memory perspectives: data analysis week 9 practical
TRANSCRIPT
MEMORY PERSPECTIVES:
DATA ANALYSIS
Week 9 Practical
WEEK 9 PRACTICALMEMORY PERSPECTIVES
WEEK 1
WEEK 2
WEEK 3
WEEK 4
WEEK 5
WEEK 6
WEEK 7
WEEK 8
WEEK 9
WEEK 10
LECTURE 1 PRACTICAL
NONPARAMETRICS 1 1ST PRACTICAL
NONPARAMETRICS 2 1ST ANALYSIS
SAMPLING DISTRIBUTIONS
1ST ANALYSIS + PROBLEMS 1
HYPOTHESIS TESTING
2ND PRACTICAL
RELATED T-TEST
2ND ANALYSIS + SOLUTIONS 1
INDEPENDENT T-TEST
INDEPENDENT ANOVA
DEPENDENT ANOVA
2ND ANALYSIS + PROBLEMS 2
3RD PRACTICAL
3RD ANALYSIS + SOLUTIONS 2
3RD ANALYSIS + PROBLEMS 3
NO LECTURE NO PRACTICAL
LEARNING OUTCOMES
BY THE END OF THE SESSION, YOU SHOULD BE ABLE TO:
Produce a (very nice) graph in Excel which assists in the interpretation of the data.
Use SPSS to test the second hypothesis in the memory perspectives practical and interpret the output.
Use SPSS to test the first hypothesis in the memory perspectives practical and interpret the output.
Make a start on writing up your RESULTS and DISCUSSION sections for your lab report.
MEMORY PERSPECTIVES
RESULTS
The first 2 columns show subject id and group membership.
The last two columns show recall for LIST A (BURGLAR) and LIST B (BUYER).
MEMORY PERSPECTIVES
(Perspect 0 = BURGLAR; Perspect 1 = BUYER)
RESULTS
In SPSS, Independent t-test may be found under analysis >
compare means > independent-samples t test.
Independent t-testINTERVAL + BETWEEN Ss + 2 GROUPS
Q1: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST A (burglar relevant items)?
MEMORY PERSPECTIVES
RESULTS
SPSS would like to know what the test variables (DV) is. At the moment, we’re just interested in LIST A recall.
We also need to define our ‘grouping variable’ (IV) which is BURGLAR (0)
or BUYER (1).
We have to tell SPSS that our first group is assigned to the number
value 0 and the second group to the number value 1.
Independent t-testINTERVAL + BETWEEN Ss + 2 GROUPS
Q1: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST A (burglar relevant items)?
MEMORY PERSPECTIVES
RESULTS
Remember that Levene’s test assesses whether our two groups have equivalent variance. If Levene’s is NON-SIGNIFICANT we assume equality.
Independent t-testINTERVAL + BETWEEN Ss + 2 GROUPS
Q1: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST A (burglar relevant items)?
With Levene’s F = 1.60, p = .207, we arrive at t(151) = 6.64, p < .001.
MEMORY PERSPECTIVES
RESULTS
In SPSS, Independent t-test may be found under analysis >
compare means > independent-samples t test.
Independent t-testINTERVAL + BETWEEN Ss + 2 GROUPS
Let’s repeat this exercise for the second hypothesis.
MEMORY PERSPECTIVES
Q2: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST B (home-buyer relevant items)?
RESULTS
Now, we’re interested in LIST B (buy_fea) recall rather than LIST A
(burg_fea) recall, so switch these test variables around.
Everything else can stay as is.
Independent t-testINTERVAL + BETWEEN Ss + 2 GROUPS
MEMORY PERSPECTIVES
Q2: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST B (home-buyer relevant items)?
RESULTS
Once again, Levene’s test comes through for us, supporting equal variance between the burglars and the buyers.
Independent t-testINTERVAL + BETWEEN Ss + 2 GROUPS
With Levene’s F = 1.12, p = .291, we arrive at t(151) = -3.90, p < .001.
MEMORY PERSPECTIVES
Q2: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST B (home-buyer relevant items)?
RESULTS
Q2: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST B (home-buyer relevant items)?
Q1: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST A (burglar relevant items)?
If you’re hungry for the stats, and wanted to spit out both SPSS output
to Q1 and Q2, then all you have to do is define multiple test variables…
So, everything’s significant, but what are the directions
of these effects?
Excel to the rescue.
MEMORY PERSPECTIVES
DOWNLOAD AND SAVE THE FILE ‘MEMPER_ANALYSIS’
RESULTS
DOWNLOAD AND SAVE THE FILE ‘MEMPER_INEXCEL’
To calculate mean:
AVERAGE(cellab:cellcd)
To calculate standard deviation:
STDEV(cellab:cellcd)
To calculate standard error:
=STDEV(cell) / sqrt (no. observations)
To start graphing:
Select means and labels
THIS SHEET CONTAINS THE SAME DATA AS IN SPSS
MEMORY PERSPECTIVES
RESULTS
COLUMN
MEMORY PERSPECTIVES
RESULTS
SELECT SERIES IN COLUMNS > NEXT
MEMORY PERSPECTIVES
RESULTS
MODIFY
MEMORY PERSPECTIVES
RESULTS
DOUBLE CLICK ONE SET OF BARS (BURGLARS ARE HIGHLIGHTED)
MEMORY PERSPECTIVES
RESULTS
ADD CUSTOM +/- STANDARD ERROR RELATED TO THOSE BARS
MEMORY PERSPECTIVES
RESULTS
REPEAT FOR THE OTHER SET OF BARS (BUYERS ARE HIGHLIGHTED)
MEMORY PERSPECTIVES
RESULTS
Q2: Do ‘BURGLARS’ and ‘BUYERS’ have different levels of recall for LIST B
(home-buyer relevant items)?
Q1: Do ‘BURGLARS’ and ‘BUYERS’ have different levels
of recall for LIST A (burglar relevant items)?
LIST A BURGLARS > BUYERS
0
2
4
6
8
10
12
List A (Burglar) List B (Buyer)
Memory Perspective
Lis
t R
ec
all
BURGLARS
BUYERS
MEMORY PERSPECTIVES
LIST B BURGLARS < BUYERS
What implications do these two hypotheses have for the memory
perspectives account?
LEARNING OUTCOMESMEMORY PERSPECTIVES
BY THE END OF THE SESSION, YOU SHOULD BE ABLE TO:
Produce a (very nice) graph in Excel which assists in the interpretation of the data.
Use SPSS to test the second hypothesis in the memory perspectives practical and interpret the output.
Use SPSS to test the first hypothesis in the memory perspectives practical and interpret the output.
Make a start on writing up your RESULTS and DISCUSSION sections for your lab report.
MEMORY PERSPECTIVES
THERE IS NO PRACTICAL SESSION IN WEEK 10
CLARIFY ANY OUTSTANDING ISSUES YOU HAVE WITH YOUR TUTORS NOW...
DISCUSSION
GET TOGETHER IN GROUPS OF THREE OR FOUR AND REFLECT ON TODAY’S EXPERIENCE USING THE FOLLOWING QUESTIONS
What are the combined factors that justify this
statistical test?
Are there any interesting observations to be made
from the data?
Could I have made one-tailed hypotheses? How would this have changed
the p value?
MEMORY PERSPECTIVES