Back
to top
A2 psychology help please!!!
Watch
Announcements
Page 1 of 1
Go to first unread
Skip to page:
In the research methods unit I get everything but the stupid probability and significance. I don't get what type 1 and 2 errors are? What is the purpose of significance levels and what do they mean?
Don't mean to be a pain but I'm really lost
Don't mean to be a pain but I'm really lost
0
reply
Report
#2
(Bear with me with this explanation because I haven't revised research methods fully yet!)
The first thing to remember is we always start off with the null hypothesis ('There will be no difference') rather than the alternative hypothesis (which is directional or non directional). This is all to do with Popper and falsification (which you also need to know about!)
I've tried to separate significance and probability but I think they're quite interlinked.
PROBABILITY: Probability level tells us how much the researcher thinks the results could have been down to chance alone, rather than the IV. Psychologists generally use the probability level p=0.05. This means the probability of the results being down to chance is 5%, whilst there is a 95% probability the results were in fact the product of the IV.
SIGNIFICANCE: this tells us if the data actually means anything. I think the simplest way to see this is 'Is the null hypothesis true or not?' It's kind of similar to probability. So you're using statistical tests to determine 'Is there a real, existing difference between variables or is it down to chance?'.
TYPE 1 TYPE 2 ERRORS: So we start off with our null hypothesis. For example, you have a null hypothesis of 'There will be no difference in the amount of words recalled between Year 7's and Year 11's. After doing your statistical tests and other aspects, you can decide whether to reject of accept the null hypothesis as part of your conclusion. This can pose two types of error:
TYPE 1 ERROR: You reject the null hypothesis but it is actually true (i.e. you've said there is a difference in amount of words recalled by Year 7's and Year 11's but in fact there is no difference).
TYPE 2 ERROR: You accept the null hypothesis but it is actually false (i.e. you've said there is no difference in amount of words recalled by Year 7's and Year 11's but in fact there is a difference).
If you're still stuck I would recommend the Psychology A2: Complete Companion for AQA A (third edition) by Mike Cardwell and Cara Flanagan. At the back, they have spreads on Research Methods which I find are great at explaining this sort of stuff (which I was totally lost with during my lessons).
Feel free to ask more questions or PM me if my messy explanation doesn't make any sense!
The first thing to remember is we always start off with the null hypothesis ('There will be no difference') rather than the alternative hypothesis (which is directional or non directional). This is all to do with Popper and falsification (which you also need to know about!)
I've tried to separate significance and probability but I think they're quite interlinked.
PROBABILITY: Probability level tells us how much the researcher thinks the results could have been down to chance alone, rather than the IV. Psychologists generally use the probability level p=0.05. This means the probability of the results being down to chance is 5%, whilst there is a 95% probability the results were in fact the product of the IV.
SIGNIFICANCE: this tells us if the data actually means anything. I think the simplest way to see this is 'Is the null hypothesis true or not?' It's kind of similar to probability. So you're using statistical tests to determine 'Is there a real, existing difference between variables or is it down to chance?'.
TYPE 1 TYPE 2 ERRORS: So we start off with our null hypothesis. For example, you have a null hypothesis of 'There will be no difference in the amount of words recalled between Year 7's and Year 11's. After doing your statistical tests and other aspects, you can decide whether to reject of accept the null hypothesis as part of your conclusion. This can pose two types of error:
TYPE 1 ERROR: You reject the null hypothesis but it is actually true (i.e. you've said there is a difference in amount of words recalled by Year 7's and Year 11's but in fact there is no difference).
TYPE 2 ERROR: You accept the null hypothesis but it is actually false (i.e. you've said there is no difference in amount of words recalled by Year 7's and Year 11's but in fact there is a difference).
If you're still stuck I would recommend the Psychology A2: Complete Companion for AQA A (third edition) by Mike Cardwell and Cara Flanagan. At the back, they have spreads on Research Methods which I find are great at explaining this sort of stuff (which I was totally lost with during my lessons).
