Select the analysis options for Probit Analysis

Stat > Reliability/Survival > Probit Analysis > Options

Model parameters

  • Estimate model parameters:
    Use starting estimates
    If you have starting estimates, enter one column to apply to all the response variables, or enter a separate column for each response variable. Each column must contain one value for each coefficient in the regression table, in the order that the coefficients appear in the regression table.
    The maximum likelihood solution may not converge if the starting estimates are not in the neighborhood of the true solution. If the algorithm does not converge to a solution, specify what you think are good starting values. For more information, go to Entering values for estimated model parameters.
    Maximum number of iterations
    Enter a positive integer to specify the maximum number of iterations for the maximum likelihood method. The default value is 20. Minitab uses the modified Newton-Raphson algorithm, a recursive method, to calculate the maximum likelihood estimates. If Minitab reaches the maximum number of iterations before convergence, the command terminates.
  • Use historical estimates: Select to enter your own estimates for the model parameters. Enter one column to apply to all the response variables, or enter a separate column for each response variable. Each column must contain one value for each coefficient in the regression table, in the order that the coefficients appear in the regression table.

    You can use historical estimates to cross-validate the model with an independent sample. For more information, go to Entering values for estimated model parameters.

Natural Response Rate

Indicate how you want Minitab to calculate the natural response rate, which is the probability that a unit fails without being exposed to any of the stress. If you do not select an option to estimate the natural response rate from the data or to set its value, Minitab assumes that the natural response rate is 0.
Estimate from data
Estimate the natural response rate from the sample data. If you select this option, you can enter a starting value for the estimate (see the following option).
Set value
Enter a value to either set the natural response rate at a fixed value, or to indicate a starting point for an estimate of the natural response rate. You might set the rate if you have a historical estimate from past data. If you do not select Estimate from data, then Minitab uses the value that you enter as the natural response rate. If you select Estimate from data, then Minitab uses the value that you enter as a starting value for the algorithm that estimates the natural response rate.

Reference Options

Event
If you have response/frequency data, you can enter a value to define the occurrence of an event. For example, if a response of F indicates a failure and a response of S indicates survival, you can enter F to define the failure as the event. If you do not enter a value, Minitab uses the highest value in the column to define the event. By default, the rank of text values is determined by alphabetical order.
Reference factor level
If you have a factor, you can enter a reference level for the factor. The estimated coefficients are interpreted relative to this level. By default, Minitab uses the lowest value in the factor column for the reference level. By default, the rank of text values is determined by alphabetical order.

Option for Hosmer-Lemeshow Test

Number of groups
Enter the number of groups for the Hosmer-Lemeshow goodness-of-fit test. By default, this test bins the data into 10 groups, which works well for most data. However, if you have a small or large number of distinct factor/covariate patterns, you may want to adjust the number of groups. Hosmer and Lemeshow suggest using a minimum of 6 groups.
Important

To display the Hosmer-Lemeshow goodness-of-fit test results, you must select the option to display all results in the Results subdialog box.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy