June 6 data analysis notes

[JoeyBernhardt]

weird things happen in data analysis of dapnia respiration rates:

When I calculate the slope using the oxygen in mg I get a slope of -0.57:

Call:
lm(formula = log(oxygen_in_mg) ~ temp.kelvin, data = resp.k)

Residuals:
     Min       1Q   Median       3Q      Max 
-2.97492 -0.17970  0.08528  0.37809  1.72083 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  18.6101     5.1711   3.599  0.00067 ***
temp.kelvin  -0.5708     0.1295  -4.407 4.68e-05 ***

---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.6509 on 57 degrees of freedom
Multiple R-squared:  0.2542,    Adjusted R-squared:  0.2411 
F-statistic: 19.42 on 1 and 57 DF,  p-value: 4.682e-05

but when I calculate the slope using torr, I get a slope of -.71:

Call:
lm(formula = log(mean) ~ temp.kelvin, data = resp.mass)

Residuals:
     Min       1Q   Median       3Q      Max 
-2.97650 -0.18143  0.08371  0.37644  1.72314 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  27.0159     5.1755   5.220 2.61e-06 ***
temp.kelvin  -0.7115     0.1296  -5.489 9.73e-07 ***

---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.6514 on 57 degrees of freedom
Multiple R-squared:  0.3458,    Adjusted R-squared:  0.3343 
F-statistic: 30.12 on 1 and 57 DF,  p-value: 9.732e-07

I don't know why???