Presentation is loading. Please wait.

Presentation is loading. Please wait.

Extension: How could researchers use a more powerful measure of analysis? Why do you think that researchers do not just rely on descriptive statistics.

Similar presentations


Presentation on theme: "Extension: How could researchers use a more powerful measure of analysis? Why do you think that researchers do not just rely on descriptive statistics."— Presentation transcript:

1 Extension: How could researchers use a more powerful measure of analysis? Why do you think that researchers do not just rely on descriptive statistics (graphs, measures of central tendency, measures of dispersion) when deciding which hypothesis to accept?

2

3 * Learning objectives By the end of this lesson you will be able: * To explain how probability is used by psychologists and what is meant by differing levels of significance  To explain and use the sign test.  To apply this knowledge to research.

4 You will already be familiar with the idea of the probability of an event happening, for example: * Getting heads when tossing a coin * Scoring a six when throwing a dice * Drawing the ace of hearts from a pack of cards * Winning the lottery 1 in 2 1 in 6 1 in 52 1 in 14 million

5 * If you were to toss a coin 100 times, you would reasonably expect the coin to land showing heads 50 times, and tails 50 times. * You might express the probability of getting heads in a number of ways, for example:  1 in 2  50%  50:50 * You can also express this as a decimal value, which in this case would be 0.5.

6 * Probability or p is expressed as a number between 0 (definitely will not happen) and 1 (definitely will happen). * The role of statistical significance tests is to find out how likely it is that what we have found in our sample accurately reflects what happens in the population.

7 * Suppose that we wanted to investigate if drinking a can of Red Bull influences performance on a memory test.  Our results might suggest the group who had Red Bull achieved higher memory test scores than the group who drank the placebo. Is this graph enough for us to know whether to accept or reject our experimental/alternative hypothesis?

8 NO!!!!!! We need to use a statistical test to tell us if the difference between the two conditions is big enough to be considered significant in the sample size used.

9 NO However, in Psychology, we are happy to be 95% certain In other words, we accept that the probability of results being due to chance is….. 5% or 0.05

10 * When we use the P≤0.05 significance level we are saying that the probability of our results occurring by chance is equal to or less than 5% * In other words, we are 95% confident that the results we have obtained are due to the manipulation of the independent variable rather than chance factors. P≤ 0.05 P means the probability of the results being due to chance ≤ means less than or equal to 0.05 means 5% or 5 in 100

11 * This is one of many statistical tests. * It is only used when: * You are looking for a difference * You have used a repeated measures design * You have nominal data (in categories)

12 * 1) Put your data into a table... The table below shows the scores on an attention test on a day where participants did eat breakfast and a day with no breakfast. Participant number BreakfastNo breakfast 14547 23431 367 44548 55825 66468 74951

13 * 2) Put a plus or minus sign to indicate the direction of the difference for each participant. Participant number BreakfastNo breakfastDifference 14547+ 23431- 367 No difference 44548+ 55825- 66468+ 74951+

14 * 3) To calculate the observed value, add up the number of times the less frequent sign occurs. This is ‘S’. Participant number BreakfastNo breakfastDifference 14547+ 23431- 367 No difference 44548+ 55825- 66468+ 74951+ Plus sign = 4 Minus sign = 2 S = 2

15 * 4) Look up the critical value of s in a critical value table. * You need to make sure you know the number of pairs of scores (omitting scores with no + or – sign), whether you have a one or two tailed (directional or non-directional) hypothesis and the significance level you will be using (usually 0.05). S = 2

16 Critical value = 0

17 * 6) Compare your critical value to s. The calculated value of s must be equal to or less than (≤) the critical value on the table at the 0.05 level of significance for your results to be significant. S = 2 Critical value = 0 The results are not significant. We accept the null hypothesis and reject the experimental hypothesis. Read the description in your RM booklet and complete the activity in your activity booklet.

18 1) P=10 means there is a 10% probability the results occurred by chance. 2) Psychologists tend to use the 5% significance level. 3) If your experiment is well controlled, you could potentially be 100% sure the results are due to your IV. 4) If your results are significant at the significance level you have chosen (i.e. 1%, 5%, or 10%) then you accept your null hypothesis. 5) P>0.05 means there is a less than 5% probability the results occurred by chance. Select true or false for the statements below. If any are false, you should change them so they are correct! False – 0.10 is 10% T False – we can never be 100% certain. EV can always affect our results. False – you would accept your experimental hypothesis False – the > means greater than. < means less than.

19 * Learning objectives You are now able: * To explain how probability is used by psychologists and what is meant by differing levels of significance  To explain and use the sign test.  To apply this knowledge to research.

20 Due in one week: Assessment three: * Complete the sample exam question paper. * Revise and time yourself for 30 minutes to answer the questions. If you haven’t finished by then, just draw a line across the page and then continue to the end.


Download ppt "Extension: How could researchers use a more powerful measure of analysis? Why do you think that researchers do not just rely on descriptive statistics."

Similar presentations


Ads by Google