Determining the Number of Factors in Approximate Factor Models
Summary (3 min read)
Introduction
- The growing number of studies focused on child and family migration has brought the phenomena of living life across international borders increased attention in recent years (Parrenas 2005; Ní Laoire et al.
- Free movement of EU migrant workers and their families has different characteristics than asylum seeker and refugee migrations to and within the EU, in which the impacts of family separation are well documented (see for example Spicer 2008, Szilassy and Arendas 2007).
- There is a need for more in-depth study on the ways in which children may be involved in migration decisionmaking in their families, the processes of family separation they experience and the ways in which they manage their transnational lives.
- Children in group two experienced separation from one or both parents and/or siblings until they migrated themselves.
Migrant Worker Families in Europe
- In 2004, in an action that paralleled the actions of Sweden, the United Kingdom and Ireland did not place restrictions on migration from countries that acceded to the EU that year.
- Children from Poland and other European countries made up a sizable proportion of migrants to Scotland and Ireland (see, for example, the data from the Scottish Government, Pupil Census – Supplementary Data 2012) and from the national census 2011 in Ireland (Central Statistics Office – CSO 2012).
- 88) demonstrate, however, that migrant parents with children may measure ‘success’ in the new society in terms of how well the child is doing in school, learning the new language, and making new friends, also known as Adams and Shambleau (2006.
- What the small body of research focused on children’s experiences of intra-EU migration as part of migrant worker families suggests is that there are multiple ways in which children manage and cope with processes of intra-EU family migration (see Darmody, Tyrrell and Song 2011; Devine 2011; Ní Laoire et al.
Research Design
- The data that are analysed and discussed in this paper were gathered as part of two studies on intra-EU migration that were conducted independently.
- The data from the Scotland study that are discussed in this article were collected between 2008 and 2010 during fieldwork with 65 members of Polish migrant families in Scotland (41 children and 24 adults).
- Interviews and discussions between the researcher and children took place in English2 although children often communicated in Polish with each other in group activities or when carrying out individual tasks in group contexts.
- A distinctive feature of both projects was to pay particular attention to the views of children (Christiansen and James 2000) and children’s competence as research participants was recognised (Morrow 2008).
- The authors recognise that this is a limitation of the study.
Migration Decision-Making in EU Migrant Worker Families
- 5 The methods employed depended on a number of factors: children’s choice, children’s age and understanding, the research location, group or individual activity.
- Accession to the EU has brought many employment opportunities and free movement for the people of Poland and other new EU countries.
- This reflects the broader positioning of children within much research on family migration until recently (White et al. 2011) and the lack of acknowledgement that children may participate in making migration decisions in some circumstances (Bushin 2009).
- A negative aspect that sometimes follows children’s lack of involvement in decision- making is that children find hard to understand the choices of their parents, especially if they are very young (Bonizzoni 2009).
- Philip (male, age 15, Ireland study) said that his parents, particularly his mother, were keen to remain living in Ireland but they had retained a property in their home city in Poland in case his father had to return to work there.
Processes of Step-Migration and Separation in Intra-EU Migrant Worker Families
- Much of the research in Europe on transnational families has focused on those from outside the EU (Bryceson and Vuorela, 2002).
- Many participating children have also experienced separation at the time of their own migration, leaving grandparents, uncles, cousins and other close relatives and friends behind.
- Vicky (female, age 11, Scotland study) wanted to come to Scotland: ‘I missed my dad [when he lived in Scotland and she lived in Poland], he was at home maybe once a year.
- In Poland I have friends but maybe I do not have them anymore.’.
- Children also reflected on these friendships and compared them to friendships ‘back home’.
Living Transnational Family Lives
- For both children and parents, relatives and/or friends in Poland frequently provided an important source of emotional support through telephone/internet chats and emails.
- Robert is very attached to his grandparents in Poland as he lived three years with them after his mother migrated for work to Scotland.
