4 stats test, accepted significance level, type one and two errors, reducing the risk of these errors

HideShow resource information
  • Created by: charlotte
  • Created on: 29-05-13 14:59

Statistical Tests

Statistical Tests

  • Mann-Whitney
  • Wilcoxon
  • Chi-Square
  • Spearman's Rho
1 of 4

Accepted Significance Level

Accepted Significance Level


Why do we use this significant level?

Researchers usually accept results as significant if the probability of them being due to chance is not more than 5%, the generally accepted level of significance

When is a finding significant?

The experimental hypothesis will be accepted when p<0.05 this means the probability of the results being due to chance is less than 5% so there is an effect

The null hypothesis will be accepted with p>0.05 which means that the probability of the results being due to chance is more than 5%

2 of 4

Type One and Two Errors

Type One Errors

We wrongly accept the experimental hypothesis when the null hypothesis is true

This is an optimistic error

The researcher has concluded that there is a difference between the variables when there isn't

These are more likely to occur at lenient significant levels e.g. p<0.10

Type Two Errors

We wrongly accept the null hypothesis when the experimental hypothesis is true

This is a pessimistic error

Concluded there is not a difference between variables when there is

More likely at stricter levels of significance e.g. p<0.01

3 of 4

Level of Data

Nominal Level Data

Categories of information

E.g. Males and females with blue eyes

Ordinal Data

Ranking data in order

E.g. Places in a rowing competition

Interval Ratio Level Data

Points on a measuring scale

E.g. Possible for date to be 10cm

4 of 4


No comments have yet been made

Similar Psychology resources:

See all Psychology resources »