how to calculate aic of normally distributed pdf?

how to calculate Akaike information criterion (AIC) a of normally distributed pdf?

[the cyclist]

A distribution does not have an AIC.

Do you mean you have data that you fit a normal distribution to, and want to know the AIC?

[Lalit Upadhyaya]

yes, I have data that fit a normal distribution and I want to calculate AIC.

[Lalit Upadhyaya]

Here is the data:

m=[ 203.8 230.6 376.8 101.2 128.8 286.8 316.5 313.9 386.4 116 94.8 314.9 267.26 201.65];

[Manikanta Aditya]

Hi,

Check this calculation:

m = [203.8 230.6 376.8 101.2 128.8 286.8 316.5 313.9 386.4 116 94.8 314.9 267.26 201.65];
n = length(m); % number of data points
mu = mean(m); % mean of the data
sigma = std(m); % standard deviation of the data

% Maximum likelihood estimation
L = sum(log(normpdf(m, mu, sigma)));

% Number of parameters in the model (mu and sigma)
k = 2;

% Calculate AIC
AIC = 2*k - 2*L;

Hope this helps you.

[Sam Chak]

Hi @Lalit Upadhyaya

Could you please provide the formula for calculating the AIC (Akaike Information Criterion) value? This will allow forum users to clearly see which information can be extracted from the data and then incorporated into the AIC formula. Taking this primitive approach will help the users gain a better understanding of the calculation process.

m = [203.8 230.6 376.8 101.2 128.8 286.8 316.5 313.9 386.4 116 94.8 314.9 267.26 201.65];
stem(m), grid on

[Lalit Upadhyaya]

Suppose that we have a statistical model of some data. Let k be the number of estimated parameters in the model. Let L be the maximized value of the likelihood function for the model. Then the AIC value of the model is the following.

AIC = 2 * k − 2 * ln⁡(L)