In general, the answer is no, both negative and positive z score values should be expected. A z-score (or standardize score) is the raw data value minus the mean and then this result divided by the standard deviation. If the data can be considered normally distributed and a random sample is taken from a population, then as the sample size becomes large, approximately half the z-scores should be negative and half of the z-scores should be positive. There are some exceptions. Small data sets may have only positive values. A non-normal (skewed) distribution if skewed to the right, may have, after normalizing, may have a higher portion of z scores as positives.
Chat with our AI personalities
No it is not.
A negative z-score indicates that the observed value (or statistic) was below the mean. In non-directional tests, a negative z-score is just as likely as a positive one.
No. If the underlying distribution is approximately Normal then 1.4 is not at all unusual.
In the same way that you would convert a positive z-score. Only leave a negative sign in front of it.
The sign of the z score is negative if the observation was below the mean and positive if it was greater.