Applied Statistics 1 Flashcards
What are the two types of variable?
- Scale
- Categorical
What are the two types of scale variable?
- Continuous
- Discrete
What is a continuous variable?
Measurement on a continuous numerical scale
What are the two types of categorical variable?
- Ordinal
- Nominal
What is an ordinal variable?
Categories that can be ordered lor ranked
What is a nominal variable?
Categories with no meaningful order
What is the definition of a sample?
all of the subjects/ items that we collect data from in the study
What is the definition of a population?
All of the possible subjects/ items that could have been included in the study
What are descriptive statistics?
Statistics that summarise the data observed for the sample
What are inferential statistics?
Methods which use the data from the sample to try to make conclusions about a wider population
What are descriptive statistics?
- Generate summaries to describe key features of the dataset
- Organise and present our data in a meaningful way
- reduce a large amount data to a few relevant pieces of information
- Highlight potential relationships between variables
What is Central Tendency?
What is the average value?
What is the definition of variability?
How spread out the values are
What is the definition of Distribution?
How many times each value occurs
What does a bar chart present?
- Counts/ Percentages
- Can see the mode visually
What does a frequency table present?
Presents counts or percentages
What do bivariate statistics describe?
Two variables together
What do inferential statistics describe?
Use the data from a sample to try make conclusions about a wider population
When would you use a parametric test?
Use when the DV is continuous and test assumptions are satisfied
When would you use a non-parametric test?
Use when the DV is ordinal, or DV is continuous
What is the chi-squared test?*
* used for
Use to investigate whether there is an associated between two categorical variables
What is the fishers exact test?
Alternative to the chi-squared test when assumptions about expected frequencies are not met
What is pearsonns correlation?
Parametric method which explores the strength and direction of a linear relationship between two continuos variables
What is simple linear regression?
The next step on from pearsonns correlation, used to predict the values of one of the variables (DV) based on the (IV)
What do both Pearsons and Spearmanns correlations produce?
they produce a **correlation coefficient ** which is a value between -1 and 1 that indicates the strength and direction of the relationship between two variables
When should you not use a parametric test?
when assumptions are not met as it may lead to an invalid result
What is a normal distribution?
Symmetric probability distribution which follows a bell-shaped curve
What does it mean when a variable is normally distributed?
values follow a pattern of a normal distribution
What does the confidence interval give us?
Range of values around a parameter estimate within which we can reasonable confident that the true value lies
What effects the width of the confidence interval?
- Standard error
- Confidence level
What does hypophysis testing begin with?
It begins with a research question- exploring a link between two variables
What does a statistical test always assume?
Always assumes the null hyphophysis is true
What is the definition of a p value?
The probability of observing a result that is equal to or more extreme than that for your data, assuming that the null hypophysis is true
What is the purpose of the significance level?
If the p level is below the threshold, null hyophysis is rejected and the result is statistically significant
What is a false positive?
Rejecting the null hyopophysis when it is true
What is a false negative?
You do not reject the null hypophysis when it is false
What is the definition of power?
The probability of rejecting the null hypophysis when we should
What is the definition of effect?
the difference/association/relationship being investigated between groups or variables in a study
What is the definition of effect size?
The Size/ Strength of the effect
What is a one-tailed test?
A one-tailed test is a test where the alternative hypophysis specifies a specific direction of the effect/ relationship
What is a two-tailed test?
allocates half of your alpha to testing statistical significace in one direction and the other half to testing significance in the other direction
