Welcome back. So now that we know what approach we would take for doing the survey, how are we going to actually construct the ideal survey, get it to the right people and then analyze the information? In this lesson and the next, I will go over the steps involved in designing and implementing a quantitative survey. This will give you a sense of the big picture and where this part of the process fits into the whole. So after this lesson, you'll be able to list the steps in conducting a quantitative research project and describe how each of the first three steps fit into the big picture of quantitative research and analysis, all right? Let's get started. Conducting quantitative research for commercial purposes is a process. Like any process, there are steps involved. When you know the steps to take in the correct order, you'll have a better sense of what to do next and where your work fits in the big picture. So without further ado, here are the steps. One, planning, which means defining the objective and the problem. Two, design, which means determining the research design and the preparing of the instrument. Three, sample selection. Four, implementation, basically collecting all your data through your instrument. Five, data analysis. Six, reporting, both in the form of a written report and presentation of some sort. Let's look at each step in more detail. We will cover the first three in this lesson, then cover the last three in the following lesson. Step 1 is planning. As we have briefly discussed, intricate planning of the research really sets the stage for the entire research project. It really helps to clearly define your goals, which are vitally important. To do this, you first need to establish the root question that needs to be informed by market research. The root question is usually directed to the key business problem or decision that needs to be solved. You want to imagine what you may capture in the research report. It is imperative that you understand the business problem clearly in order to keep your research focused and effective. The key take away here is to make sure your objectives for the research are crystal clear. Step 2 is design. When designing your research instrument or questionnaire, you need to think about what the best way is for each question to get the data that will provide answers to your overall business question and research goals. You want to decide on your plan of attack. What type of survey will best get to the target audience you want to explore? What type of questions will elicit the best and clearest responses? You also want to think about what type of analysis your client wants. Do they want simple cross tabs or do they want a complex statistical analysis? Most market research provides percentages, statistical significance, and cross tabs, nothing too fancy. Descriptive research. You have most likely already conducted what is called exploratory research when you did focus groups and in person interviews prior to the quantitative survey. Now you will most likely conduct what is known as Descriptive Research where you will get detailed data about a specific topic. Causal Research would be the next step where an experiment is setup to determine the relationship between two variables. We will only be discussing Descriptive Research in this quantitative course. Part of the design stage of this process is designing the research instrument, better known as developing the questionnaire. No matter whether you're doing a mail, phone, in-person, or online survey your questions need to be in an ideal order and format to get the best response rate. It is very important to pretest your survey with at least five to ten respondents and enter the data in an Excel file to see that all responses are sound and quantifiable. Step 3 is a Sample Selection. You want to be able to pick a subset of people who are both representative of your target market and who will be able to answer the questions in order to get your data that the client wants. Here are some key words you need to know in order to ensure a good sample selection. Target market, parameters, populations, sample, representative sample, random selection procedure, or probability sampling, and sampling frame. In choosing the sample, you first have to clearly identify your target market. Do you want young mothers, doctors, lawyers, teenagers, young adults? Do you want it to be random or not? Do you want certain geographic regions? This is called defining the parameters of the population you want to study. A population reflects the most common attribute of the people you want to study. So if the researcher wants to study students age 18 to 24 who purchase cell phones, this is the population you want to choose from. UC Davis students would be a sample from this population. You also want to determine how many responses do you need to make the data significant. In determining your representative sample that you can generalize the entire student population, the rule of thumb is that you would need to sample at least 400 students. Ever wonder how people come up with that number? Here is how. Market research aims to get a margin of plus or minus 5% at the 96% confidence level. That is the industry standard. If you calculated that on a sample calculator, you'd see that you would need 387 respondents. So if we rounded up to 400 that is ideal. That's why you often hear 400 for a sample size. That number is what you need to be scientifically credible in the market research profession for quantitative surveys. You would use a random selection procedure to choose the participants for the survey. These participants are known to be included in the sampling frame. There are different types of random sampling to learn about which we will cover at a later time in this course. Random sampling, every member has an equal chance. Stratified sampling, population is divided into subgroups, strata, and members are randomly selected from each group. Systematic sampling uses a specific system to select members such as every tenth person on an alphabetized list. Cluster random sampling divides the population into clusters. Clusters are randomly selected and all members of the cluster selected are sampled. Multi-stage random sampling, a combination of one or more of the above methods. All of these ingredients are extremely important in determining the sample for your survey. Let's wrap up this lesson right here, now that we have covered the first three steps in this process. You should recall that these steps are planning, design, sample selection, implementation, data analysis and reporting. We will cover the last three in the next lesson. I will see you there.
