use of pseudo-panels was required. We start by explaining how we constructed theinstrument.2.1 Database TreatmentThe data used for the construction and estimation of the pseudo-panel were obtained from theNational Employment and Unemployment Survey (ENEMDU for its Spanish acronym) collectedby the National Institute of Statistics and Census (INEC). The census is taken at the nationallevel in November every 10 years, and the results are processed and made public the followingmonth. This data collection methodology has been applied since 2003. In some years, nationalcensus data are presented in May or June. To avoid any seasonal bias due to variations in thelevels of economic activity at different times of the year, only those surveys presented inDecember were used. The database used to estimate the pseudo-panel is constructed as a series of independentcross-sections, one for each period analyzed. To determine the period in which the pseudo panelought to be constructed, it is first necessary to examine the changes made by INEC in themethodology for both the determination of the sample and the estimation of the relevantvariables. There are two important changes made in the last decade in the ENEMDU’smethodology which are so significant that, without taking them in account, any estimation madefor the whole period would suffer from serious bias. The first occurred in December of 2003,before which time only the urban population was analyzed. The definition of what constitutes anurban settlement was also changed in 2003 to include centers with more than 2,000 inhabitantsrather than the 5,000 used earlier. The definitions of several labor variables were also modified, 3
  • 7. and others were included. The second set of changes introduced by INEC in September 2007consisted of several modifications in labor market definitions and classifications, but there wereno significant changes in the variables used for this study (even though income estimationunderwent some changes, which will be discussed below). Because of the loss of information that would result from the construction of a largerpanel (in the time dimension), only the 2003-2010 period was studied. To maintain theconsistency of the data for the period analyzed, special attention was paid to the changes in themethodology, variable classification, and labels used. The method used for the estimation ofindividual income was also changed, and new income criteria were introduced after 2007. Inaddition, even if a survey question was not modified, some of the responses were changed, whichin some cases made it impossible to use the variable for the whole period. To account for all ofthese issues, the income series was constructed using the previous methodology, and all of theother variables included were previously processed to ensure their statistical comparability.Using this methodology, income is calculated as any payment, either monetary or in-kind,received by the individual on a regular basis (daily, weekly, or monthly). Two types of incomesources were considered: income generated by work and income derived from capital,investment, contractual, or non-contractual transfers. A monthly income series was thenconstructed by adding all sources of personal revenue. The ENEMDUs were processed in order to obtain the pertinent variables at householdlevel, as the information relevant for this study on an individual level is collected by INEC. Datamining techniques were used and, with the use of Structured Query Language (SQL), incomeand other covariates were aggregated at the desired level. The first key concept in determining the effect of entrepreneurship on income mobility isthe definition of which households are to be considered entrepreneurs. The focus of the study isthose households that are entrepreneurs by choice rather than entrepreneurs due to lack ofoptions (a group that is difficult to correctly identify considering the scant information available).In order to reduce the probability of error at the moment of classification, only those householdsin which at least one member currently employs other workers are considered entrepreneurs. 4
  • 8. 2.2. Construction of the Pseudo-panelIn order to analyze the dynamic nature of income mobility, household income needs to beobserved over time. Given the absence of panel data, a pseudo-panel must be constructed. Thepseudo-panel approach consists of categorizing “similar” individuals into a number of cohorts,which can be constructed over time, and then treating the average values of the variables in thecohort as synthetic observations in a pseudo-panel. Even though this approach has manylimitations compared to real panel data, it reduces several problems characteristic of real paneldata. First, it greatly diminishes the problem of sample attrition, hence allowing the possibilityfor the construction of larger panels in the time dimension. A second contribution is that, as theobservations are obtained by averaging different observations in a cohort, the possibility ofmeasurement error is greatly reduced (provided the cohorts are adequately constructed). The efficiency and consistency of the estimators depends, among other things, on thecriterion used for the