TOPIC #9: Hypothesis Testing

Module 4 DATA1001

Hypothesis

A claim or statement that we make

Hypothesis testing

Scientific framework for assessing the evidence provided by the data to make evidence-based decisions

Null hypothesis (H₀)

assumes that the difference between the observed value (data) and the expected value (EV) is due to chance alone

Alternative hypothesis H₁)

assumes that the difference between the observed value data), and the expected value (EV) is not due to chance alone.

What does the null hypothesis describe?

The default scenario, status quo, nothing is happening, nothing new

What does the alternative hypothesis describe?

What we think is happening, or the research question to be proven

When would you use a two sided hypothesis test?

When you are interested in a deviation from the null hypothesis in any direction.

When would you use a one sided hypothesis test?

When you are interested in a deviation from the null hypothesis in only one direction.

Test statistic

measures the difference between what is observed (OV) in the data and what is expected according to the null hypothesis (EV)

test statistic formula

[Observed value (OV) - Expected value (EV)]/standard error (SE)

What hypothesis do we use to set up the box model?

Null hypothesis

what is the p-value?

the probability of observing the test statistic (or something more extreme) if H₀ is true. the p value is used to quantify ow consistent our data is with the null hypotheisis

common mistakes with the p value

the p value is not the chance that the null hypothesis is true
a large p value does not mean that the null hypothesis is true

proportion test

is used to determine if the proportion of a certain outcome in a sample differs significantly from an expected proportion

are hypotheses made with respect to the population or the sample?

population