Task: Define each of these key terms. Correlation Positive correlation Negative correlation No correlation Task: Define each of these key terms. REVVING UP

Correlations 11 November 2018 Component 01 Research Methods 11 November 2018 Correlations L.O: To identify and describe different correlations and how a correlation co-efficient is calculated. The aim of this session will be to introduce correlations to students. Teacher to deliver information about positive and negative correlations (most students should be familiar from GCSE Maths, so teacher should encourage students to give information rather than passively receive it)

How will you know that you have made progress this lesson? Progress Criteria GOING STRONG I can create a scatter graph to represent a set of correlational data. ACCELERATING I can distinguish positive, negative and no correlations. REVVING UP I can define a correlation and identify the difference between correlation as a technique and a method.

Stretch & Challenge: If there is no IV, what can’t we establish? Correlations Correlation: a measure of how strongly two or more variables are related to each other: Height is positively correlated to shoe size The taller someone is, the larger their shoe size tends to be. Like Self Report and Observation, there is no manipulation of data, conditions or groups in correlations. No IV or DV, just to co-occurring variables (co-variables). Teacher to stress the correct use of terminology: co-variables rather than IV and DV. Stretch & Challenge: If there is no IV, what can’t we establish? REVVING UP

Unlike experiments there is no IV, just two variables that occur together as ‘co-variables.’ As there is no IV to manipulate we cannot establish cause and effect We don’t know which variable is causing the other, we just know there is a relationship between them. CoV Correlation NO CAUSE & EFFECT ? REVVING UP

Correlations Still use the same sampling methods: Volunteer, self selected, random, snowball Still consider the same ethical issues: How many of the ethical issues can you identify? Give an example of how each ethical issue may need to be considered in a correlation. Encourage students to recall how each of the sampling techniques would be used in addition to the ethical guidelines. Learners should be given a few minutes to recall independently, use a random name generator, or similar, to target students to share information REVVING UP

Correlations can be both the primary method or secondary technique. Self reports and observations can both be used as a way to gather data on variables, and then see if there is a relationship between them. Primary method: Correlations Secondary technique: Self report/Observation Experiments can compare the data between two groups using correlations. I find out men have a stronger correlation between age and time spent looking in the mirror than women. Primary method: Experiment Secondary technique: Correlation Students should be aware of the difference between correlation as a method and as a technique. Encourage students to think of examples of core studies that use correlation. Stretch and Challenge: which core study uses experiment as the method and correlation as the technique?

Task Activity 1: Identify other possible correlations we could investigate for age and sleep. Extension: Identify any two variables you would find interesting to investigate (you will be expected to conduct your own investigation at a later stage). Workbook activity 1 – Identifying correlations. ACCELERATING

Positive and negative correlations Positive Correlation: as one variable increases, so does the other. Negative Correlation: as one variable increases, the other decreases. No Correlation: there is no relationship between the variables. ACCELERATING Stretch and Challenge: The more revision is done, the higher the final grade is. Is this a positive or negative correlation?

Positive, negative and no correlations Perfect Positive Relationship No relationship Perfect Negative Relationship Students could be asked how correlations are represented graphically and what positive, negative and no correlations look like on a graph. This can then be presented after activity 2. ACCELERATING

Scatter diagrams We can display correlation data in scatter diagrams. One variable (amount of revision done) along one axis and another variable (final grade) along the other. Each ‘point’ on the scatter diagram represents one participant: how much revision they put in and what their final grade was. Students will be given the opportunity to plot their own scattergraph, identifying the need to include titles and label axes GOING STRONG

Amount of revision (in hours) Grade achieved A*-U Amount of revision (in hours) 2 5 7 10 Final grade U E C B A*

Amount of revision (in hours) Grade achieved A*-U We can then use the scatter diagram to describe the relationship between the variables Link back to correlation co-efficient. Get students to identify which correlation co-efficient would best fit here.

Task Plot one variable on the x axis and one on the y axis. Plot using dots or crosses. Remember to include: Title Clearly labelled both axes (including measurements when possible). Students can use their data from activity 3, or they can use their own data. GOING STRONG

Correlations 11 November 2018 Component 01 Research Methods 11 November 2018 Correlations L.O: To identify and describe different correlations and how a correlation co-efficient is calculated. The aim of this session will be to introduce correlations to students. Teacher to deliver information about positive and negative correlations (most students should be familiar from GCSE Maths, so teacher should encourage students to give information rather than passively receive it)

How will you know that you have made progress this lesson? Progress Criteria GOING STRONG I can evaluate the strengths and weaknesses of correlations. ACCELERATING I can explain what a correlation co-efficient is and how to calculate a correlation co-efficient. REVVING UP I can define a different types of hypothesis.

