CAL 1 Flashcards
What is the definition of standard deviation
Standard deviation is a measure of how scattered the data is
What does a probability distribution describe
describes how a value will change when measured on a group of people
what shape does a normal distribution have
bell shaped curve
What does the mean correspond to on the normal distribution curve
the highest point
what properties does the normal distribution have
68% of all values lie within 1 standard deviation above and below the mean
90% of all values lie within 1.64 standard deviations below and above the mean
95% of all values lie between 1.96 standard deviations below and above the mean
How do you work out the upper and lower bound (the 68% range)
Lower bound = Mean - Standard deviation
Upper bound = mean + Standard deviation
- the answers that you get for these are the answers that are in 68% of the range
- mean that below the lower bound is 16% of figures and above the upper bound is 16% of figures
how do you work out the upper and lower bound for the 90% range
Lower bound = Mean - (1.64 x standard deviation)
Upper bound = Mean + (1.64 x Standard deviation)
- the answers that you get for these are the answers of the 90% range, range that 90% of figures fall in to
- below the lower bound 5% of figures fall
- above the upper bound 5% of figures are
How do you work out the upper and lower bound for the 95% range
Lower bound = Mean - (1.96 x standard deviation)
Upper bound = Mean + (1.96 x Standard deviation)
- the answers that you get for these are the answers of the 95% range, the range that 95% of figures fall into
- below the lower bound 2.5% of figures fall
- above the upper bound 2.5% of figures are
what range is the widest, 68%, 90% or 95%
95%
What is the standard error
a measure of spread of the mean value from a group of sample
How do you work out the standard error
standard deviation/ square root of n (n is the number of people in the study)
what is the confidence interval
95% confidence interval = mean +/- (1.96 x Standard Error)
what confidence interval is the widest out of 68, 95, 99%
99%
how do you calculate the 68, 95 and 99% confidence interval
+/- means upper and lower boundaries, - for lower bounds and plus for upper boundaries
68% = mean +/- (1 x Standard error) 95% = mean +/- (1.96 x Standard Error) 99% = mean +/- (2.58 x Standard Error)
a decreasing standard deviation makes the curve …
tighter and closer together
if the standard deviation remains the same and the mean decreases the curve…
remains the same shape
- moves towards the left
if the standard deviation increases and the mean remains the same …
the 95% range becomes wider
What is a confidence interval for the difference in means used
used to say whether the difference between two groups is statistically different or not
How do you calculate the confidence interval for the difference in means
95% interval = difference in means +/- (1.96 x standard error of difference)
what does standard error of difference equal
the square root of the standard error of group 1 plus the square root of the standard error of the other group
why is a difference not significantly different
the confidence interval equals 0
- indicates no difference between the two groups
what can changes in the placebo group be caused by
chance placebo effect effect of time other effects - the real group can also be caused by all of these and the actual effect of the stimulus
How do you make the standard error for the difference in changes
add the standard error of the two groups together
what is the mean change in the between two groups
mean of groups 1 - mean of group 2
What is a P value
the p-value or probability value is the probability of obtaining test results at least as extreme as the results actually observed during the test, assuming that the null hypothesis is correct
if the P value is less than 0.05% what does this mean
enough evidence to show something is biased or chance
what is a two sided P value
A two-tailed test will test both if the mean is significantly greater than x and if the mean significantly less than x.
How does sample size effect P value
if the difference in mean and standard deviation are the same, increasing the sample size decreases the P value
the smaller the mean…
the bigger the sample size needed to show that the P value is not due to chance alone
If the sample size increases but the mean and standard deviation remain the same, the confidence mean gets wider, true or false?
false
