✏
Psychological Inquiry 3
Class Psychology Foundations: The Social Self
https://docs.google.com/document/d/1JcTYXMhf9TBxPgXpEPaYkrhZL3MAUASpGAUvsHvlSjc/edit https://docs.g
Materials K7ESGA/edit https://docs.google.com/document/d/1W-EKSkJwP4lgVRRfWDZfCmgxLs-dKbZU8j9joCh82qA/edit
Reviewed
Learning Outcomes:
1. Identify the advantages and disadvantages of various types of experimental designs.
2. Distinguish between descriptive and inferential statistics.
3. Organise data in the form of frequency distribution tables and graphs.
4. Calculate and differentiate between the three measures of central tendency (mean, median, and mode).
5. Calculate measures of variability or dispersion (range, variance, standard deviation).
6. Describe the philosophical assumptions underlying big 'Q' qualitative research and what this approach means for research in
Learning Outcome 1: Identify the advantages and disadvantages of various types of experimental designs.
Within-subject designs: recording score of the same person that could be in one setting or at different time points. We compar
Repeated measure designs: ‘Repeated’ and ‘measures’ because you are making repeated measurements with the same pe
To conduct a within-subjects design you:
1. Manipulate the independent variable to create different conditions (e.g., before and after a treatment)
2. Use the same group of participants for each condition
3. Measure the dependent variable for each participant in each condition
4. Compare that dependent variable across the conditions
Between-subject designs (independent measure design): the scores for the different treatment conditions come from differe
To conduct a traditional between-subjects design you:
1. Manipulate the independent variable to create different conditions (e.g., no treatment, treatment 1, treatment 2)
2. Assign people into one of each of those conditions (..if you are in one you can't be in the other)
3. Measure the dependent variable of each participant in each condition
4. Compare the dependent variable across the conditions
Matched-subjects design: tries to get the best of both worlds by combining the within-subjects and between-subjects designs.
Power is the likelihood that you will detect differences between treatment conditions, if there are really differences to detect.
It's the probability of detecting the differences, if there actually are differences to detect.
What affects power?
Size of sample: Sample size is the biggest threat to power is down to your sample size. Between-subjects designs hav
Variability: variability is another threat to power. If I have noisy variable data and so a lot of spread of scores between m
Variability also threatens this idea of power and it’s related to sample size because it’s the individual differences in the d
POWER In Designs:
Within-subjects: the most powerful designs. The reason is that we're removing the noise that's added in by individual
Matched-subjects: The next powerful is matched-subject designs. matching on possible extraneous variables. So you
Psychological Inquiry 3 1
, Between-subjects: The least powerful. That's where you have the noisiest data because you're going to have the bigg
💡 So, within-subjects is the most powerful and between-subjects is the least powerful design, and because of tha
Experimental Design Advantages
Within-Subject/Repeated measure design Having the same participants in each condition removes many possible extraneous variables that ca
Within-Subject/Repeated measure design
Within-Subject/Repeated measure design
Within-Subject/Repeated measure design
Within-Subject/Repeated measure design Counterbalance: This is where you randomly vary the order in which people do each condition.
Between-Subject The measures for each condition are independent of one another. So there are no confounding var
Matched-subjects
Matched-subjects
Learning Outcome 2: Distinguish between descriptive and inferential statistics.
1. Descriptive Statistics: Descriptive statistics give us a way to reduce that big list of numbers, that meaningless spreadshee
a. Descriptive statistics summarise and simplify raw data.
b. descriptive statistics allow us to organise, summarise and simplify the raw data, making order out of chaos, so we can e
Mean and Median:
Population Parameters: So these are things like the mean in the population or the standard deviation, which is a measu
Sample Statistics: Sample statistics are written in Roman script, often in italics, so we would use M for the mean of the s
2. Inferential Statistics:
We go from our sample statistic and we infer a population parameter. Inferential statistics are a special branch of maths
Inferential statistics are essential for what we do in psychology because they allow us to make conclusions about popula
Inferential Statistic decide whether sample data represent a particular relationship in the population.
Learning Outcome 3: Organise data in the form of frequency distribution tables and graphs.
1. Frequency Distribution: We want to describe the distribution of our data. We want to have a look at it and see, for example
Frequency distributions show us how many times (f) we observed any particular score (X).
Another definition: A table or graph that displays how many times each score occurs in a sample.
Another thing to note is that if you sum up all of those frequencies, you will get the total number of people in your data s
2. Tables:
a. Regular frequency table:
b. Grouped frequency table: When using this type of frequency table you want to make sure that your group ranges are eq
A grouped frequency table: A type of frequency table where scores are divided into ranges.
