Statistics Flashcards
denominator
name for the bottom half of a formula
descriptive
Statistics that describe an aspect of data (e.g. mean, median, mode, variance, range)
inferential
Statistics that allow you to make predictions about or comparisons between data (e.g., t-value, F-value, rho)
interval estimates
a range of values that summarise an aspect of a data set. Examples include the range, variance, standard deviation, standard error and confidence intervals.
mean
A descriptive statistic that measures the average value of a set of numbers
median
The middle number in a distribution where half of the values are larger and half are smaller
numerator
name of the top half of a formula
participant
the word used to describe someone who has taken part in a study. Note that subject is outdated and no longer used
point estimates
a single value that summarises an aspect of a data set. Examples include the mean, median, and the mode.
population
All members of a group that we wish to generalise our findings to
sample
a subset of the population that you wish to make an inference about through your test
Parametrics
Rules or assumptions about the data that must be confirmed before we use a specific test, otherwise the findings would be meaningless. Examples: t-tests, pearson correlation, single regression, multiple regression
Spread
Degree of dispersion (variability) of values in a dataset
Range
least informative, lowest value to highest value
Interquartile Range
summarising values between the 25th and 75th percentile and captures 50% of the distribution
Variance
a measure of spread which uses information from all the scores in a dataset - averaged squared deviated from the mean
steps of calculation:
1. Find the difference between value and the mean
2. square the difference
3. sum all the squared differences together
4. Divide by N-1
Standard Deviation (SD)
measure of the average deviation from the mean in the original scale, using all the values in the data set
steps of calculation:
1. Find the difference between each value and the mean.
2. Square each difference
3. Sum all the squared differences together
4. Divide by N-1
5. Take the square root
Standard Error of the Mean (SEM)/(SE)
A statistical measure that describes how much the sample mean is expected to vary from the true population mean
calculated by dividing the SD by the square root of the number of values
Probability
the likelihood of the occurrence of an event or outcome
p = number of ways the event could arise/number of possible outcomes
joint probability
the unrelated events occurring at the same time. calculated by multiplying together the probability of each individual event
replacement
resetting the number of outcomes to the original value after an event occurs
Binomial distribution
a discrete distribution in which every event has a probability on a given distribution
A statistical distribution that summarises the probability that a value will take one of the two independent values under a given set of parameters or assumptions
Normal distribution
a theoretical distribution with a particular bell shape. the peak of the distribution corresponds to the mean, mode, median = 0 and the SD = 1
Null hypothesis significance testing (NHST)
A technique for establishing if a hypothesis is likely based on the probability of finding a value as large as or larger, than the one you have found, if the null hypothesis was true
null hypothesis
there is no difference or relationship
level of significance (alpha)
the probability level at which we reject the null hypothesis, usually a = .05
Rejection region
a portion of a sampling distribution which includes samples with probabilities less than alpha
z-score
the number of standard deviations any particular score is away from the mean
calculated by subtracting the mean from the value and dividing it by the SD
one sample chi-square test
method of investigating the probabilities of values being in specific categories/groups. used when dealing with frequencies rather than scores. Assumes independents samples and nominal scale data (categorical data).
observed frequencies
counts per category, expected: most basic approach is equal likelihood of each option
expected frequencies
represent a uniform frequency distribution expected under H0 (no preference)
degrees of freedom
the number of observation (units/data points) that are free to vary to produce a given outcome
for one sample chi square calculated as: k-1 (k is number of conditions)
for cross tabulation chi squares: calculated as (R-1) * (C-1) where R refers to number of rows and C to number of columns
effect size
a common effect size for the chi quare test is phi. it is a standardised measure of the difference of interest that is comparable across experiments that use different N
alpha
pre-determined level of significance at which we agree to reject the null hypothesis
p (p-value)
the probability of finding a test statistic as large or larger than the one found in your study, if the null hypothesis were true
cross tabulation chi square tests
tests whether variable A and B are related in producing the observed frequency distribution
t test
inferential test used to compare between two samples/conditions or between one sample and a criteria
t value
t value is the ratio between two aspects of the data
difference between group means/variability about the group means
one sample t test
compare one sample against a known test value
Assumptions: interval/ratio data, independent scores, data approximately normally distributed
within subjects t test
compare two conditions where it is the same participant in each condition
Assumptions: continuous data, difference is normally distributed
between samples t test
compare two groups or conditions where the participants are different in each group and have not been matched
Assumptions: continuous data, independent scores, approximately normally distributed, homogeneity of variance
Order of a results section
- Restate hypotheses
- Check assumptions
- Descriptives
- Inferentials
- Accept/reject hypothesis with Brief interpretation