Welcome to week 3. In the first week of this course we covered hypothesis, remember that a hypothesis is a prediction about a particular outcome that could be based on personal experience or research. In the second week, we covered measurement and talked about how to collect data to test your hypothesis. This week, we're going to talk about data analysis and in particular, explore have to interpret results that you'll see in positive psychology articles. The videos for this week will be broken up into three parts, this first video will provide an overview of analysis more generally and how the type of analysis is driven by the type of hypothesis you have. In the second video, we'll discuss descriptive analysis both quantitative and qualitative and then the third video we'll talk about inferential analysis where you're trying to make a prediction or draw conclusion based on the data that's been collected. For both of these forms of data collection, we'll talk about how you can apply this learning to the interpretation of positive psychology articles. So what is Data Analysis? It's the process of inspecting and modeling data with the goal of either supporting or rejecting your hypotheses, there are many different methods for analyzing data. And in this week, we'll focus on two over-arching of analysis. Quantitative and qualitative. Remember that quantitative methods emphasize objective methods and numerical analysis and qualitative methods emphasize deeper understanding of phenomenon. A third approach to data analysis is the use of mixed methods which integrates both quantitative and qualitative to investigate key hypothesis. When determining what type of analysis to run, you need to consider what type of hypothesis you have. Broadly speaking, there are two types of hypotheses, descriptive and inferential. First, descriptive hypotheses are hypotheses where you're just describing trends. You're not trying to manipulate any data, but just observing the world around you. For example, let's say you had a hypothesis that teachers were very gritty. You would use quantitative descriptive analysis and investigate this type of hypothesis, which describes the observed data either using numbers or graphs. Another type of descriptive hypothesis is one where you are trying to understand key trends. Often times this type of hypothesis are answered through qualitative analysis. So say for example you have a hypothesis about how individuals exhibit grit, or are in the early stages of developing a new construct and in interviewing people or conducting observations to build your understanding. Then you would analyze this qualitative data to understand key trends. Second, inferential hypothesis are hypothesis where you're interested in the difference between groups or testing the relationship between two variables. So for example, let's say you were interested in whether an intervention you had developed had an impact on teachers level of grit. You will develop the intervention and then assign some people to receive that intervention and other people to not receive that intervention, then at the end of the study you would compare the people who had received the intervention with those who havent. This is an example of a group differences hypothesis where you were testing whether there was a difference between two groups. The other type of inferential hypothesis compares variables to see if they're related to each other. So let's say you're interested in comparing two continuous variables,.grit and teacher's performance. This type of relationship based hypothesis is the second type of inferential hypothesis. In both of these cases, inferential statics allows for generalization about a sample to the broader population. Using inferential statistics, you can identify the relationship between two variables of interest or the difference between two groups. When you run inferential statistics, you test what's called the null hypothesis, which is the statement that an intervention has no effect on an intended outcome. Or that there's no relationship between variables. It's a little bit counter intuitive when you think about it. Most of the time we have a prediction that we're interested in testing. For example, you may think that growth mindset will lead to greater success, or that optimism will lead to greater life satisfaction. But in statistics you don't test your prediction. You assume that your prediction is incorrect and the burden of proof is on finding a different or relationship. So, in the example that just provided you will assume that their isn't relationship between growth mindset and success. Or between optimism and life satisfaction this would be your null hypothesis. Then you would run analysis to see if theres enough evidence to reject the null hypothesis and accept your alternative hypothesis or prediction. In this case that growth mindset would lead of greater success or optimism would lead to greater life satisfaction. We'll talk more about how you do this in the final video. As you can see from this slide all of these different example hypothesis are related to grit but the type of analysis they require various depending on the type of hypothesis you have and the questions you are trying to answer. In the next video Will turn to talk more about descriptive analysis, where you're merely describing or understanding trends in existing data. And in the final video for this week, we'll turn to inferential analysis, where we'll discuss some key terms that you're likely to come across in the results section of psychology articles and help you understand how to make sense of the data.