Question 2: Calculate confidence intervals for the regression coefficients.
Click Analyze, Regression, Linear. Select Quadriceps strength into Dependent and Height and Age into Independents(s). Now click Statistics, Confidence intervals, Continue. Click OK.
You will get four tables of output, of which the last is
| Coefficients(a) | ||||||||
|---|---|---|---|---|---|---|---|---|
| Model | Unstandardized Coefficients | Standardized Coefficients | t | Sig. | 95% Confidence Interval for B | |||
| B | Std. Error | Beta | Lower Bound | Upper Bound | ||||
| 1 | (Constant) | -465.626 | 460.333 | -1.011 | .318 | -1397.523 | 466.270 | |
| Height (cm) | 5.398 | 2.545 | .314 | 2.121 | .040 | .246 | 10.550 | |
| Age (years) | -3.075 | 1.467 | -.311 | -2.096 | .043 | -6.046 | -.105 | |
| a. Dependent Variable: Quadriceps strength (newtons) | ||||||||
The confidence intervals appear in the table.
The coefficient for height can now be written 5.40 newtons/cm, 95% CI 0.25 to 10.55 newtons/cm, P=0.04. The coefficient for age can now be written −3.08 newtons/year, 95% CI −6.05 to −0.11 newtons/year, P=0.04.
I have given the confidence limits to the same number of decimal places as the coefficients.
Note that I put in leading zeros for nmbers between −1 and +1. Lazy programmers (like me) usually leave these out, but in a report we should include them. They make the numbers easier to read.
I have also included the units for the coefficients.
Back to Exercise: Multiple regression of muscle strength on age and height.
To Applied Biostatistics index.
To Martin Bland's M.Sc. index.
This page maintained by Martin Bland.
Last updated: 21 February, 2012.