# Proportions

To determine if there is a significant difference between proportion. A portions is a data set with only good or false results (Nominal Scale). For example a portions of 90% with a samples size of 200 is 180 good and 20 false results.

## 1 sample Proportion test

To determine the significant difference between an Hypothesized proportion and a measured proportion.

### Interpretation

• The smaller the p value is the more likely there is a significant difference between the proportion and the hypothesized proportion.
• Develve uses the commonly accepted value of p < 0.05 for significance.
• For a good power (0.8 in Develve) the sample size for both data sets must be bigger than the minimum sample size calculated.

### Colors of the cells

• Green
No significant difference
• Yellow
Significant difference
• Orange
Sample size to small

### Formula With the z value can the program interpolate the p value out of the z table.

### Sample size

#### Not Equal #### Bigger/smaller ## 2 sample Proportions test

To determine the significant difference between an two different proportions.

### Interpretation

• The smaller the p value is the more likely there is a significant difference between the 2 proportions.
• In Develve for proportions a significant difference the p value must be below 0.05.
• For a good power (0.8 in Develve) the sample size for both data-sets must be bigger than the minimum sample size calculated.

### Colors of the cells

• Green
No significant difference
• Yellow
Significant difference
• Orange
Sample size to small

### Formula With the z value can the program interpolate the p value out of the z table.

### Sample size

#### Not Equal #### Bigger/smaller ## Legend

n = n
x = amount of positive/negative situations
p = n-x
q = 1-p = Hypothesized proportion = Proportion a = Proportion b