1. Google
vs. PsycINFO:
a.
Google yields more results and a greater variety in its types of
sources along with a higher rate of relevancy but less currency.
b.
PsycINFO tends to be more
specific than Google which may return many irrelevant results. For example,
searching PsycINFO for tension will find only
publications related to psychological and biological tension, but searching
Google for tension will obtain results for mechanical and physical tension as
well, which may not be relevant for your research.
c.
With PsycINFO, there are many more
metadata fields than Google Scholar. In the case of Google Scholar, much of
this metadata is not as easily available as in PsycINFO
(e.g. the latest revisions and exact descriptors). The related articles feature
of Google does not have enough depth to satisfy a scholar or professional.
d.
Google is very user friendly, but it is less in-depth than PsycINFO.
e.
Google is good at finding information quickly. PsycINFO requires more effort as it has more data and
metadata.
2. Induction:
Induction is employed, for example, in the following argument:
·
Every star we know of is spherical.
·
All stars must be spherical in order to exist.
Inductive reasoning permits the possibility that the conclusion is
false, even where all of the premises are true For
example:
·
All of the people we have seen are less than 8 feet tall.
·
All people are less than 8 feet tall.
Deduction is employed, for example, in the following argument:
·
All stars are spherical
·
We have found an object in outer space that is not spherical
·
Therefore, what we have found is not a star.
3. Between-subjects
design:
a.
A “between-subjects” experiment is where you use two (or more)
different groups - e.g. attitudes between those who have seen a TV program and
those who haven't. The dependent variable is the attitude of the people, and
the independent variable is whether they’ve seen the program or not.
b.
Within subjects design is where you use the same subjects twice.
e.g. measure people's attitude to nuclear power before
they see a documentary on the Chernobyl disaster and then after. It's
"within subjects" because you are measuring the change in the
variable among the same subjects. The dependent variable is the attitude of the
people, and the independent variable is whether they’ve seen the documentary or
not.
4. 2x2
Factorial Design: Suppose you want to analyze the total power used by each of two
different engines, A and B, running at each of two different speeds, 4000 or
6000 RPM. The 2x2 factorial experiment would consist
of four experimental units: engine A at 4000 RPM, engine B at 4000 RPM, engine
A at 6000 RPM, and engine B at 6000 RPM. Each combination of a single level
selected from every factor is present once.
5. Stratified
vs. proportionate stratified sampling: Stratified sampling is
the process of separating members of a population into homogeneous subgroups
prior to sampling. The strata should be mutually exclusive, i.e. each member of
the population must be assigned to one and only one stratum. The strata should
also be collectively exhaustive: no member should be left out. Proportionate
allocation uses a sampling fraction in each of the strata that is proportional
to that of the total population. For instance, if the population consists of 60%
in the plant stratum and 40% in the animal stratum, then the relative size of
the two samples (three plants, two animals) should reflect this proportion.