Essential theory Flashcards
Choice of statistic, or statistical test, depends
on 4 things
What are they?
- Scale of measurement
- Research aims
- Experimental design
- Properties of dependent/outcome variable
What are the 3 types of research aims?
- Descriptive only
- Relational (correlation)
- Experimental (differences)
What type of test do we use for normally distributed data?
Parametric
What type of test do we use for not normally distributed data?
Non-parametric
What 3 things do we look for in an experiment based on its experimental design?
- Subjects design (between or within)
- Number of independent variables (IVs)
- Number of IV levels
What are the 4 types of scales of measurement?
- Nominal
- Ordinal
- Interval
- Ratio
- Nominal
- Ordinal
- Interval
- Ratio
These are…?
Scales of measurement
Which scales of measurement are used for categorical data?
Nominal
Which scales of measurement are used for discrete or continuous data?
- Ordinal
- Interval
- Ratio
What is nominal data?
Numbers or names serve as labels but no numerical relationship between values
e.g. gender, political party, religion
Numbers or names serve as labels but no numerical relationship between values
e.g. gender, political party, religion
This is known as…?
Nominal data
What is ordinal data?
Data is organised by rank
Values represent true numerical relationships but intervals between values may not be equal
e.g. race position, likert scale ratings
What is interval data?
True numerical relationships and intervals between values are equal but scale has not true zero point
e.g. temperature (ºF), shoe size
What is ratio data?
True numerical relationships, equal intervals and true zero point
e.g. height, distance
Data is organised by rank
Values represent true numerical relationships but intervals between values may not be equal
e.g. race position, likert scale ratings
This is known as…?
Ordinal data
True numerical relationships and intervals between values are equal but scale has not true zero point
e.g. temperature (ºF), shoe size
This is known as…?
Interval
True numerical relationships, equal intervals and true zero point
e.g. height, distance
This is known as…?
Ratio
A study’s research aim is to describe
What descriptive statistics should be used?
Summarise a set of sample
values
What research aim does not allow us to make predictions and infer causality?
The research aim to describe
What are the 2 statistics used in a study following the research aim of describing?
- Central tendency
- Spread
What are the 3 types of measure of central tendency?
- Mean
- Median
- Mode
What are the 2 types of measure of spread?
- Standard deviation
- Range
When do we use the mean as a measure of central tendency?
When data is:
- Discrete or continuous
- Normally distributed
When data is:
- Discrete or continuous
- Normally distributed
We use…?
a. Mode
b. Mean
c. Median
b. Mean
When do we use the median as a measure of central tendency?
When data is:
- Discrete or continuous
- Not normally distributed
When data is:
- Discrete or continuous
- Not normally distributed
We use…?
a. Mode
b. Mean
c. Median
c. Median
When do we use the mode as a measure of central tendency?
When data is categorical
When do we use standard deviation as a measure of spread?
When data is:
- Discrete or continuous
- Normally distributed
When data is:
- Discrete or continuous
- Normally distributed
We use…?
a. Standard deviation
b. Range
a. Standard deviation
When do we use range as a measure of spread?
When data is:
- Discrete or continuous
- Not normally distributed
When data is:
- Discrete or continuous
- Not normally distributed
We use…?
a. Standard deviation
b. Range
b. Range
Relational research explore …?
The relationship between observed behaviours or phenomena
True or False?
Relational research actively manipulate variables
False
Nothing is actively manipulated in relational research
What type of research aim allows us to make predictions but not infer causality?
Relational research
Explores relationship between observed behaviours or phenomena
a. Describe
b. Infer differences
c. Infer relationships
c. Infer relationships
Summarise a set of sample
values
a. Describe
b. Infer differences
c. Infer relationships
a. Describe
Examines the influence of one or more variables (IVs) on other variables (DVs)
a. Describe
b. Infer differences
c. Infer relationships
b. Infer differences
Experimental research examines …?
The influence of one or more variables (IVs) on other variables (DVs)
We cannot make predictions or claims of causality
a. Describe
b. Infer differences
c. Infer relationships
a. Describe
We can make predictions but not claims of causality
a. Describe
b. Infer differences
c. Infer relationships
c. Infer relationships
We can make predictions and claims of causality if confounding variables are controlled for
a. Describe
b. Infer differences
c. Infer relationships
b. Infer differences
True or False?
We can always make claims about causality regardless of whether we have controlled for confounding variables
False
We can only make claims about causality IF we have controlled for confounding variables
How does experimental research control for confounding variables?
List 2 ways
- Random allocation (between-subjects)
- Counterbalancing (within-subjects)
When is controlling for confounding variables not possible?
Quasi-experimental design
What type of research manipulates a small number of variables to measure the effect of the manipulated variables?
a. Descriptive
b. Relational
c. Experimental
c. Experimental
What is an IV?
