Information Technology Reference
In-Depth Information
A.6 Hunter [31]
Statistical Replication. For statistical replications as perfectly replicated studies:
1. All studies measure the independent variable in exactly the same way.
2. All studies measure the dependent variable in exactly the same way.
3. All studies use exactly the same procedure.
4. All studies draw samples from the same population.
Scientific Replication. For scientific replications for simple causal studies:
1. All studies measure the same independent variable X.
2. All studies measure the same dependent variable Y.
3. All studies use essentially the same procedure.
4. All studies should sample from populations that are equivalent in terms
of the study question and hence the study outcome. The difference is that
statistical replications assume that the word “same” means identical, while
scientists interpret the word “same” to mean equivalent.
Conceptual Replication. This replication verifies one of the hypotheses that were
not tested in the original study. The researcher of the original study defines con-
trol groups to test the most obvious alternative hypotheses against administrative
details that are thought to be irrelevant. Any treatment, intervention or manipu-
lation is a set of administrative procedures, which are mostly intrinsic to the active
ingredient of the treatment. These replications examine whether the administra-
tive procedures influence the treatments as reflected in the dependent variable.
A.7 Van IJzendoorn [63]
Complete Secondary Analysis. It is a kind of replication in which all parame-
ters except the researcher and the method of data analysis are kept constant.
Secondary analysis also is one of the most inexpensive and ecient types of
replication, because it is based on existing data sets. One of the main barriers
to secondary replication is, however, the accessibility of the original data sets.
The complete secondary analysis may include recoding of the original raw data.
In this replication, there are two phases of processing the raw data involved: the
coding and analyzing of the data.
Restricted Secondary Analysis. In this type, the coding system is not changed but
only the methods of analyzing the data, to see whether the original results survive
statistical criticism or the application of refined methods of statistical analysis.
Exact Replication. A replication will be called “exact” if it is essentially similar
to the original study. This replication is applied to (dis)confirm the doubts, and
to check the assumptions of the varied replications. Many scientists feel that exact
replications may be carried out, but usually are irrelevant for scientific progress.
Varied Replication. Replications should be carried out in which new data un-
der different conditions are being collected. From the start, the original study
will be “trusted” so much that rather significant variations in the design will be
 
Search WWH ::




Custom Search