Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
58 Cards in this Set
- Front
- Back
- 3rd side (hint)
p- values,
|
the probability that whatever pattern or difference found in data came across by chance
|
|
|
by chance
|
|
|
|
Null hypothesis,
|
means there is no difference/pattern in data
|
|
|
Cut off rate for p value,
|
0.05
|
|
|
Discrete/ categorical,
|
nominal and ordinal
|
|
|
Continuous/ numeric,
|
interval and ratio |
|
|
Interval,
|
no absolute zero , can’t multiply or divide values e.g. temperature
|
|
|
Ratio,
|
absolute zero, arithmetically meaningful, add subtract multiply divide
|
|
|
Interquartile range,
|
difference between 1st and 3rd quartile
|
|
|
Variance,
|
the average distance from the mean
|
|
|
Standard deviation,
|
square root of variance
|
|
|
Central limit theorem,
|
the sampling distribution of the sample mean approximates the normal distribution
|
|
|
Histograms,
|
continuous data, shows frequency
|
|
|
Bar Charts,
|
discrete data, shows frequency |
|
|
Box whisker plot,
|
shows median, quartiles, min, max and outliers |
|
|
Scatter plot,
|
continuous data, relationship between two variables |
|
|
Error bar chart,
|
shows mean and 95% confidence intervals
|
|
|
Pie charts,
|
discrete data, shows proportions
|
|
|
Unimodal,
|
one peak in the distribution |
|
|
Normal distribution,
|
mean, mode and median are the same, a symmetrical distribution
|
|
|
Skewness,
|
is a measure of the asymmetry of the probability distribution of a real-valued random variable about its mean
|
|
|
Kurtosis,
|
describes how pointy the distribution is
|
|
|
Leptokurtic,
|
pointy distribution
|
|
|
Mesokurtic,
|
similar to a normally distributed data set |
|
|
Platykurtic,
|
almost flat |
almost flat
|
|
Rules for normal distribution,
|
If skewness and kurtosis aren’t 2x standard error score means you have a normal distribution |
If skewness and kurtosis aren’t 2x standard error score means you have a normal distribution
|
|
Why is normal distribution useful?,
|
We know the probability of a score falling within certain number
|
|
|
|
|
|
|
Z scores,
|
converting your real scores to standardized scores, which follow the normal distribution
|
|
|
t-test,
|
examines whether two sample means are different
|
|
|
one smaple t-test,
|
tests whether mean of a sample is different to a specific number
|
|
|
within groups t-test,
|
compares mean of same sample in two different conditions
|
|
|
between groups t-test,
|
compares mean of two different samples in different conditions
|
|
|
p = .001,
|
means we’ve got a significant difference
|
|
|
Wilcoxon’s signed ranks test,
|
nonparametric equivalent to the paired samples t-test converts data to ranks
|
|
|
Mann-whitney’s U,
|
nonparametric equivalent to independent samples t-test
|
|
|
Levene’s test,
|
an inferential statistic used to assess the equality of variances for a variable of two or more groups
|
|
|
Correlation,
|
the similarity of 2 variables within a group
|
|
|
Positive relationship,
|
as one variable increases, the other increases
|
|
|
Negative relationship,
|
as one variable increases, the other decreases
|
|
|
|
|
|
|
|
|
|
|
Third variable,
|
there’s a third variable causing the relationship
|
|
|
Variance,
|
is a measure of dispersion |
|
|
Covariance,
|
how much the two variables vary together
|
|
|
Pearson’s r,
|
a measure of the linear dependence between two variables
|
|
|
Pearson’s r scores,
|
1- a perfect positive relationship, 0 – no relationship, -1 – a perfect negative relationship
|
|
|
Pearson’s r assumes…,
|
a linear relationship
|
|
|
95% Confidence intervals,
|
means we can be 95% confident the population will fall into upper and lower bounds
|
|
|
R2 ,
|
tells how much shared variance between your variables
|
|
|
R2 = 1,
|
(100% shared variance between two variables)
|
|
|
R2 = .25,
|
25% shared variance between two variables
|
|
|
Spearman’s P,
|
the non parametric equivalent to Pearson’s r, converts scores to ranks than uses Pearsons equation
|
|
|
Partial correlation,
|
if there are say three variables we can partial out one variable
|
|
|
Correlation coefficients,
|
used to measure how variables covary with each other |
|
|
Univariate graph,
|
a graph with only one variable e.g. histogram
|
|
|
Statistical tests,
|
t-test and correlation test
|
|
|
Bivariate data,
|
two variables represented at the same time e.g. scatter plot
|
|