Page 271 - Area 9 - Relevant Document

18

4.5. Outline the statistical analyses to be performed and the
pertinent summary tables.
4.6. Statement of costs to conduct the proposed experiment.
5. Examination of possible outcomes and reference back to
6. The reasons for the inquiry to be sure that the experiment provides
the required information to an adequate extent.
7. Consideration of the possible results from the point of view of the
statistical procedures, which will be applied to them, to ensure that
the conditions necessary for these procedures to be valid are
satisfied.
8. If steps 3, 5 and 6 are satisfactory, perform the experiment.
9. Apply the proposed statistical procedures to the experimental
results.
10. Draw conclusions with measures of the reliability of estimates of
any quantities that are evaluated, careful consideration being given
to validity of the conclusions for the population of inference to which
they are apply.
11. Prepare a complete, correct and readable report of the
experiment.
12. Evaluate the entire investigation particularly in light of other
investigations on the same or similar problem.

Basic Principles in Designing an Experiment

1. Replication of treatment is an independent observation of the treatment
and therefore the Replication of treatment is an independent
observation of the treatment and therefore the replications of a
treatment must involve the same number of experimental units to
receive the treatment. Most often, researches use duplicate or split
samples to generate observations and call them replicates when
actually they are sub samples or repeated measures. For instance in
agronomy, a researcher planted all the seeds of a given variety of plants
in a row, each row planted with a different variety. Then the rows were
partitioned into a part and this part were called” replication” when in
fact they are not. Actually, one of the functions of replication is to have
an estimate of the experimental error. Experimental error or error of
variances describes the failure of two identically treated experimental
units to yield identical results. It is a measure of variation that exists
among observation on experimental units treated alike. Variations may
come from the inherent variability, which exists, in the experimental
unit to which treatment is applied or failure to conduct the experiment
uniformly.

2. Randomization of treatments is the procedure of allocating treatments
so that each of the experimental unit will have the chance of receiving
any of the treatments. This is one technique that prevents the
introduction of systematic bias into the experiment. If the researcher