Beruflich Dokumente
Kultur Dokumente
Statistics serve two primary purposes. The first is to summarize and describe
a set of data from a research study. The second is to provide an objective basis for
drawing conclusions from the data collected in a research study. Statistics is also the
art and science of collecting, analyzing, presenting, and interpreting data.
If the sample have drawn from the population does not represent the
population, the results cannot be regarded as correct. Sample doesn’t represent the
population is also called Sampling Bias. It is undesirable, but often unavoidable.
Sampling bias is mostly classified as a subtype of selection bias, sometimes
specifically termed sample selection bias, but some classify it as a separate type of
bias. A distinction, albeit not universally accepted, of sampling bias is that it
undermines the external validity of a test (the ability of its results to be generalized
to the entire population), while selection bias mainly addresses internal validity for
differences or similarities found in the sample at hand. In this sense, errors
occurring in the process of gathering the sample or cohort cause sampling bias,
while errors in any process thereafter cause selection bias.
5. Give the uses of statistics and explain each use briefly. Do you think that any
science will develop without tests of the hypotheses? Support your answer.
a. It can give a precise description of data. It enables us to make precise statements
or judgments about averages, variability and relationship. Ex. Is when you
describe the academic performance of a group of pupils according to the
computed mean, standard deviation, and correction with another factor.
b. It can predict the behavior of individuals. In school, the grades of students can be
predicted through aptitude test. In industry, the work performance is usually
predicted by an aptitude test related to that particular type of work. Other sets of
data can be used to predict the success of a teacher in his work. To measure the
success of individuals, we may have to compute measures like the mean,
standard scores, percentiles, statins and other statistical methods.
c. It can be used to test a hypothesis. We can determine whether a variable is
related or not to another variable through a test of inference such as in
correction. Other statistical measures we can apply for inferential purposes are
the t-test, chi-square test, F-test, and others. It is wise to remember that your
choice of the statistics to use in testing hypothesis depends upon the nature of
your data. This includes the scale of measurement used such as nominal, ordinal,
internal, and ratio; and its distribution whether normally distributed or not; and
other considerations such as your purpose.