construction of the different cohorts and the asymptotic nature of the dataassumed. Several of the requirements for the consistency of pseudo-panel estimation arediscussed by Verbeek and Nijman (1992), who recommend that the choice of the variables forthe discrimination of the cohorts in the sample should follow three criteria: • The cohorts are chosen such that the unconditional probability of being in a particular cohort is the same for all cohorts. • The variables chosen should be constant over time for each individual, because individuals cannot move from one cohort to another. This maintains the independence of the different cohort observations. • These variables should be observed for all individuals in the sample. This could be remedied by the use of unbalanced panel methods, but due to the short time span of the constructed pseudo-panel, this alternative is not considered. Following these assumptions, cohorts were constructed using gender and date of birth ofthe household head. To determine the number of cohorts to be constructed, first the distributionof the date of birth variable was tested with conventional goodness of fit methods, but notraditional distribution seemed to adjust the data correctly. To ensure relatively similarprobabilities of belonging to a birth cohort, the aggregated data for year of birth for the eight 5
  • 9. periods were divided into deciles. This avoids the possibility that a cohort in a given periodbecomes too small to provide an accurate estimation of its true characteristics. After consideringthe weights of the observations due to sample stratification, the following deciles were obtained: Table 1. Date of Birth (𝒛 𝒊𝟏 ) Cohorts Criterion Date of Birth (𝒛 𝒊𝟏 ) cohorts criterion 𝒛 𝒊𝟏 < 𝟏𝟗𝟑𝟒 𝟏𝟗𝟑𝟒 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟐 𝟏𝟗𝟒𝟐 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟗 𝟏𝟗𝟒𝟗 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟓𝟒 𝟏𝟗𝟓𝟒 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟓𝟖 𝟏𝟗𝟓𝟖 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟔𝟐 𝟏𝟗𝟔𝟐 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟔𝟔 𝟏𝟗𝟔𝟔 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟕𝟏 𝟏𝟗𝟕𝟏 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟕𝟕 𝟏𝟗𝟕𝟕 ≤ 𝒛 𝒊𝟏 Source: Authors’ calculations.head (𝑧 2 ). The conjunction of the two variables (considering the criterion proposed for the date Another criterion used to determine the number of cohorts is the gender of the household 𝑖of birth) results in 20 cohorts per year and 160 synthetic observations in the pseudo-panel. Thedistribution of the observations and their corresponding expanded population values (by the useof sampling weights) in each of the categories explained are presented in the Appendix. Theinclusion of the gender of the household head as a determinant for the conformation of thecohorts makes the probability of belonging to a cohort uneven for most cohorts (as malehousehold heads are more frequently found). As the synthetic observations are calculated withdifferent sample sizes, a systematic heteroskedasticity component is introduced to the error. Themethods to correct this problem are discussed in Gurgand et al. (1997). This problem becomesless relevant in cohorts constructed with a large number of observations, since the variance of themean approaches zero as this number tends to infinity. 6
  • 10. 2.3 Treatment of OutliersThe household income series each year is irregular, as its standard deviation is between 2 and 4times the mean. The asymmetries presented by the data may complicate the estimation of anyinference model applied. This is also maintained at a cohort level, and important differences invariances between each cohort average are observed. These differences make theheteroskedasticity component, described in the previous section, more important. To account forthis problem, data mining techniques are applied to determine and exclude outliers. A median ofabsolute deviations (MAD) approach is used to determine outliers in each cohort as, due to thenature of the series, the median is a better central tendency measure than the mean. Under thisscheme, the following univariant filter was applied to each observation, and observations that �𝑥 𝑐𝑡 − 𝑚𝑒𝑑𝑖𝑎𝑛 𝑐𝑡 𝑥 𝑐𝑡 � 𝑗 𝑗satisfy this restriction are considered outliers: 𝑖 > 102 𝑀𝐴𝐷 𝑐𝑡 As shown in the formula, the method is applied at a cohort level for each period.Approximately 1.2 percent of the sample was determined to be an outlier. In Figures 1 and 2, theaverage income estimated for male and female cohorts is presented before and after the MADtreatment is applied. The red dotted bands denote the 95 percent confidence interval for theestimated means (solid blue line) for the period analyzed. The graph to the left of each verticalblack line corresponds to the estimated cohort mean of household incomes before the univariantfilter is applied, and to the right the results excluding outliers are presented. In observing the two figures, it is noteworthy that the error bands on male cohorts aresmaller than those observed for female cohorts, possibly due to the lower number of observationsin the female cohorts. But even after considering those wider confidence intervals, for most ofthe years studied and most of the birth cohorts, male-headed households experience asignificantly higher income than female-headed households (at a 95 percent confidence level).Without the application of the MAD univariant filter, some birth cohorts exhibit very irregularbehavior, and in the case of female cohorts some of the error bands explode (raising seriousconcerns about the validity of those estimations in a pseudo-panel context). However, once2 Traditionally the tolerance criterion is set at 4.5, but this resulted in the loss of 12 percent of the sample, includingan important percentage of entrepreneurs. 7