Feel free to ask more questions or PM me if my messy explanation doesn't make any sense!
1
reply
(Original post by lemonysnicketing)
(Bear with me with this explanation because I haven't revised research methods fully yet!)
The first thing to remember is we always start off with the null hypothesis ('There will be no difference') rather than the alternative hypothesis (which is directional or non directional). This is all to do with Popper and falsification (which you also need to know about!)
I've tried to separate significance and probability but I think they're quite interlinked.
PROBABILITY: Probability level tells us how much the researcher thinks the results could have been down to chance alone, rather than the IV. Psychologists generally use the probability level p=0.05. This means the probability of the results being down to chance is 5%, whilst there is a 95% probability the results were in fact the product of the IV.
SIGNIFICANCE: this tells us if the data actually means anything. I think the simplest way to see this is 'Is the null hypothesis true or not?' It's kind of similar to probability. So you're using statistical tests to determine 'Is there a real, existing difference between variables or is it down to chance?'.
TYPE 1 TYPE 2 ERRORS: So we start off with our null hypothesis. For example, you have a null hypothesis of 'There will be no difference in the amount of words recalled between Year 7's and Year 11's. After doing your statistical tests and other aspects, you can decide whether to reject of accept the null hypothesis as part of your conclusion. This can pose two types of error:
TYPE 1 ERROR: You reject the null hypothesis but it is actually true (i.e. you've said there is a difference in amount of words recalled by Year 7's and Year 11's but in fact there is no difference).
TYPE 2 ERROR: You accept the null hypothesis but it is actually false (i.e. you've said there is no difference in amount of words recalled by Year 7's and Year 11's but in fact there is a difference).
If you're still stuck I would recommend the Psychology A2: Complete Companion for AQA A (third edition) by Mike Cardwell and Cara Flanagan. At the back, they have spreads on Research Methods which I find are great at explaining this sort of stuff (which I was totally lost with during my lessons).
Feel free to ask more questions or PM me if my messy explanation doesn't make any sense!
(Bear with me with this explanation because I haven't revised research methods fully yet!)
The first thing to remember is we always start off with the null hypothesis ('There will be no difference') rather than the alternative hypothesis (which is directional or non directional). This is all to do with Popper and falsification (which you also need to know about!)
I've tried to separate significance and probability but I think they're quite interlinked.
PROBABILITY: Probability level tells us how much the researcher thinks the results could have been down to chance alone, rather than the IV. Psychologists generally use the probability level p=0.05. This means the probability of the results being down to chance is 5%, whilst there is a 95% probability the results were in fact the product of the IV.
SIGNIFICANCE: this tells us if the data actually means anything. I think the simplest way to see this is 'Is the null hypothesis true or not?' It's kind of similar to probability. So you're using statistical tests to determine 'Is there a real, existing difference between variables or is it down to chance?'.
TYPE 1 TYPE 2 ERRORS: So we start off with our null hypothesis. For example, you have a null hypothesis of 'There will be no difference in the amount of words recalled between Year 7's and Year 11's. After doing your statistical tests and other aspects, you can decide whether to reject of accept the null hypothesis as part of your conclusion. This can pose two types of error:
TYPE 1 ERROR: You reject the null hypothesis but it is actually true (i.e. you've said there is a difference in amount of words recalled by Year 7's and Year 11's but in fact there is no difference).
TYPE 2 ERROR: You accept the null hypothesis but it is actually false (i.e. you've said there is no difference in amount of words recalled by Year 7's and Year 11's but in fact there is a difference).
If you're still stuck I would recommend the Psychology A2: Complete Companion for AQA A (third edition) by Mike Cardwell and Cara Flanagan. At the back, they have spreads on Research Methods which I find are great at explaining this sort of stuff (which I was totally lost with during my lessons).
Feel free to ask more questions or PM me if my messy explanation doesn't make any sense!
0
reply
X
Page 1 of 1
Go to first unread
Skip to page:
Quick Reply
