Data is a collection of facts that can be measured or translated. Data may consist of words, numbers, observations, descriptions of things, and measurements. Data may be qualitative or quantitative. “Qualitative data is descriptive information that describes something. Quantitative data is continuous measurements of numerical information” (Lind, Marchal, & Wathen, 2011, p. 9). Data can be collected in many ways but the simplest way is direct observation. Understanding data analysis helps people to make an informed decision.
Team A has been tasked with analyzing the Excel data set of freshmen’s weight both before and after their first semester at a leading state university. The freshmen lived in either an on-campus dorm (O), or a private off-campus dorm managed by DormsRUs (D), who claims their students have a healthier lifestyle. After carefully reviewing the clean data, which includes the subjects, on and off campus dorms, initial and final weight, and gender, two research questions was presented. How many female students lost weight during their freshmen year?
How many male students lost weight during their freshmen year? Six is the number of female students who lost weight during their freshmen year. The number of male students who lost weight during their freshman year is 10. This would be of interest to DormsRUs management as well as incoming students because only one of the students who lost weight lived in an on-campus dorm. The most interesting research question concerning the topic but cannot be answered through this data set is, “What is the activity level of the students who participated in this study? If Team A had to redesign this study, the team came to a consensus that the activity level of the students would be collected. In identifying the target population, we have to survey the freshmen at this leading university before the beginning of the first semester until the end of the semester. In this survey the targeted population consists of both males and females who live on the campus as well as off campus. In collecting the data or population of this experiment, we must decide in the manner to collect the data.
In this particular experiment, we will conduct an experiment called the designed experiment in this survey. We will use the weight of the each freshmen randomly selected at this leading university whom either lives in the dormitory or off- campus in private dormitories. Another way of collecting data is conducting it as a survey in which researcher will sample a group of people both male and female to ask one or more questions, and record the information. This information can be used as part of the research conducted. Observational study is another form of collecting data.
In observational studies the observer will study the habit and functions of the targeted population. In this case it would be the freshmen at this leading university that live on campus or in private off-campus dorms. All of these examples of collecting and conducting data will have to involve using samples conducted by the population and applying inferential information, which is obtained through representatives. These samples are typically those possessed by the population of interest when conducting a sample population by choosing random samples of every different sample size.
It gives them an equal chance of selection and does not target those that would compromise the data. In conducting research and using a targeted population, always try to use as large enough a sample of the population as possible. The reason is the larger the sample, the better it represents the population (Yount, 2006). This information collected in the research will conclude that some of the collected information is discrete and continuous and it could also be quantitative and qualitative.
Research shows that the data utilized by Team A is quantitative data. Quantitative data is data that can be measured including humidity, temperature, sound levels, height, and weight. The most important aspect of quantitative data that separates it from qualitative is the fact that quantitative data involves numbers. Quantitative is more quantity based where qualitative is more focused on the quality. Team A research involved the difference of weight of freshmen at a leading university that lived on campus versus a private off campus dorm.
Their initial weight was recorded at the beginning of a semester and then recorded and compared at the end of that semester. The variables used by Team A consist of continuous data. Continuous data can occupy any rate over a continuous range because it is not restricted to a defined set of values. The freshmen’s initial weight at the beginning of the semester had the possibility of fluctuation and was not set therefore the ending weight was not defined either. The level of measurement that was utilized by Team A was the interval/ratio level.
This level uses numbers as a means to express quantities. For example, the initial weight of the freshmen compared to their weight at the end of the semester. Their weight is used numerically to express a quantity. When numerical data input errors are made or data is incomplete, it can cause research questions to go unanswered. Errors and missing data usually can be handled by computer programming, however, depending on the severity of the missing or incorrect data, some cases would have to be scrutinized considering the data limitations.
Computer software packages include programs to address the issues with data completeness. The most likely fix is for the missing data to be replaced with a symbol or numbers, for instance, 999 or “”. This can cause the programming to ignore these particular values during computation, and just compute the data available with a smaller count of items. Some things that must be considered besides the missing values are whether or not there is a pattern to what is missing. In the freshman weight study, there are missing and misrecorded values.
Two are final weights, and two are obviously misrecorded measurements. As it is hard to believe that an incoming college freshman is 82 pounds or that an incoming freshman male lost 60 pounds in his first semester in college. When processing this data it was easy to spot and delete because of such a small sample, but with larger samples computer programs are most helpful in deciphering this data. In some cases it is important to recognize conflicting or odd measurements in a data set.
An outlier is an observation that is unusually large or small relative to the data values we want to describe and is set apart from the other data. (McClave, J. T. , Benson, P. G. , & Sincich, T. , 2011). In some cases this is necessary to figure out if the study should go on or be redesigned. Team A had the task to decipher the data set of freshman weight in their first semester of college. We studied the data on the spread sheet and developed a clean copy. This data set was quantitative because of its numerical value and also continuous because it is not restricted to a defined set of values.
It was found that freshmen gained more in on-campus dorms and that more weight was loss in off-campus dorms managed by DormsRUs. This could be a great marketing tool for DormsRUs. Incoming freshman would be excited to have this knowledge and investigate its causes. Perhaps the freshman would get more exercise walking to school or maybe there are health clubs and healthy eating establishments close by. Management could utilize this data to enhance their product and attract more business for their dorms. This is an example of how statistics can be beneficial in business.
Lind, D. A. , Marchal, W. G. , & Wathen, S. A. (2011). Basic statistics for business and economics (7th ed. ). New York, NY: McGraw-Hill/Irwin. Retrieved from the UOPX EBOOK Collection. McClave, J. T. , Benson, P. G. , & Sincich, T. (2011) Statistics for Business and Economics Retrieved from: https://portal. phoenix. edu/classroom/coursematerials/qnt_351 Yount, R. (2006) Populations and Sampling. Retrieved from: http://www. napce. org/documents/research-design yount/