This document discusses statistical testing and levels of measurement. Statistical tests are used to determine if results are statistically significant or occurred by chance by accepting or rejecting the null hypothesis. Choosing the correct statistical test involves determining the type of data, whether looking for a correlation or difference between variables, and the experimental design. There are four levels of measurement - nominal for categorical data where only quantity matters, ordinal for ordered data where rank but not differences matter, interval for equally spaced data where order and differences matter, and ratio for having a true zero point. The appropriate statistic to use depends on the level of measurement.
This document discusses statistical testing and levels of measurement. Statistical tests are used to determine if results are statistically significant or occurred by chance by accepting or rejecting the null hypothesis. Choosing the correct statistical test involves determining the type of data, whether looking for a correlation or difference between variables, and the experimental design. There are four levels of measurement - nominal for categorical data where only quantity matters, ordinal for ordered data where rank but not differences matter, interval for equally spaced data where order and differences matter, and ratio for having a true zero point. The appropriate statistic to use depends on the level of measurement.
This document discusses statistical testing and levels of measurement. Statistical tests are used to determine if results are statistically significant or occurred by chance by accepting or rejecting the null hypothesis. Choosing the correct statistical test involves determining the type of data, whether looking for a correlation or difference between variables, and the experimental design. There are four levels of measurement - nominal for categorical data where only quantity matters, ordinal for ordered data where rank but not differences matter, interval for equally spaced data where order and differences matter, and ratio for having a true zero point. The appropriate statistic to use depends on the level of measurement.
- Statistical testing is used to determine whether the results of an investigation are
statistically significant or whether they could have occurred by chance. - Statistical tests allow us to accept or reject the null hypothesis. - They are designed for specific purposes and so must be chosen carefully. Choosing the correct test involves 3 questions: What kind of data do you have? Are you looking for a correlation or difference between variables? What experimental design was used? Levels of measurement Nominal level Categorical data: Nominal data is discrete- data can only appear in one category Tells us little about the thing the number represents other than the quantity. Ordinal level Data is ordered in some way Numbers with ordinal level of measurement have a position in some kind of rank The order of scores matters but not the difference between values. Interval order of measurement Interval data can be ordered, and there are equal intervals between points of a scale It is the most precise form of data.
Nominal data : use the mode
Ordinal data: use median, range Interval data: use the mean, standard deviation