Psychological Inquiry 3 2
Psychological Inquiry 3
Class Psychology Foundations: The Social Self
https://docs.google.com/document/d/1JcTYXMhf9TBxPgXpEPaYkrhZL3MAUASpGAUvsHvlSjc/edit https://docs.g
Materials K7ESGA/edit https://docs.google.com/document/d/1W-EKSkJwP4lgVRRfWDZfCmgxLs-dKbZU8j9joCh82qA/edit
Reviewed
Learning Outcomes:
1. Identify the advantages and disadvantages of various types of experimental designs.
2. Distinguish between descriptive and inferential statistics.
3. Organise data in the form of frequency distribution tables and graphs.
4. Calculate and differentiate between the three measures of central tendency (mean, median, and mode).
5. Calculate measures of variability or dispersion (range, variance, standard deviation).
6. Describe the philosophical assumptions underlying big 'Q' qualitative research and what this approach means for research in
Learning Outcome 1: Identify the advantages and disadvantages of various types of experimental designs.
Within-subject designs: recording score of the same person that could be in one setting or at different time points. We compar
Repeated measure designs: ‘Repeated’ and ‘measures’ because you are making repeated measurements with the same pe
To conduct a within-subjects design you:
1. Manipulate the independent variable to create different conditions (e.g., before and after a treatment)
2. Use the same group of participants for each condition
3. Measure the dependent variable for each participant in each condition
4. Compare that dependent variable across the conditions
Between-subject designs (independent measure design): the scores for the different treatment conditions come from differe
To conduct a traditional between-subjects design you:
1. Manipulate the independent variable to create different conditions (e.g., no treatment, treatment 1, treatment 2)
2. Assign people into one of each of those conditions (..if you are in one you can't be in the other)
3. Measure the dependent variable of each participant in each condition
4. Compare the dependent variable across the conditions
Matched-subjects design: tries to get the best of both worlds by combining the within-subjects and between-subjects designs.
Power is the likelihood that you will detect differences between treatment conditions, if there are really differences to detect.
It's the probability of detecting the differences, if there actually are differences to detect.
What affects power?
Size of sample: Sample size is the biggest threat to power is down to your sample size. Between-subjects designs hav
Variability: variability is another threat to power. If I have noisy variable data and so a lot of spread of scores between m
Variability also threatens this idea of power and it’s related to sample size because it’s the individual differences in the d
POWER In Designs:
Within-subjects: the most powerful designs. The reason is that we're removing the noise that's added in by individual
Matched-subjects: The next powerful is matched-subject designs. matching on possible extraneous variables. So you
Psychological Inquiry 3 1
, Between-subjects: The least powerful. That's where you have the noisiest data because you're going to have the bigg
💡 So, within-subjects is the most powerful and between-subjects is the least powerful design, and because of tha
Experimental Design Advantages
Within-Subject/Repeated measure design Having the same participants in each condition removes many possible extraneous variables that ca
Within-Subject/Repeated measure design
Within-Subject/Repeated measure design
Within-Subject/Repeated measure design
Within-Subject/Repeated measure design Counterbalance: This is where you randomly vary the order in which people do each condition.
Between-Subject The measures for each condition are independent of one another. So there are no confounding var
Matched-subjects
Matched-subjects
Learning Outcome 2: Distinguish between descriptive and inferential statistics.
1. Descriptive Statistics: Descriptive statistics give us a way to reduce that big list of numbers, that meaningless spreadshee
a. Descriptive statistics summarise and simplify raw data.
b. descriptive statistics allow us to organise, summarise and simplify the raw data, making order out of chaos, so we can e
Mean and Median:
Population Parameters: So these are things like the mean in the population or the standard deviation, which is a measu
Sample Statistics: Sample statistics are written in Roman script, often in italics, so we would use M for the mean of the s
2. Inferential Statistics:
We go from our sample statistic and we infer a population parameter. Inferential statistics are a special branch of maths
Inferential statistics are essential for what we do in psychology because they allow us to make conclusions about popula
Inferential Statistic decide whether sample data represent a particular relationship in the population.
Learning Outcome 3: Organise data in the form of frequency distribution tables and graphs.
1. Frequency Distribution: We want to describe the distribution of our data. We want to have a look at it and see, for example
Frequency distributions show us how many times (f) we observed any particular score (X).
Another definition: A table or graph that displays how many times each score occurs in a sample.
Another thing to note is that if you sum up all of those frequencies, you will get the total number of people in your data s
2. Tables:
a. Regular frequency table:
b. Grouped frequency table: When using this type of frequency table you want to make sure that your group ranges are eq
A grouped frequency table: A type of frequency table where scores are divided into ranges.
Psychological Inquiry 3 2
