Agriculture Reference
In-Depth Information
is clearly defined, (c) how the area of the study is
clearly stated and restricted, (d) how the methods
and collection of information specific to the
objective of the study are clearly understood or
executed, (e) how best the efforts are taken to
remove the bias from the information collected,
(f) how best the statistical tools required for the
purpose are adopted, and (g) how best the inter-
pretation has been made only in the light of the
observations and objective of the study. Too
much generalization of the results of the study
must be avoided.
Table 4.1
Before and after research design
Group
Before
After
Y
i
0
Treatment
Y
i
X
i
0
Control
X
i
the
X
i
s for the targ
et
ed population
and tests the hypothesis H
0
:
Y
i
s and
D ¼
0 using an
appropriate test statistic.
2. After Only with Control Design
In this type of experimentation, in addition to
a treatment group, there will be one control
group, which will not be treated. The level of
phenomenon will be measured on both the
treatment group and control group before and
after treatment. The impact of the treatment
will be studied against the control group. Let
X
ij
0
be the observations of the
4.2.3.2 Research Designs for
Experimental Studies
In an experimental type of studies, a researcher
wants to test the hypothesis with respect
to the populations through experimentations.
Experiments are designed and are conducted to
get proper solutions to the problems at hand. The
design for experimental studies has its origin in
agricultural research. Prof. R.A. Fisher is the
pioneer in this field of study. Experimental
design may be of two types: (a)
th individuals
on the particular phenomenon for the control
group after treatment. Similarly
i
Y
i
0
is the value
of the phenomenon of the
th individual of the
treatment group after the treatments. Thus, we
i
P
n
i¼
1
Y
i
0
X
i
0
1
n
have
δ
¼
ð
Þ
.
informal
and
formal
(b)
.
The
re
searcher would be interested in test-
ing H
o
:
δ
¼
0 using an appropriate test statistic.
3. Before and After with Control Design
In this type of research design, the researcher
is interested in comparing the
Informal Research Designs
Informal research designs
are based on or
associated with a less sophisticated form of anal-
ysis. Informal experimental design can be of
three categories: (1) before and after without a
control design, (2) after only with a control
design, and (3) before and after with a control
design.
1. Before and After Without Control Design
In this type of design, variables are measured
before and after the introduction of
treatments. The impact of the treatment is
measured by taking the differences in the
measurements of a particular phenomenon at
two different points of time. Hypothesis is
tested whether the treatment has any effect
on the level of phenomenon or not. Thus,
in the
level of phenomenon for two groups of peo-
ple, that is, treatment group and control group
(Table
4.1
).
change
P
n
i¼
1
Y
i
0
Y
i
ð
Þ
1
n
δ
¼
;observations are recorded
P
n
1
X
i
0
X
i
ð
Þ
i¼
in both control and treatment groups before and
a
fter treatment. The researcher tests the H
o
:
δ
¼
0 using the appropriate test statistic.
Formal Experimental Design
Compared to informal experimental design, in
the formal experimental design, the researcher
has more control over the experiments. As such
more sophisticated statistical tools would be used
for the analysis of the data from the experiments.
P
n
i¼
1
ðY
i
X
i
Þ
1
n
D ¼
, where
Y
ij
and
X
i
are
values of the phenomenon after and before
the treatment. The experimenter measures
