Monday, October 16, 2017

gender, managerial behaviors and leadership

managerial behaviors and leadership traits of men and women
the private sector (Harlan and Weiss 1982), state legislatures (Cammisa and Reingold 2004), state agencies (Bowling et al. 2006; Brudney, Hebert, and Wright 2000; Bullard and Wright 1993),
local governments (Fox and Schuhmann 1999), school districts (Keiser et al. 2002; Meier,
Mastracci, and Wilson 2006; Meier, O’Toole, and Goerdel 2006; Meier and Wilkins 2002),
and law enforcement agencies (Meier and Nicholson-Crotty 2006).

gender differences in organizational values, management styles, policy preferences, and leadership strategies (e.g., see Burns 1979; Gilligan 1982; Hatcher 2003; Kathlene 1989, 1995; Rosener 1990, 1995; Thomas 1994).

Women offer notable emotional labor to an organization (Bellas 1999; Guy and Newman 2004; Meier, Mastracci, and Wilson 2006), have different motivations for work in the public sector (DeHart-Davis, Marlowe, and Pandey 2006), are more democratic (Bass and Avolio 1993), and are ‘‘less hierarchical and more participatory, interactional, flexible, consociational, and multifaceted’’ (Meier, O’Toole, and Goerdel 2006, 25).

In a study of female versus male accountants, Burke and Collins (2000) found that women were more likely to report using an interactive style of management, which resulted in more effective coaching, development, and communication.

Applebaum, Audet, and Miller (2003) observed that women’s leadership styles differ from men’s and noted that both genders can learn from each other. Eagly, Karau, and Johnson (1992) found that although female principals scored higher than male principals on measures of task-oriented leadership style, more similarity existed on measures of interpersonally oriented style. The
most significant difference was related to the tendency to lead democratically or autocratically,
with female principals adopting a more democratic (or participative) style than their
male counterparts. Although Mandell and Pherwani (2003) did not note significant differences
in the transformational leadership scores of male and female managers, they did find
significant differences between the genders with respect to emotional intelligence.

whether passive representation of a subset of the population (i.e., women) leads
to policy outcomes more in line with their specific needs and preferences (Pitkin 1967).
Within this vein, there are numerous findings and conclusions (Dolan and Rosenbloom
2003; Kingsley 1944; Krislov and Rosenbloom 1981; Meier and Bohte 2001; Miller, Kerr,
and Reid 1999; Pitkin 1967; Riccucci and Meyers 2004; Riccucci and Saidel 1997; Selden
1997; Selden, Brudney, and Kellough 1998; Sigelman 1976).


Jacobson, W. S., Palus, C. K., & Bowling, C. J. (2010). A Woman's Touch? Gendered Management and Performance in State Administration. Journal of Public Administration Research and Theory, 20(2), 477-504. doi: 10.1093/jopart/mup017

Sunday, October 15, 2017

警政統計

https://ba.npa.gov.tw/npa/stmain.jsp?sys=100

家暴案件, domestic violence

https://ba.npa.gov.tw/npa/stmain.jsp?sys=100

http://iiqsw.mohw.gov.tw/InteractiveIntro.aspx?TID=F42F97B134F60D75

入, 出境, 大陸人士

http://statis.moi.gov.tw/micst/stmain.jsp?sys=100

http://statis.moi.gov.tw/micst/stmain.jsp?sys=100

刑事案件

http://statis.moi.gov.tw/micst/stmain.jsp?sys=100

https://ba.npa.gov.tw/npa/stmain.jsp?sys=100

原住民人數

http://statis.moi.gov.tw/micst/stmain.jsp?sys=100

外籍, 大陸配偶

http://statis.moi.gov.tw/micst/stmain.jsp?sys=100

variable transformation

Regression: Transforming Variables

https://stats.stackexchange.com/questions/4831/regression-transforming-variables

log transformation vs square root transformation, Can I do both?

 Y=X1+X2+X3+X4Y=X1+X2+X3+X4
Can I have the log on Y and square root on X1 and square root on X2, at the same time?
that is,
logY=SQX1+SQX2+X3+X4


Yes; you can do this and still achieve a valid model.
Interpretation, however, is complicated by this transformation. Your model then looks like
log(E(Yi))=β0+β1Xi1+β2Xi2+β3Xi3+β4Xi4

This means that e.g. a doubling of X1 is associated with an expected increase of Y by a factor exp(β12), all other factors kept equal. For a unit increase in X1 there is no easy interpretation; that depends on the current value of X1.
A unit increase of X3 is associated with an expected increase of Y by a factor exp(β3). So, interpretation is easier without transforming the variables. However, if square root transformation improves the fit or is necessary in some other way, then it is mathematically perfectly correct.
https://stats.stackexchange.com/questions/306177/log-transformation-vs-square-root-transformation-can-i-do-both