Null Hypothesis Testing

If an outcome has a high probability of occurring if the null hypothesis is true, what decision should the researcher make?

If there is a high probability of getting those data (it is likely that the score we got could have happened by chance alone), we retain the null hypothesis (we say there is no difference)

Which of the following is false about inferential statistics?

Inferential statistics always starts with the assumption that there is an effect

Sampling error

Natural discrepancy (or amount of error) between a sample statistic and its corresponding population parameter.

1. State the hypotheses

Null hypothesis (Ho) ; in the general population, there is no change, no difference, or no relationship. Alternative hypothesis (H1) : there is a change, a difference, or relationship in the general population.

H1

Our sample mean is different from the sample mean

Ho

Our sample mean is not different from the population mean

Set critiera 3: Alpha (a)

Probability value set by the experimenter to define the point at which a value is 'very unlikely' a= 0.05 a=0.01

Even if a treatment has no effect it is still possible to obtain an extreme sample that is very different from the population. What outcome is likely if this happens?

Reject the null hypothesis and make a type I error

Which of the following would be an example of a null hypothesis?

There is no effect

Inferential tests are

Used to determine whether or not the null hypothesis is true.

Set criteria 1 : divide the distribution of sample means

Values that are likely to occur is Ho is true. Values that are "very unlikely" if h0 is true

Null hypothesis testing (4 steps)

a statistical method that uses data from a sample to evaulate a hypothesis about a population

A type II error is defined as

failing to reject a false null hypothesis (occurs when in reality the null hypothesis is false, but we have retained it. No error has occured either when we reject a null hypothesis that was false or retain a null hypothesis that was true.

In general, the null hypothesis

generally compares the sample and population means and states that there is no difference between two scores.

In general, increasing the alpha level (for example from .01 to .05) will

increase the likelihood of rejecting the null hypothesis and increase the risk of a Type I error

The probability of committing a Type I error

is determined by the level of significance (a, alpha) that one chooses.

Interential Statistics are probablisitic,

meaning they rely on the laws of probability and are used to make conclusions (or inferences) about the population based on a sample.

A type I error is defined as

rejecting a true null hypothesis (False positive) occurs when in reality the null hypothesis is true, but we have rejected it.

If a treatment has a very small effect, then a hypothesis test evaluating the treatment effect is likely to,

result in a type II error

All Inferential statistics start with

the null hypothesis (the assumption that there is no effect) and the calculation of the probability of getting a particular set of data if the null hypothesis were true.

Set Critieria 2 (critical regions)

values that are "very unlikely" to occur if Ho is true

No error has occured either when

we a reject a null hypothesis that was false or retain (fail to reject) a null hypothesis that was true.