2. Missing at random (MAR) mild: The probability of being missing in X depended on the value of Y, and was determined using the logistic regression specification logit p(X is missing) = ζ + ηY.
We modeled the probability that a SNP s in block b was an associated SNP, π s b, given the functional data for that SNP, F s b, using the logistic regression model logit(π s b )= α+ F s b β.
Ordinal regression using the cumulative logit model [ 26] was conducted to identify factors associated with the knowledge level.
We analysed responses to the choice tasks by multinomial logistic regression using the aggregate logit function in CBC for SSI Web software (Sawtooth Software , Inc Orem, Utah, USA).
Stata estimates a logistic regression model using the logit function, which reports the regression coefficients, measured in logged odds.
Logistic regression is essentially ordinary regression using the logit, or the log-odds of any particular species within a family being threatened (T), as the response variable.
Binary variables were predicted using simple logistic regression (logit GLM), continuous variables (features 3, 6, 24, 27) were predicted using a Gaussian GLM.
Finally, we fitted a logistic regression model using the following: Logit = β0 + β1 × (expanded SAPS II) + β2 × log([expanded SAPS II] + 1) Where β0, β1 and β2 are the model parameters.
The outcome correctness (yes/no) on diagnostic information (both total and partial correctness categorized as "yes") was modelled using logistic regression (using the logit and glamm commands in Stata).
The influence of baseline parameters on the abstinence rate was tested by means of a logistic regression analysis (SAS ProcLogistic using the binary logit model).
Stepwise logistic regression using the logit-model with 95% CI (confidence interval) and ordinal regression were employed for multivariate analyses.
