1.Using STATA run linear regression equation for lymphocyte count as a function

Question

1.Using STATA run linear regression equation for lymphocyte count as a function of percent reticulocytes. Using the output, estimate the lymphocyte count to be if a patient had 1.5% reticulocytes?

2.The calculation from the output will have a margin of error, express your estimate with the error using the information from the regression printout.

3.What would your response to a colleague who wanted to know what the lymphocyte count would be for a patient who has 5% reticulocyte?

Table 11.19 Hematologic data for patients with aplastic anemia Patient Lymphocytes % Reticulocytes er mm2) number 2 3 4 5 6 7 8 9 3.6 2.0 0.3 0.3 0.2 3.0 0.0 1700 3078 1820 2706 2086 2299 676 2088 2013 2.2 Source: Reprinted with permission of The New England Journal of Medicine, 312(16), 1015-1022, 1985

Explanation / Answer

we can provide solution using open source statistical package R , the concepts and workings remain the same

Please see the complete snippet as follows

Reti <- c(3.6,2,.3,.3,.2,3,0,1,2.2)
Lymph <- c(1700,3078,1820,2706,2086,2299,676,2088,2013)

## fit the regression model

fit <- lm(Lymph ~ Reti)
summary(fit)

## plot
par(mfrow=c(2,2))
plot(fit)

The results are

summary(fit)

Call:
lm(formula = Lymph ~ Reti)

Residuals:
Min 1Q Median 3Q Max
-1218.82 -128.47 67.84 168.76 958.95

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1894.8 348.5 5.437 0.000969 ***
Reti 112.1 184.7 0.607 0.563109
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 700.6 on 7 degrees of freedom ### the standard error of the model as highlighted
Multiple R-squared: 0.04998,   Adjusted R-squared: -0.08574
F-statistic: 0.3683 on 1 and 7 DF, p-value: 0.5631

The regression equation is Lymph = 1894.8 +112.1*Reti

Put reti = 5 in the regression equation to get the value of Lymph

Lymph = 1894.8 +112.1*5 = 2455.3

again put reti = 1.5%

using the regression equation , 1894.8 +112.1*1.5 = 2062.95

Related Questions

Navigate

• Browse (All)
• Browse 1
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.