- Maintaining transnational connections in some migrant families allows them to provide not only emotional support from a distance but also practical support, including various forms of childcare.
- After three years, my younger son came to join me.
- I take care of the children and bring them to school and back, do homework with them.
Conclusion
- Migratory processes and experiences of intra-EU migrant worker families who recently migrated from Poland to Scotland and Ireland.the authors.
- By considering family migration to be a process or set of varying processes rather than a singular event (after Halfacree and Boyle 1993), the nuances of intraEU family migration decision-making, step-migration and separation can be revealed.
- The studies show that many migrant children seemed to function well despite periods of separation from parents and/or other family members.
- The authors studies confirm White’s (2011) argument that emotional reasons can prevail over apparent economic rationality.
Did you find this useful? Give us your feedback
Citations
6,169 citations
6,022 citations
4,189 citations
3,170 citations
2,906 citations
References
9,693 citations
7,169 citations
6,763 citations
1,832 citations
Related Papers (5)
Frequently Asked Questions (14)
Q2. What future works have the authors mentioned in the paper "Determining the number of factors in approximate factor models" ?
Many issues in factor analysis await further research. But using Theorem 1, it maybe possible to obtain these limiting distributions. It can be shown that ŷT+1|T is not only a consistent but a√ T consistent estimator of yT+1, conditional on the information up to time T ( provided that N is of no smaller order of magnitude than T ). Stock and Watson ( 1998 ) suggest how dynamics can be introduced into factor models when both N and T are large, although their empirical applications assume a static factor structure.
Q3. What is the drawback of the approach?
The drawback of the approach is that, because the number of parameters increases with N ,3 computational difficulties make it necessary to abandoninformation on many series even though they are available.
Q4. What are the two main assumptions that are crucial for the validity of the test?
because their test is based on a comparison of variances over different time periods, covariance stationarity and homoskedasticity are not only technical assumptions, but are crucial for the validity of their test.
Q5. What is the main advantage of these three panel information criteria?
The main advantage of these three panel information criteria (ICp) is that they do not depend on the choice of kmax through σ̂2, which could be desirable in practice.
Q6. What is the test for the number of factors in asset returns?
For large dimensional panels, Connor and Korajczyk (1993) developed a test for the number of factors in asset returns, but their test is derived under sequential limit asymptotics, i.e., N converges to infinity with a fixed T and then T converges to infinity.
Q7. What is the significance of the likelihood ratio test?
A likelihood ratio test can also, in theory, be used to select the number of factors if, in addition, normality of et is assumed.
Q8. How can the forecast mean squared error of a large number of macroeconomic variables be reduced?
More recently, Stock and Watson (1999) showed that the forecast mean squared error of a large number of macroeconomic variables can be reduced by including diffusion indexes, or factors, in structural as well as non-structural forecasting models.
Q9. What is the way to determine the number of factors in a series?
Assuming N, T → ∞ with √ N/T → ∞, Stock and Watson (1998) showed that a modification tothe BIC can be used to select the number of factors optimal for forecasting a single series.
Q10. What is the idiosyncratic component of returns?
In this case, Xit represents the return of asset i at time t, Ft represents the vector of factor returns and eit is the idiosyncratic component of returns.
Q11. What is the implication of the proof of the theorem 2?
However the proof of Theorem 2 mainly uses the fact that ̂Ft satisfies Theorem 1, and does not rely on the principle components per se.
Q12. What is the way to determine the number of factors in a dynamic setting?
Stock and Watson (1998) suggest how dynamics can be introduced into factor models when both N and T are large, although their empirical applications assume a static factor structure.
Q13. What is the simplest way to estimate the rank of a demand system?
when J is large, the theory developed in this paper still provides a consistent estimation of the rank of the demand system and without the need for nonparametric estimation of theG(·) functions.
Q14. What is the simplest way to determine the number of factors?
The shifting interesttowards use of multifactor models inevitably calls for a formal procedure to determine the number of factors.