Hypothesised to influence the DV
The IV is measured on a ____ scale
a. Categorical
b. Discrete
c. Continuous
a. Categorical
What is a DV?
Hypothesised to be ‘dependent’ on the IV
The DV is measured on a ____ scale
a. Categorical
b. Discrete
c. Continuous
b. Discrete
c. Continuous
Why do we measure the DV under different levels of the IV?
To determine the effect of the IV
How do we determine the effect of the IV?
We measure the DV under different levels of the IV
List 2 characteristics of true-experimental IVs
- IVs are actively manipulated
- Random allocation is possible (can make claims about causality)
List 2 characteristics of quasi-experimental IVs
- IV reflects fixed characteristics
- Random allocation is not possible (must be cautious about implying causality)
IVs are actively manipulated
This applies to…?
a. True experimental IVs
b. Quasi-experimental IVs
a. True experimental IVs
IV reflects fixed characteristics
This applies to…?
a. True experimental IVs
b. Quasi-experimental IVs
b. Quasi-experimental IVs
Random allocation is possible (can make claims about causality)
This applies to…?
a. True experimental IVs
b. Quasi-experimental IVs
a. True experimental IVs
Random allocation is not possible (must be cautious about implying causality)
This applies to…?
a. True experimental IVs
b. Quasi-experimental IVs
b. Quasi-experimental IVs
Handedness (2 levels: right, left) is an example of a…?
a. True experimental IV
b. Quasi-experimental IV
b. Quasi-experimental IV
Treatment group (3 levels: placebo, drugs, counselling) is an example of a…?
a. True experimental IV
b. Quasi-experimental IV
a. True experimental IV
Sport context (2 levels: solo, competitive) is an example of a…?
a. True experimental IV
b. Quasi-experimental IV
a. True experimental IV
Age (3 levels: 18-20yrs, 20-22yrs, 22-24yrs) is an example of a…?
a. True experimental IV
b. Quasi-experimental IV
b. Quasi-experimental IV
Distribution of participants across IV levels is known as…?
Subjects design
What is subjects design?
Distribution of participants across IV levels
Participants exposed to only one IV level
a. Between-subjects (Independent Groups)
b. Within-subjects (Repeated Measures)
c. Mixed
a. Between-subjects (Independent Groups)
Participants exposed to all IV levels
a. Between-subjects (Independent Groups)
b. Within-subjects (Repeated Measures)
c. Mixed
b. Within-subjects (Repeated Measures)
At least one IV is between subjects AND at least one IV is within subjects
a. Between-subjects (Independent Groups)
b. Within-subjects (Repeated Measures)
c. Mixed
c. Mixed
Intervention vs. control group
a. Between-subjects (Independent Groups)
b. Within-subjects (Repeated Measures)
c. Mixed
a. Between-subjects (Independent Groups)
Sober vs. drunk
a. Between-subjects (Independent Groups)
b. Within-subjects (Repeated Measures)
c. Mixed
b. Within-subjects (Repeated Measures)
At the end of Year 1, Year 2 and Year 3 of Uni
a. Between-subjects (Independent Groups)
b. Within-subjects (Repeated Measures)
c. Mixed
b. Within-subjects (Repeated Measures)
Teachers vs. accountants vs. nurses
a. Between-subjects (Independent Groups)
b. Within-subjects (Repeated Measures)
c. Mixed
a. Between-subjects (Independent Groups)
An investigator is interested in whether right and left-handed people differ in their performance on different types of computer-games (his theory is that left-handed people will have an advantage on games requiring better visuo-spatial skills). He measures the scores of 30 right handers and 30 left handers who each play Daley Thompson’s Decathlon, Horace Goes Skiing & Tetris
What is the…?
a. IV(s)
b. IV(s) levels
c. DV
d. Subjects design
a. Handedness, Games
b. 2 (right and left), 3 (Decathlon, Horace and Tetris)
c. Performance on computer games
d. Mixed
What analysis do you perform on an experimental study with 1 IV and 2 levels and participants are exposed to only one IV level?
Independent t-test
What analysis do you perform on an experimental study with 1 IV and 2 levels and participants are exposed to all IV levels?
Paired t-test
What analysis do you perform on an experimental study with 1 IV and more than 2 levels and participants are exposed to only one IV level?
One-way independent ANOVA
What analysis do you perform on an experimental study with 1 IV and more than 2 levels and participants are exposed to all IV levels?
One-way repeated measures ANOVA
What analysis do you perform on an experimental study with 2 IVs and participants are exposed to only one IV level?
Two-way independent ANOVA
What analysis do you perform on an experimental study with 2 IVs and participants are exposed to all IV levels?
Two-way repeated measures ANOVA
What analysis do you perform on an experimental study with 2 IVs and participants are exposed to all IV levels for one IV and only one level for the other IV?
Two-way mixed ANOVA
What are the properties of normal distribution?
