02.06.2014 Views

Evaluation of the Australian Wage Subsidy Special Youth ...

Evaluation of the Australian Wage Subsidy Special Youth ...

Evaluation of the Australian Wage Subsidy Special Youth ...

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

94<br />

3: Study 1 Replication<br />

In this section, <strong>the</strong> first aim is to first replicate <strong>the</strong> bivariate probit analysis <strong>of</strong> SYETP as<br />

reported by Richardson (1998). The key value <strong>of</strong> <strong>the</strong> replication is to validate <strong>the</strong> results,<br />

and to ensure that <strong>the</strong> later analyses are carried out using comparable data. The<br />

Richardson (1998) analysis was <strong>the</strong> most sophisticated <strong>of</strong> <strong>the</strong> SYETP analyses, as shown<br />

in <strong>the</strong> earlier review. This study has selected to build upon Richardson (1998) for this<br />

reason.<br />

Firstly, <strong>the</strong> motivation for replication is presented. Then, <strong>the</strong> methods needed to carry out<br />

<strong>the</strong> replication are described. The data are briefly detailed. Finally, <strong>the</strong> results <strong>of</strong> <strong>the</strong><br />

replication are shown and discussed.<br />

3.1 Motivation for replication<br />

A number <strong>of</strong> papers have discussed <strong>the</strong> importance <strong>of</strong> replication. King (1995, 2002) has<br />

been one <strong>of</strong> <strong>the</strong> more vocal in recently maintaining <strong>the</strong> importance <strong>of</strong> <strong>the</strong> scientific step<br />

<strong>of</strong> replication. However, earlier work by Dewald, Thursby and Anderson (1986) also<br />

presented strong evidence <strong>of</strong> <strong>the</strong> value <strong>of</strong> replication. King (2002) p1 describes <strong>the</strong><br />

‘Replication Standard’:<br />

“Sufficient information exists with which to understand, evaluate and build<br />

upon a prior work if a third party can replicate <strong>the</strong> results without any<br />

additional information from <strong>the</strong> author.”<br />

Empirical evidence that meets <strong>the</strong> replication standard allows <strong>the</strong> conclusions <strong>of</strong> <strong>the</strong> work<br />

to be maintained and built upon in accordance with <strong>the</strong> scientific method. King (1995)<br />

argues convincingly that “…Without complete information about where <strong>the</strong> data have<br />

come from and how we measured <strong>the</strong> real world and abstracted from it, we cannot truly<br />

understand a set <strong>of</strong> empirical results…” (King (1995): 445). King (1995) p 445 also<br />

suggests that replication is a prerequisite to fur<strong>the</strong>r development and is <strong>the</strong> most<br />

productive method <strong>of</strong> building on existing research, by “…following <strong>the</strong> precise path

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!