masthead
 

Model 1 (Fig. 12.3) using PROC REG

DATA PATHS;
INPUT FLR NPR NND /* variables (abbreviations in Table 12.1) */
APH PPF PROPFS;
FLR = LOG(FLR); /* transform variables */
NPR = SQRT(NPR);
NND = LOG(NND);
ASPROPFS = ARSIN(SQRT(PROPFS));
CARDS; /* raw data would be here (6 columns for 139 plants) */

 

PROC CORR COV; /* request correlation and covariance matrices, using list-wise deletion */
VAR FLR NPR NND APH PPF ASPROPFS;

PROC REG; /* regression for approaches */
MODEL APH = FLR NPR NND/STB; /* "STB" requests standardized output */
OUTPUT OUT=A P=PRED R=RESID; /* store residual and predicted values */
PROC UNIVARIATE PLOT NORMAL;
VAR RESID; /* check normality of residuals */
PROC PLOT; PLOT PRED*RESID; /* check for heteroscedasticity */
PROC REG DATA = PATHS;
MODEL PPF = FLR NPR NND APH/STB; /* regression for probes per flower per hour */
MODEL ASPROPFS = APH PPF NND/STB; /* regression for proportion fruit set */

*** Statements similar to those in the regression for APH could be used to
check normality and heteroscedasticity, but for brevity are omitted. ***



Website Terms and Conditions and Privacy Policy
Please send comments or suggestions about this Website to custserv.us@oup.com        
cover