I am trying to run an ancova and am having trouble setting it up properly.
I have nearly 10,000 measurements of fish length, girth and stage of sexual
development. I am suspicious that the stage of development is affecting the
length (as they get full of eggs they get more round and are more difficult
to measure and measure shorter).
My data looks somethign like this:
Length
girth
stage
40
50
2
42
48
3
37
40
5
38
38
6
34
44
2
36
45
3
36
39
4
39
42
4
39
39
6
but now I am not quite sure what to do next.
I have tried this: fit<-lm(length ~ girth + stage)
summary(fit)
Residuals:
Min 1Q Median 3Q Max
-12.18198 -1.59198 -0.06057 1.50504 17.56265
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 24.97431 0.29956 83.37 <2e-16 ***
data$girth 0.24616 0.00571 43.11 <2e-16 ***
data$stage 0.67371 0.02742 24.57 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1
Residual standard error: 2.388 on 9864 degrees of freedom
(1101 observations deleted due to missingness)
Multiple R-squared: 0.1934, Adjusted R-squared: 0.1933
F-statistic: 1183 on 2 and 9864 DF, p-value: < 2.2e-16
but this has not told me anything about where the differences in length that
are attributable to sexual development lie. any suggestions?
Thank you
Jacob
[[alternative HTML version deleted]]
I am trying to run an ancova and am having trouble setting it up properly.
I have nearly 10,000 measurements of fish length, girth and stage of sexual
development. I am suspicious that the stage of development is affecting the
length (as they get full of eggs they get more round and are more difficult
to measure and measure shorter).
My data looks somethign like this:
Length
girth
stage
40
50
2
42
48
3
37
40
5
38
38
6
34
44
2
36
45
3
36
39
4
39
42
4
39
39
6
but now I am not quite sure what to do next.
I have tried this: fit<-lm(length ~ girth + stage)
summary(fit)
Residuals:
Min 1Q Median 3Q Max
-12.18198 -1.59198 -0.06057 1.50504 17.56265
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 24.97431 0.29956 83.37 <2e-16 ***
data$girth 0.24616 0.00571 43.11 <2e-16 ***
data$stage 0.67371 0.02742 24.57 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1
Residual standard error: 2.388 on 9864 degrees of freedom
(1101 observations deleted due to missingness)
Multiple R-squared: 0.1934, Adjusted R-squared: 0.1933
F-statistic: 1183 on 2 and 9864 DF, p-value: < 2.2e-16
but this has not told me anything about where the differences in length that
are attributable to sexual development lie. any suggestions?
Thank you
Jacob
[[alternative HTML version deleted]]