P-Values and NHST Flashcards
What is the relevance of probability to psychological experiments?
Statistics allow psychologists to present data in ways that are easier to comprehend. Visual displays such as graphs, pie charts, frequency distributions, and scatterplots make it possible for researchers to get a better overview of the data and to look for patterns that they might otherwise miss
Probability refers to the likelihood of an event occurring. … Statistical tests allow psychologists to work out the probability that their results could have occurred by chance, and in general psychologists use a probability level of 0.05. This means that there is a 5% probability that the results occurred by chance.
The main purpose(s) of inferential statistical tests are
population. The purpose is to answer or test the hypotheses. A hypothesis (plural hypotheses) is a proposed explanation for a phenomenon. Hypothesis tests are thus procedures for making rational decisions about the reality of observed effects. Probability is the measure of the likelihood that an event will occur. Probability is quantified as a number between 0 and 1 (where 0 indicates impossibility and 1 indicates certainty).
The purpose of inferential statistics is to determine whether the findings from the sample can generalize - or be applied - to the entire population. There will always be differences in scores between groups in a research study.
An experimental / alternate hypothesis is
Alternative hypothesis (H1 and Ha) denotes that a statement between the variables is expected to be true.
The null hypothesis is
In inferential statistics, the term ‘null hypothesis’ (H0 ‘H-naught,’ ‘H-null’) denotes that there is no relationship (difference) between the population variables in question.[
Cut-off for significance is
The P value (or the calculated probability) is the probability of the event occurring by chance if the null hypothesis is true. The P value is a numerical between 0 and 1 and is interpreted by researchers in deciding whether to reject or retain the null hypothesis
In the majority of analyses, an alpha of 0.05 is used as the cutoff for significance. If the p-value is less than 0.05, we reject the null hypothesis that there’s no difference between the means and conclude that a significant difference does exist. If the p-value is larger than 0.05, we cannot conclude that a significant difference exists.
Below 0.05, significant (p < 0.05 = results are significant, so reject the null)
Over 0.05, not significant (p > 0.05 => results are not significant, so do not reject the null hypothesis)
p = 0 (an event which is certain not to happen) p = 1 (an event which is certain to happen) p = .5 (an event which is just as likely to happen as it is not to happen)
Benefits of effect sizes are
Effect size is a quantitative measure of the magnitude of the experimenter effect. The larger the effect size the stronger the relationship between two variables. You can look at the effect size when comparing any two groups to see how substantially different they are.
You can look at the effect size when comparing any two assessment results to see how substantially different they are. For example, you could look at the effect size of the difference between your pre- and post-test to learn about how substantially your students knowledge of the subject tested changed as a result of your course.
Because the standard deviation includes how many students you have, using the effect size allows you to compare teaching effectiveness between classes of different sizes more fairly. Effect size is a popular measure among education researchers and statisticians for this reason.
What is the effect size proposed by Cohen?
Large: 0.8
Medium: 0.5
Small: 0.2
What is the difference between the null and alternative hypotheses?
Ho states there will not be a difference
e.g. no difference between males & females in verbal ability
H1 states there will be a difference
e.g. males score differently than females in verbal ability
We make the assumption that the null hypothesis is true and then find the probability of obtaining our pattern of findings as a result of ‘sampling error’ i.e. happens by chance.
What is a sample error?
In statistics, sampling error refers to the amount of inaccuracy that is estimated to exist within a sample population of the trait being measured. More simply put, since psychological and social science experiments use samples of people or animals during experiments (since we obviously cannot use the entire human population), it’s accepted that a sample population doesn’t absolutely reflect the precise reality of the population as a whole. Therefore, a sampling error is calculated to reflect how accurate the results of a study actually are.
When we randomly select samples from a population there will be minor differences between them
The differences between them are the result of sampling error (i.e. chance)
Statistical analyses tell us how likely the differences we observe are due to sampling error
How can a sample error be reduced?
The sampling error can be reduced by increasing the sample size. If the sample size n is equal to the population size N, then the sampling error is zero. … This method is called stratified-random sampling.
How do we know if we can/can’t reject the Ho?
Use inferential statistics!
Used so that we can make inferences/generalisations about populations from our samples
Help us determine if the difference* in our data scores is due to chance or not
Probability
Probability refers to the likelihood of an event occurring. It can be expressed as a number (0.5) or a percentage (50%). Statistical tests allow psychologists to work out the probability that their results could have occurred by chance, and in general, psychologists use a probability level of 0.05.Probability
A likelihood that an event will occur e.g., what is the probability of there being an ace at the top of a deck of (shuffled) cards?
How is probability expressed in numbers?
p = 0 (an event which is certain not to happen) p = 1 (an event which is certain to happen) p = .5 (an event which is just as likely to happen as it is not to happen)
Are findings due to chance?
If the probability that your findings have occurred due to chance is sufficiently low, then the inference is that your results did not occur due to chance
What is standard deviation?
Standard deviations are scores around the mean of a distribution. It measures how much a set of scores is dispersed around an average measure of variability. Deviations around the mean can be calculated to express it as a variance or a standard deviation.
Standard dev`iations are a measure of the variance in our data – small SD indicate little variance in scores, large SD suggest quite a lot of variability in your scores.
Shows the average of scores away from the mean