  • 11. outliers are excluded, the error bands decrease considerably and the behavior of the income meanbecomes smoother. Figure 1. Average Income Before and After MAD Treatment for Male Cohorts Source: Authors’ calculations. 8
  • 12. Figure 2. Average Income Before and After MAD Treatment for Female Cohorts Source: Authors’ calculations. Additional descriptive statistics regarding the cohorts constructed after the outliertreatment are presented next. For most of the male cohorts, the percentage of households locatedin urban areas is significantly lower than the one presented by female cohorts. This might be dueto a more traditional family life in rural areas, which makes single-parent families, or female-headed households, a less common occurrence. It is also important to note that the number ofentrepreneur households headed by women is significantly lower than those headed by men. Thisis accentuated by the fact that almost half of all female entrepreneur households include amember, different from the household head, who owns a business. 9
  • 13. Table 2. Urban Ratio Male Households Female Households 𝒛 𝒊𝟏 < 𝟏𝟗𝟑𝟒 2003 2004 2005 2006 2007 2008 2009 2010 2003 2004 2005 2006 2007 2008 2009 2010𝟏𝟗𝟑𝟒 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟐 59% 56% 58% 56% 54% 53% 53% 53% 54% 59% 63% 64% 66% 62% 63% 62% 63%𝟏𝟗𝟒𝟐 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟗 64% 61% 55% 56% 61% 60% 60% 59% 68% 67% 62% 63% 65% 67% 66% 71%𝟏𝟗𝟒𝟗 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟓𝟒 66% 64% 62% 61% 61% 61% 59% 58% 71% 74% 72% 73% 71% 72% 72% 72%𝟏𝟗𝟓𝟒 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟓𝟖 70% 67% 65% 66% 66% 68% 63% 63% 75% 75% 79% 79% 77% 77% 74% 76%𝟏𝟗𝟓𝟖 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟔𝟐 69% 70% 67% 68% 67% 68% 67% 66% 81% 81% 80% 77% 80% 75% 74% 73%𝟏𝟗𝟔𝟐 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟔𝟔 68% 68% 70% 71% 67% 69% 63% 66% 78% 80% 78% 76% 83% 84% 78% 79%𝟏𝟗𝟔𝟔 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟕𝟏 66% 69% 68% 73% 68% 67% 67% 66% 72% 76% 78% 79% 78% 76% 77% 77%𝟏𝟗𝟕𝟏 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟕𝟕 67% 67% 68% 66% 67% 66% 66% 66% 77% 76% 78% 82% 79% 78% 81% 80% 𝟏𝟗𝟕𝟕 ≤ 𝒛 𝒊𝟏 69% 70% 69% 68% 67% 70% 68% 76% 73% 80% 74% 77% 71% 82% 82% 71% 69% 71% 75% 70% 70% 73% 73% 84% 84% 86% 77% 84% 82% 86% 83%Source: Authors’ calculations. 10
  • 14. Table 3. Entrepreneurship Ratio Male Households Female Households 𝒛 𝒊𝟏 < 𝟏𝟗𝟑𝟒 2003 2004 2005 2006 2007 2008 2009 2010 2003 2004 2005 2006 2007 2008 2009 2010𝟏𝟗𝟑𝟒 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟐 6% 11% 9% 9% 5% 6% 4% 3% 3% 3% 2% 4% 2% 3% 2% 2%𝟏𝟗𝟒𝟐 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟗 9% 13% 11% 11% 8% 9% 7% 5% 5% 8% 5% 7% 5% 5% 3% 2%𝟏𝟗𝟒𝟗 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟓𝟒 9% 13% 13% 13% 11% 13% 7% 7% 4% 10% 5% 6% 5% 5% 3% 4%𝟏𝟗𝟓𝟒 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟓𝟖 9% 12% 12% 14% 12% 11% 9% 7% 7% 7% 7% 10% 6% 6% 4% 3%𝟏𝟗𝟓𝟖 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟔𝟐 9% 15% 12% 16% 8% 11% 10% 8% 7% 7% 5% 7% 6% 5% 6% 3%𝟏𝟗𝟔𝟐 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟔𝟔 8% 13% 12% 12% 12% 10% 10% 7% 5% 4% 5% 5% 3% 5% 5% 4%𝟏𝟗𝟔𝟔 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟕𝟏 8% 12% 10% 13% 10% 11% 7% 8% 3% 7% 6% 6% 5% 6% 3% 1%𝟏𝟗𝟕𝟏 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟕𝟕 5% 10% 10% 10% 10% 10% 8% 9% 5% 6% 4% 6% 6% 3% 2% 3% 𝟏𝟗𝟕𝟕 ≤ 𝒛 𝒊𝟏 6% 9% 8% 9% 9% 8% 6% 5% 3% 5% 4% 7% 3% 4% 1% 3% 5% 6% 5% 6% 3% 4% 4% 2% 3% 3% 2% 3% 2% 5% 1% 1%Source: Authors’ calculations. 11
  • 15. Table 4. Percentage of Entrepreneurs who are Household Heads Male-headed Households Female-headed Households 2003 2004 2005 2006 2007 2008 2009 2010 2003 2004 2005 2006 2007 2008 2009 2010 𝒛 𝒊𝟏 < 𝟏𝟗𝟑𝟒𝟏𝟗𝟑𝟒 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟐 76% 88% 88% 87% 72% 77% 70% 77% 26% 35% 78% 69% 76% 71% 72% 76% 62% 68% 37% 52% 30% 49% 58% 40% 21% 42%𝟏𝟗𝟒𝟐 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟒𝟗 73% 82% 85% 79% 80% 80% 82% 69% 53% 66% 34% 52% 58% 45% 49% 39%𝟏𝟗𝟒𝟗 ≤ 𝒛 𝒊𝟏 < 𝟏𝟗𝟓𝟒 78% 81% 78% 82% 86% 79% 87% 80% 84% 74% 70% 50% 63% 80% 56% 59%𝟏𝟗𝟓𝟒 ≤ 𝒛 𝒊𝟏 &
  • Recommended
    View more...
    We Need Your Support
    Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

    Thanks to everyone for your continued support.

    No, Thanks
    SAVE OUR EARTH

    We need your sign to support Project to invent "SMART AND CONTROLLABLE REFLECTIVE BALLOONS" to cover the Sun and Save Our Earth.

    More details...

    Sign Now!

    We are very appreciated for your Prompt Action!

    x