2 Flashcards
In statistics, some categories are classified as qualitative data. Explain why psychologists consider it to be quantitative.
Although the data isn’t numerical, it can be classified into groups and the number of people in each group can be counted up.
What are frequency tables?
They show the number of observations in each group.
Nominal data is data that exists in categories with…
no natural order
Ordinal data is data that exists in categories with…
a natural order
4 types of quantitative data
nominal, ordinal, ratio, interval
ratio data
Takes on number values, for which we can tell exactly how much bigger one value is than the other
interval data
Takes on number values, for which we can tell exactly how much bigger one value is than the other
CAN go below 0
continuous vs discrete data
- discrete data is restricted to certain numbers
- continuous data isnt restricted to certain numbers
example of continuous and discrete data
continuous (height, temperature, blood pressure)
discrete (number of babies, number of cars, shoe size)
which data is continuous?
ratio, interval
which data is discrete?
ratio, interval, nominal, ordinal
5 types of sampling
- volunteer
- opportunity
- systematic
- random
- stratified
volunteer sampling
Volunteer sampling is when researchers post an advert and wait for people to volunteer.
pro of volunteer sampling
con of volunteer sampling
- easy and reaches lots of people
- not representative of the population
opportunity sampling
Opportunity sampling is when a researcher approaches members of the population who are willing and available to be participants.
pro and con of opportunity sampling
- quick and easy way
- not representative of the population
systematic sampling
The third type of sampling is systematic sampling which is when researchers pick every
nth person from the entire
population
pro and con of systematic sampling
- more representative than volunteer/ opportunity
- hard as the researcher needs to obtain AND if there is a pattern in how the data is listed, the sample may not be representative of the population
random sampling
Picking randomly from a list of the entire population, so that everyone has an equal chance of being a participant.
pro and cons of random sampling
- representative as everyone has an equal chance
- need a list AND a way to randomise AND doesn’t guarantee a representative sample
stratified sampling
Stratified sampling is when researchers sample so that their sample has the same proportion of each subgroup as the total population.
stratified sampling process
- First, identify important subgroups within your population.
- Identify how many people from each subgroup are needed to have the same proportion as the original population
- Randomly sample from each subgroup until you get the required number of participants.
pro and con of stratified sampling
- most representative
- may accidentally miss a subgroup AND difficult and time- consuming
x and y axis of frequency graph
x axis is continuous data
y axis is discrete data
histograms
Histograms are graphs that represent frequency counts or frequency for continuous data that has been grouped into categories.
bar charts
Bar charts are graphs that represent
frequency counts for discrete data that has been grouped into categories.
Central tendency
where the middle of the distribution is
Dispersion
how spread out the distribution is
2 features of distribution
central tendency and dispersion
mode
the most frequently occurring value
range
measure of dispersion
the bigger the standard deviation..
the further away the results are from the mean
standard deviation
Standard deviation measures the distance, on average, of the data from the mean
5 steps to calculate standard deviation
To calculate the standard deviation:
1. Find the mean of the set of data.
2. Subtract the mean calculated in step 1 from each individual data point.
3. Square the value calculated in step 2.
4. Find the mean of the squared values in step 3.
5. Finally, find the square root of the mean calculated in step 4
3 ways to measure central tendency
mode, mean, median
2 ways to measure dispersion
standard deviation, range
what do pie charts present?
proportions/ percentages
in normal distribution:
1SD
2SD
3SD
1sd = 68%
2sd = 95%
3sd = 99%
Inference
taking something we can observe to make a conclusion about something we can’t observe.
As the t-value gets bigger, the probability gets…
and the _____ likely the null hypothesis is correct
smaller
less
3 factors affecting t value
- difference in mean
- dispersion
- sample size
p value
probability of observing our results if the null hypotheses is correct
type 1 error
researchers incorrectly reject the null hypotheses and say there is a real difference between 2 experimental groups, when really there isn’t
significance level
The significance level tells us how likely we are to make a type 1 error.
type 2 error
Researcher fails to reject a null hypothesis which is really false. Here a researcher concludes there is not a significant effect, when actually there really is.
significance level to balance risk of type 1 and 2 error
To balance the risk of a Type 1 and Type 2 error, we set the significance level to 5 %.
degrees of freedom
The total sample size across the two groups subtract 2.
Primary vs secondary data
Primary data- you get yourself
Secondary data - already existing
