UOW Library: Research Proposal on Computer Usage on Ground Floor

This research proposal investigates the usage of computers on the ground floor of the UOW library to determine whether there is a need for additional computer resources. The study aims to assess the current computer availability and utilization by students, considering the university's belief that 70% of computers are occupied. The methodology involves collecting data on computer usage at various times throughout the day using a 24-hour system. The data will be analyzed using a one-sample t-test to compare the sample mean of occupied computers against the university's claim. The proposal outlines the assumptions required for the t-test, including continuous data, Gaussian distribution, and simple random sampling. The analysis will be conducted using R-studio, and the significance level will be set at 5%. The findings will inform decisions about resource allocation and benefit the student community by ensuring adequate computer access. The proposal also defines key statistical terms such as parameter, statistic, hypothesis, p-value, and SRS.

Research proposal:
Title: Research on Usage of Computers on the ground floor in UOW library to verify whether
more computers are needed or not.
Author:
Introduction:
Now a days every library has computers as they help to keep track of student records and e-
books are easily available where as to find a hardcopy of a book one has to spend time or it may
happen that a particular book’s 3 copies are available in the library but all of them are issued in
such cases e-books are very much helpful and to use e-books one need to use computer. It
ensures to achieve active learning, developing academic and personal goals set by
themselves.Libraries give public access to personal computers. The library’s public access
computers are equipped with basic productivity or educational software. University libraries
gives the students access to the computers on the basis of who come first.
In order to check whether the students are getting proper facilities and whether they are able to
use the facilities properly. In such cases we find out the means which give an idea about the
whole population, as mean is based on all observation. We check whether the mean is supporting
our belief or not.
Relevant paper Review:
1: “Skaik Y., “The bread and butter of statistical analysis “t-test”: Uses and misuses”, Pak J
Med Sci 2015;31(6):1558-1559”
In the above mentioned article, one sample t-test is taken as “the bread and butter” of statistical
analysis . It is true in many aspects. Three types of the t-test, which are used for comparing a
single population mean or two population means are discussed here. Also under which specific
conditions and criteria. each t-test can be used is also mentioned. Here we get, One sample t-test
is used to compare a single mean to a fixed number or gold standard.
It is also mentioned that if the sample size is reasonable (at least 15), the one-sample t-test should
be avoided if there are presence of outliers. So we should take care of this.
2: “ Skaik Y., “The panacea statistical toolbox of a biomedical peer reviewer”. Pak J Med Sci
2015;31(4):999-1001 ”
From the above mentioned paper we gain knowledge about the p-value. It is the predicted
probability if H0(prior belief) is true. It is used to assess the statistical significance.

Research problem:
Our research problem is focused on analyzing the number of computers which have been
occupied on the ground floor in the UOW library.
Aim of the Research:
Suppose the university authority wants to know whether there is need of more computers on the
ground floor in the UOW library . The university authority takes a decision that a test will be
done and the use of computers would be analyzed to check whether there is actual need of more
computers on the ground floor in the UOW library.
The university authority’s belief is that 70% of the computers are occupied in the library and
suppose it is claimed by the officials that more than 70% of the computers are occupied in the
library.
The methodology and procedure of the study:
Here we do not take time variable into consideration though we report the time along with the
data . We collect the data randomly in the 24-hour system.
For our research problem we will collect data as discussed above on the number of computers
that are busy during different times on the ground floor in the UOW library. Using the data at
hand we will analyze it properly by hypothesis testing. We will test the belief of the University
officials (Null hypothesis) against the claim of the library officials.
Here as we will collect data samples so we will have the sample sd(standard dev.) and the sample
mean number of computers that are busy on an average. We will then conduct an appropriate
one-sample-t test of mean to come to a decision.
Here we take our null hypothesis as simple hypothesis and alternative hypothesis as more than
type.
As here we have information about the sample standard deviation hence we will use t test
otherwise if we had information about the population standard deviation then we should have
used one sample z test.
Here from the sample we will find out the sample mean and sample standard deviation and use it
to find out the statistic associated with the test. Then we will find out the p-value. Here suppose
we obtain the value of statistic obtained from the values of our sample is t and the Statistic is T.
Then p-value=P(T>t) [As, our alternative hypothesis is greater than type]
Now if the p-value<α=0.05 then we say that ,we support the claim at 5% level of significance in
the light of the given data.
Here we assume the following as these assumptions are required before applying the appropriate
t test mentioned in the research proposal.
Assumptions :
1. The data are continuous .

2. The data must follow the Gaussian probability distribution.
3. The collected sample from the population is SRS i.e. Simple Random Sample from its
population. Each observation of the population has an equal chance of being selected in the
sample.
For the analysis purpose we shall use R-studio to conduct the one sample “t-test” of mean. We
will take the significance level as 5% throughout our problem.
We can validate our conclusion by the p-value or we can also use the critical value approach.
The critical value approach gives the rejection region of our test. If our test statistic’s obtained
value lies in that region then we say the null hypothesis i.e. our prior belief is rejected.
Note :
1)As we have collected data with respect to time we assume that the data collected is continuous.
2)Here we are analyzing the data to give conclusion about a thesis or principle. So this is a case
control study.
The significance of the problem:
The study will allow the university officials and the library officials to come to a decision whether
there is a need of providing more computers or not. This will help the student community also. Now,
The significance if any problem
Definition of Terms
Parameter: It is associated with the population. It defines the properties of the population. It does not
vary.
Statistic: It is associated with the sample. It helps to estimate the parameter. It varies from sample to
sample.
Hypothesis: A theory that is created to ascertain some event
Null Hypothesis: Null hypothesis is our prior belief about our population under concern.
Alternative Hypothesis: Alternative hypothesis is just opposite of null hypothesis which is tested
against the null hypothesis. It is basically a claim against the null hypothesis.
p-value : p-value is between 0 to 1.It is a probability measure. It helps to take the decision i.e
whether we should support the claim or we are failing to reject the null hypothesis i.e our prior
belief. If its value is less than level of significance (generally denoted by,α) then we should
support the claim in the light of the given data.
SRS: SRS means simple random sample . Here we collect samples from the population in such a
way that each and every unit of the population has the same probability or equal chance of being
included in the sample.

Continuous data: Data is classified into two categories , qualitative and quantitative. Quantitative
data are classified into discrete and continuous. These are numeric values which are measured on
a scale .
References:
Sheldon, Ross (2010). Introductory Statistics, Academic Press, USA.
Hoel, P.G.,(1971),Introduction to Mathematical Statistics, Fourth Edition, USA
Feller, William(2013),An introduction to Probability Theory and Its Applications, Volume ,Third
Edition, U.K
Skaik Y. The bread and butter of statistical analysis “t-test”: Uses and misuses. Pak J Med Sci
2015;31(6):1558-1559