Correlation report guide. PDF

Preview

Summary

Correlation report guide. ...

Description

Correlation report guide In this unit, we build on your correlation/regression report writing skills from Foundations of Statistics. Here’s a quick guide and some examples: Hypothesis Write this in the form of a prediction, rather than a research question. Make sure you’re clear about the predicted direction. Example: “It was hypothesised that people who are more (IV) tend to be have higher (DV)” Things to watch out for: Make sure it doesn’t sound like you’re comparing separate groups, stick to talking about relationship between metric variables Sample description Always describe who was in the sample and say how many. It helps to be specific! Example: “In a random sample of 62 employees”

Things to watch out for: Make sure you use the N that was used to for pearson’s r (from the box with the correlation coefficient and p-value – in this example it is 62). Sometimes this is different from the number of people in entire sample when there are missing values for either variable. Describe relationship between variables Describe the strength, form and direction of the relationship between IV and DV

Example: “there was a weak, negative, linear relationship between age and number of days sick leave

Things to watch out for: Make sure that you’re talking about a relationship between variables, not people. Also make sure you’re talking about the whole variable range, not just high or low scores. It would be incorrect to say “ there is a relationship between people who are older and people who take more sick leave” Presenting the results Say what kind of test was used, whether the relationship is significant and quote appropriate stats (r, n, p) Example: “Pearson’s r shows that this relationship is significant (r = -.31, n = 62, p = 0.015” Things to watch out for: Double check your p-value and significance interpretation, this is really important. When you’re writing -the p-value, you shouldn’t ever write “=...