Hypotheses Unlike Observation and Self Report we can generate hypotheses for Correlation Research. Recap: Null Hypothesis Alternate hypothesis (one tailed or two tailed). What is the difference between a one tailed and a two tailed hypothesis? REVVING UP

Hypotheses Correlations can’t show cause and effect Can’t mention the effect one variable will have on the other so we talk about the ‘relationship’ between two variables Still using the term significant Still must clearly state the variables and how they have been operationalised NEVER using the words cause, effect or difference. Re-cap, what are they called? REVVING UP

Which word(s) must you NEVER use in a correlational hypothesis? Hypotheses Null hypothesis: there will be no relationship There will be no significant relationship between V1 and V2. Alternate hypothesis: One tailed: There will be a significant positive/negative relationship between V1 and V2 Two tailed: there will be a significant relationship between V1 and V2. Which word(s) must you NEVER use in a correlational hypothesis? ACTIVITY - Give examples of variables, cut up key words and variables and have students sort into the correct order (or line up each with a different word from the hypothesis) REVVING UP

Identify the type of hypothesis in each of these examples There will be a significant positive relationship between number of pets owned and the amount of money spent on pet food per week. One tailed alternate hypothesis There will be no significant relationship between a person’s mood and the amount of chocolate they consume. Null hypothesis There will be a significant negative relationship between the amount of time spent watching reality TV shows and final exam grades. One tailed alternate hypothesis There will be a significant relationship between amount of exercise in hours per week and weight in kilos. REVVING UP Two tailed alternate hypothesis

A psychologist is researching whether there is a relationship between the amount of time listening to music and self-esteem. She gives participants a questionnaire with two items: how many hours they spend listening to music per week on average, and a likert scale question asking them to rate their self-esteem from one to ten (where one is low and ten is high). Write three hypotheses for the research above: Alternate one tailed hypothesis Alternate two tailed hypothesis Null hypothesis REVVING UP

Correlation Co-efficient We can measure the strength of the relationship, by using inferential statistics. Spearman's Rank Test is used with correlations. Correlation Coefficient: a number between -1 and +1 that tells us how strong the relationship is. Encourage students to explain the difference between inferential and descriptive statistics and the reasons for using each. They must also be able to demonstrate why a particular inferential test would be used (ordinal / interval level data, correlational design = Spearman’s Rho) ACCELERATING

Correlation Co-efficient +1.0 perfect positive correlation +0.8 strong positive correlation +0.5 moderate positive correlation +0.3 weak positive correlation 0 no correlation -0.3 weak negative correlation -0.5 moderate negative correlation -0.8 strong negative correlation -1.0 perfect negative correlation ACCELERATING

Spearman’s Rank Spearman's RHO is a non-parametric statistical test and is used to find out whether there is a relationship between two variables. The criteria used are: Two variables with an ordinal or interval level of measurement. Design of the research is a correlation Looking for a relationship between two variables. Two sets of pairs scores are used. ACCELERATING

Formula The formula for Spearman’s Rho produced the correlation coefficient. It is then compared to the critical value. N: the number of participants (or pairs of scores) Alternative hypothesis: directional (one-tailed or non-directial (two tailed) Level of significance: the ‘p’ value. E.g p<0.05 If the observed value is greater than the critical value then the relationship is significant, so the null hypothesis is rejected and the alternative hypothesis accepted. If the observed value is less than the critical values then the relationship is not significant so the null hypothesis is accepted and the alternative hypothesis is rejected. ACCELERATING

Task Complete Activity 3. Calculate the co-efficient for the data sets given. What can we conclude from the correlation co-efficient from this data? Watch the video and then attempt the example: https://www.youtube.com/watch?v=0qLKfMm45-4 ACCELERATING

What are the potential problems with correlations? http://www.buzzfeed.com/kjh2110/the-10-most-bizarre-correlations. Identify some possible explanations of the results. What interpretations could there be and why may the results may be misleading? There are many fun ways to demonstrate a correlation, one variable could be the students’ age in years and months or shoe size, while the other variable may be speed at completing a Sudoku puzzle (this may be good on a Monday morning to wake your students up). A fun and engaging way to introduce correlations is to look examples of how they can be misleading. There is an excellent post on buzzfeed which gives some great examples of real correlations http://www.buzzfeed.com/kjh2110/the-10-most-bizarre-correlations. This could be used as an IT task – students could explain the results, what interpretations there could be and why the results may be misleading. GOING STRONG

Strengths of Correlations Makes a good pilot study to generate a hypothesis for an experiment. Can research variables that would be unethical to manipulate. Can understand the relationship between two variables (positive/negative, weak/strong). GOING STRONG

Weaknesses of Correlations Correlations do not show causation. They have the same weakness as whatever method was used to gather the data (observation/self report). Tell us nothing about other variables that may be the real cause Often correlations are misleading: NEVER USE DIFFERENCE, EFFECT OR CAUSE when describing a correlation. GOING STRONG

Write your own correlation Step 1: Decide on the variables that you want to measure (remember that the data you collect must be quantitative and at least ordinal level). Step 2: Decide on the method you are going to use to measure your variables. Remember, if you choose to use self-report, you will need to devise a questionnaire, containing two critical questions and filler questions. If you are using an observation, decide on event / time sampling and create a coding scheme. Step 3: Collect your data (minimum 10 participants). Step 4: Use your data to draw a scatter graph. Step 5: Decide if there is a correlation between the variables you have chosen to measure. Step 6: Produce your report for peer review.