Statistical Reasoning Notes

Statistical Reasoning Notes
Researchers must be very critical when viewing statistical information. Graphs
information can also be manipulated and large numbers misleading.
Remember that data can be conveyed in two ways in order to generate statistical
1. Central tendency measures: mean, median and mode
2. Measures of variation: range and standard deviation
Remember too that a few atypical scores can distort central tendency!
When making inferences from data, it is important to keep these things in mind:
1. Representative samples are better than biased samples.
2. Less variable observations are more reliable than those that are
more variable.
3. More cases are better than fewer.
Psychologists are less concerned with particular behaviors and are more focused on
finding general principles that explain behavior. Psychologists use inferential statistics to
test the hypothesis they generate.
Null hypothesis – Predicts that the treatment will have no effect in
an experiment
Alternative Hypothesis – Predict that a treatment will have an effect.
Inferential statistics allow researchers the possibility of rejecting or accepting the null
hypothesis with a certain level of confidence. Tests such as this are significant because
they enable researchers to examine whether the effects are likely
because of treatment or a normal variation amongst the
sample population.
Researchers in psychology do not want to conclude that differences exist if in fact they
do not. Two primary errors occur when testing a hypothesis:
Type I error – Refers to the conclusion that a difference exists
when in fact it does not.
Type II error – Refers to the conclusion that there is no
difference when in fact there is.
Note that statistical decisions are made using the following model
The Null is TRUE
The Null is FALSE
Correct decision!
Type I error
You accept the null
Type II error
Correct decision!
You reject the null