**Describe the main differences between quantitative and qualitative research.**

Quantitative research is used to study information and data using measurements, statistics and hypothesis testing. The focus of these types of studies are often to describe a general population. Quantitative research is typically used in scientific fields, as well as business and marketing research.

Qualitative research on the other hand can be used to explore attitudes, emotions, beliefs or thoughts; it’s ideal for gaining insights into the thoughts that underpin behaviors. Qualitative research methods are commonly used in psychology, sociology and anthropology surveys (Basias, 2018).

**Probability and non-probability sampling are designed for specific purposes. Using appropriate examples, explain the differences between the two and the benefits of using each.**

In order to understand the difference between probability and non-probability sampling, it is important to first be familiar with the general concept behind each. In probability sampling, every member of a population has an equal chance of being selected for inclusion in a study or survey (Yang et al., 2020). On the other hand, in non-probability sampling a subset of people from the population are chosen by some other criterion than simply their inclusion probability. In practice, probability samples are preferable to non-probability sampling as they are more representative and reliable.

A probability sample represents a cross-section of the population being studied. This can be achieved by using a simple random sampling or stratified sampling approach. In simple random sampling, every possible sample of a given size has the same probability of being chosen. For example, if one wanted to gather information from first year university students, one may go down the hallway choosing students at random for their inclusion in the study. In stratified sampling, the population is divided into smaller groups based on some criteria and a sample of each group is chosen. For example, one may choose to divide first year university students into those who are male and female and then choose a sample of each group (Yang et al., 2020).

A non-probability sample can be obtained in many ways, but generally involves some sort of bias. Non-probability sampling includes convenience sampling, quota sampling and purposive sampling. Convenience sampling involves selecting people who are easy to reach. For example, if one wanted to study high school students and the population of interest was from Toronto, one may choose to sample convenience high school students in Toronto. If a researcher chose convenience sampling to study South Asians, they would use that researcher’s friends and acquaintances.

In quota sampling, members of a population are chosen according to some criteria such as age or gender. For example, if one wanted to study teachers, one may choose a selection of teachers who are both female and old enough.

In purposive sampling, the researcher specifies the criteria by which to select a sample. For example, if one wanted to study hospital administrators, one may research a sample of hospital administrators that has no more than three years of experience in administration and have the same age as the study population.

**Explain the reasons why sampling design is important.**

In statistics, sampling design refers to the selection of a subset of individuals from within a larger population in order to analyze or draw conclusions about that population as a whole. Sampling design is an important part of research and analysis because it allows the researcher to take into account only certain aspects of the population while minimizing personal bias. A good design is one that is representative of the population from which it was drawn. In other words, a sample that is representative of the population from which it was drawn will provide accurate results about the population as a whole (Teeroovengadum, 2018).

The purpose of sampling design is to make it possible for researchers to draw conclusions about generalizable properties of a population without being biased by their previous knowledge about the individuals in their sample. For example, suppose that you wanted to find out how many people had been arrested for shoplifting in the last five years. Knowing that you would only need a sample of 100 people, you approached their employers and asked to interview them. After conducting the interviews, you made a list of all the people who had been arrested for shoplifting during the past five years. All 100 names were written down on paper and divided into two piles – those who had been arrested in the last five years and those who hadn’t (Teeroovengadum, 2018). You then randomly drew a name from one pile or the other without looking at which pile each name came from. The only crucial thing you have to remember when sampling is to pick individuals at random in such a way that everyone has an equal chance of being selected. This avoids biased results.

In addition to avoiding bias, a good sampling design should also be representative of the population from which it was drawn. In other words, a sample that is representative of the population from which it was drawn will provide accurate results about the population as a whole.

**Describe the different types of sampling design.**

The two most common types of sampling designs are the simple random and stratified random sampling designs. The simplest way to illustrate them is in conjunction with an experiment that measures the cost of higher education at 50 different schools by measuring tuition, average financial aid packages and acceptance rates (Lohr, 2021).

Simple Random: This type of design involves taking a sample randomly from every population subgroup that has equal probability of being sampled (the same probability).

Stratified Random: This type of design involves taking a sample randomly from every subgroup with unequal probability of being sampled (different probabilities).

There are many other designs that can be used. However, these two designs can be used to illustrate the differences among sampling designs when conducting surveys, experiments or any type of research in which results are reported.

**Elaborate on the main difference between dependent and independent variables.**

The main difference between dependent and independent variables is the fact that in dependent variables, the outcome of an action on a variable depends on the level of another variable. For example, the amount of money a student receives for poverty or socioeconomic status is determined by their family’s financial means.

Conversely, independent variables do not have an effect on each other. The amount of calories in a donut is unaffected by whether or not you put it inside one with cream filling or chocolate glaze (dependent variable). For example, the amount of money a student receives for poverty or socioeconomic status is determined by their family’s financial means (Reggiani, 2020).

Dependent variables and independent variables are both the focus of research.

Conversely, whether two variables are independent or dependent is not the focus of research. The results of an experiment determine whether two variables are dependent or independent. For example, consider a student who is studying for an exam to determine if there is a relationship between drinking coffee for 20 minutes and reciting poetry for 20 minutes before studying, as well as if there is a relationship between paying attention to commercials during television shows and failing the exam by not studying. The results of these experiments would tell the researcher if there is a relationship between these two variables or not. This is a critical part of research because it helps inform the researcher whether their hypothesis should be changed. For example, if one variable is not significant in predicting an outcome, then the researcher should consider dropping that variable.

In order to conduct an experiment, you must consider independent and dependent variables. Determining whether or not to use independent or dependent variables is crucial for any research project.

**References**

Basias, N., & Pollalis, Y. (2018). Quantitative and qualitative research in business & technology: Justifying a suitable research methodology. *Review of Integrative Business and Economics Research*, *7*, 91-105. https://sibresearch.org/uploads/3/4/0/9/34097180/riber_7-s1_sp_h17-083_91-105.pdf

Yang, S., Kim, J. K., & Song, R. (2020). Doubly robust inference when combining probability and non‐probability samples with high dimensional data. *Journal of the Royal Statistical Society: Series B (Statistical Methodology)*, *82*(2), 445-465. https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/rssb.12354

Teeroovengadum, V., & Nunkoo, R. (2018). Sampling design in tourism and hospitality research. In *Handbook of research Methods for tourism and Hospitality management*. Edward Elgar Publishing. https://www.elgaronline.com/view/edcoll/9781785366277/9781785366277.00048.xml

Lohr, S. L. (2021). *Sampling: design and analysis*. Chapman and Hall/CRC. https://www.taylorfrancis.com/books/mono/10.1201/9780429298899/sampling-sharon-lohr

Reggiani, C., & Schiaffino, S. (2020). Muscle hypertrophy and muscle strength: dependent or independent variables? A provocative review. *European journal of translational myology*, *30*(3). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7582410/