List 2
- Symmetrical about the mean
- Bell shaped (suggests majority of the scores cluster close to the mean)
What are the 3 types of kurtosis?
- Mesokurtic
- Platykurtic
- Leptokurtic
Which kurtosis can we use for parametric statistics?
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
a. Mesokurtic
Which kurtosis can we use for non parametric statistics?
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
b. Platykurtic
c. Leptokurtic
Which kurtosis is used when data is normally distributed/bell shaped?
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
a. Mesokurtic
Which kurtosis is used when data is more varied (the distribution peak is flatter and peak at the mean is lower?
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
b. Platykurtic
Which kurtosis is used when data is less varied (the distribution peak is higher at the mean and the spread is narrow)?
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
c. Leptokurtic
Which kurtosis is used when data has a large SD?
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
b. Platykurtic
Which kurtosis is used when data has a small SD?
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
c. Leptokurtic
Which kurtosis value is -ve
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
b. Platykurtic
Which kurtosis value is +ve
a. Mesokurtic
b. Platykurtic
c. Leptokurtic
c. Leptokurtic
What does data with no skew look like?
The tail of a distribution curve is bell shaped
What does data with positive skew look like?
The tail of a distribution curve is longer on the right side (towards positive values on the x axis)
What does data with negative skew look like?
The tail of a distribution curve is longer on the left side (towards negative values on the x axis)
What is bimodal data?
Data with 2 modes
What is uniform data?
Looks like categorical data lined up instead of a curve
True or False?
Bimodal and uniform data are normally distributed
False
They are not normally distributed
We use sample statistics to infer …?
Population parameters
True or False?
We use population parameters to infer sample statistics
False
We use sample statistics to infer population parameters
What is Sampling Error?
The degree to which sample statistics differ from underlying population parameters
The degree to which sample statistics differ from underlying population parameters
This is known as…?
Sampling error
What are the 2 ways we can minimise error?
Sample size must be:
- Representative (randomly selected)
- Sufficient in size
Scores from a normally
distributed population can be converted to z -scores
What is the z-score formula?
z = (x - pop. mean) / sample mean
Percentage of scores within single standard deviation boundaries
This is known as…?
Standard Normal Distribution
What is Standard Normal Distribution?
Percentage of scores within single standard deviation boundaries
What is sampling distribution?
Distribution of a statistic
across an infinite number of samples (e.g. sampling distribution of the mean)
Distribution of a statistic
across an infinite number of samples (e.g. sampling distribution of the mean)
This is known as…?
Sampling distribution
Plotting all possible sample means gives us the …?
Sampling distribution of the mean
Plotting all possible sample means gives us the sampling
distribution of the mean
Its mean is equivalent
to the …?
Population mean
Plotting all possible sample means gives us the sampling
distribution of the mean
Its standard deviation
is given a special name …?
The standard error
The standard deviation
of the sampling distribution is known as..?
The standard error
What is the standard error?
The standard deviation
of the sampling distribution
As sample size increases, the standard error …?
Decreases
The standard error decreases as sample size
increases
What does this suggest?
Sampling error decreases as sample size increases
An estimate of the standard error, based on our sample
This is known as…?
Estimated standard error
What is ESE?
An estimate of the standard error, based on our sample
What is the formula for ESE?
ESE = SD / sqrt sample size
What are the 3 characteristics of sampling distribution of the mean?
- Mean equivalent to the
population mean - Standard deviation is the
‘standard error’ - Always normally distributed
True or False?
5% of all sampled
means will fall within ±1.96
standard errors of the
population mean
False
95% of all sampled
means will fall within ±1.96
standard errors of the
population mean
What are CIs?
Interval estimates of population parameters
Interval estimates of population parameters
This is known as…?
CI
We use 95% CI in psychology
What does this suggest?
We are declaring that there is still a chance that our
estimates are wrong
There’s a 5% chance that the population mean falls above/below the 95% CI limits
If there’s a 95% chance that the sample mean falls within the 95% bounds of the population mean, it follows that…?
There’s a 95% chance that the population mean falls within the 95% CIs of the sample mean
Is this H1 or H0?
There is no difference
between the population means
H0
The probability of measuring a difference of that magnitude if the null hypothesis is true
This is known as…?
p value
What is a p value?
The probability of measuring a difference of that magnitude if the null hypothesis is true
Threshold level of probability where we will be willing to reject the null hypothesis
This is known as…?
alpha value
What is alpha value?
The threshold level of probability where we will be willing to reject the null hypothesis
If p < 0.5 ____ the hull hypothesis
Reject
What is type 1 error?
When H0 is true but you reject it
What is type 2 error?
When H0 is false but you fail to reject it
When H0 is true but you reject it
Is this…?
a. Type 2 error
b. Type 1 error
b. Type 1 error
When H0 is false but you fail to reject it
Is this…?
a. Type 2 error
b. Type 1 error
a. Type 2 error
